ARM and x86 had duplicated versions of the dma_ops structure, the
only difference is that x86 hasn't wired up the set_dma_mask,
mmap, and get_sgtable ops yet. On x86 all of them are identical
to the generic version, so they aren't needed but harmless.
All the symbols used only for xen_swiotlb_dma_ops can now be marked
static as well.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
On PVH, PVHVM, at failure in the VCPUOP_register_vcpu_info hypercall
we limit the number of cpus to to MAX_VIRT_CPUS. However, if this
failure had occurred for a cpu beyond MAX_VIRT_CPUS, we continue
to function with > MAX_VIRT_CPUS.
This leads to problems at the next save/restore cycle when there
are > MAX_VIRT_CPUS threads going into stop_machine() but coming
back up there's valid state for only the first MAX_VIRT_CPUS.
This patch pulls the excess CPUs down via cpu_down().
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
The hypercall VCPUOP_register_vcpu_info can fail. This failure is
handled by making per_cpu(xen_vcpu, cpu) point to its shared_info
slot and those without one (cpu >= MAX_VIRT_CPUS) be NULL.
For PVH/PVHVM, this is not enough, because we also need to pull
these VCPUs out of circulation.
Fix for PVH/PVHVM: on registration failure in the cpuhp prepare
callback (xen_cpu_up_prepare_hvm()), return an error to the cpuhp
state-machine so it can fail the CPU init.
Fix for PV: the registration happens before smp_init(), so, in the
failure case we clamp setup_max_cpus and limit the number of VCPUs
that smp_init() will bring-up to MAX_VIRT_CPUS.
This is functionally correct but it makes the code a bit simpler
if we get rid of this explicit clamping: for VCPUs that don't have
valid xen_vcpu, fail the CPU init in the cpuhp prepare callback
(xen_cpu_up_prepare_pv()).
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
If CONFIG_SMP is disabled, xen_setup_vcpu_info_placement() is called from
xen_setup_shared_info(). This is fine as far as boot goes, but it means
that we also call it in the restore path. This results in an OOPS
because we assign to pv_mmu_ops.read_cr2 which is __ro_after_init.
Also, though less problematically, this means we call xen_vcpu_setup()
twice at restore -- once from the vcpu info placement call and the
second time from xen_vcpu_restore().
Fix by calling xen_setup_vcpu_info_placement() at boot only.
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When Xen restores a PVHVM or PVH guest, its shared_info only holds
up to 32 CPUs. The hypercall VCPUOP_register_vcpu_info allows
us to setup per-page areas for VCPUs. This means we can boot
PVH* guests with more than 32 VCPUs. During restore the per-cpu
structure is allocated freshly by the hypervisor (vcpu_info_mfn is
set to INVALID_MFN) so that the newly restored guest can make a
VCPUOP_register_vcpu_info hypercall.
However, we end up triggering this condition in Xen:
/* Run this command on yourself or on other offline VCPUS. */
if ( (v != current) && !test_bit(_VPF_down, &v->pause_flags) )
which means we are unable to setup the per-cpu VCPU structures
for running VCPUS. The Linux PV code paths makes this work by
iterating over cpu_possible in xen_vcpu_restore() with:
1) is target CPU up (VCPUOP_is_up hypercall?)
2) if yes, then VCPUOP_down to pause it
3) VCPUOP_register_vcpu_info
4) if it was down, then VCPUOP_up to bring it back up
With Xen commit 192df6f9122d ("xen/x86: allow HVM guests to use
hypercalls to bring up vCPUs") this is available for non-PV guests.
As such first check if VCPUOP_is_up is actually possible before
trying this dance.
As most of this dance code is done already in xen_vcpu_restore()
let's make it callable on PV, PVH and PVHVM.
Based-on-patch-by: Konrad Wilk <konrad.wilk@oracle.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Largely mechanical changes to aid unification of xen_vcpu_restore()
logic for PV, PVH and PVHVM.
xen_vcpu_setup(): the only change in logic is that clamp_max_cpus()
is now handled inside the "if (!xen_have_vcpu_info_placement)" block.
xen_vcpu_restore(): code movement from enlighten_pv.c to enlighten.c.
xen_vcpu_info_reset(): pulls together all the code where xen_vcpu
is set to default.
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Lazy TLB state is currently managed in a rather baroque manner.
AFAICT, there are three possible states:
- Non-lazy. This means that we're running a user thread or a
kernel thread that has called use_mm(). current->mm ==
current->active_mm == cpu_tlbstate.active_mm and
cpu_tlbstate.state == TLBSTATE_OK.
- Lazy with user mm. We're running a kernel thread without an mm
and we're borrowing an mm_struct. We have current->mm == NULL,
current->active_mm == cpu_tlbstate.active_mm, cpu_tlbstate.state
!= TLBSTATE_OK (i.e. TLBSTATE_LAZY or 0). The current cpu is set
in mm_cpumask(current->active_mm). CR3 points to
current->active_mm->pgd. The TLB is up to date.
- Lazy with init_mm. This happens when we call leave_mm(). We
have current->mm == NULL, current->active_mm ==
cpu_tlbstate.active_mm, but that mm is only relelvant insofar as
the scheduler is tracking it for refcounting. cpu_tlbstate.state
!= TLBSTATE_OK. The current cpu is clear in
mm_cpumask(current->active_mm). CR3 points to swapper_pg_dir,
i.e. init_mm->pgd.
This patch simplifies the situation. Other than perf, x86 stops
caring about current->active_mm at all. We have
cpu_tlbstate.loaded_mm pointing to the mm that CR3 references. The
TLB is always up to date for that mm. leave_mm() just switches us
to init_mm. There are no longer any special cases for mm_cpumask,
and switch_mm() switches mms without worrying about laziness.
After this patch, cpu_tlbstate.state serves only to tell the TLB
flush code whether it may switch to init_mm instead of doing a
normal flush.
This makes fairly extensive changes to xen_exit_mmap(), which used
to look a bit like black magic.
Perf is unchanged. With or without this change, perf may behave a bit
erratically if it tries to read user memory in kernel thread context.
We should build on this patch to teach perf to never look at user
memory when cpu_tlbstate.loaded_mm != current->mm.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Rather than passing all the contents of flush_tlb_info to
flush_tlb_others(), pass a pointer to the structure directly. For
consistency, this also removes the unnecessary cpu parameter from
uv_flush_tlb_others() to make its signature match the other
*flush_tlb_others() functions.
This serves two purposes:
- It will dramatically simplify future patches that change struct
flush_tlb_info, which I'm planning to do.
- struct flush_tlb_info is an adequate description of what to do
for a local flush, too, so by reusing it we can remove duplicated
code between local and remove flushes in a future patch.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
[ Fix build warning. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There are some leftovers testing for pvh guest mode in pv-only source
files. Remove them.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When booted as pv-guest the p2m list presented by the Xen is already
mapped to virtual addresses. In dom0 case the hypervisor might make use
of 2M- or 1G-pages for this mapping. Unfortunately while being properly
aligned in virtual and machine address space, those pages might not be
aligned properly in guest physical address space.
So when trying to obtain the guest physical address of such a page
pud_pfn() and pmd_pfn() must be avoided as those will mask away guest
physical address bits not being zero in this special case.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When running as Xen pv guest X86_BUG_SYSRET_SS_ATTRS must not be set
on AMD cpus.
This bug/feature bit is kind of special as it will be used very early
when switching threads. Setting the bit and clearing it a little bit
later leaves a critical window where things can go wrong. This time
window has enlarged a little bit by using setup_clear_cpu_cap() instead
of the hypervisor's set_cpu_features callback. It seems this larger
window now makes it rather easy to hit the problem.
The proper solution is to never set the bit in case of Xen.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Juergen Gross <jgross@suse.com>
Routines that are set by xen_init_time_ops() use shared_info's
pvclock_vcpu_time_info area. This area is not properly available until
shared_info is mapped in xen_setup_shared_info().
This became especially problematic due to commit dd759d93f4 ("x86/timers:
Add simple udelay calibration") where we end up reading tsc_to_system_mul
from xen_dummy_shared_info (i.e. getting zero value) and then trying
to divide by it in pvclock_tsc_khz().
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Commit 690b7f10b4f9f ("x86/xen: use capabilities instead of fake cpuid
values for xsave") introduced a regression as it tried to make use of
the fixup feature before it being available.
Fall back to the old variant testing via cpuid().
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Commit 84d582d236 ("xen: Revert commits da72ff5bfc and
72a9b186292d") defined xen_have_vector_callback in enlighten_hvm.c.
Since guest-type-neutral code refers to this variable this causes
build failures when CONFIG_XEN_PVHVM is not defined.
Moving xen_have_vector_callback definition to enlighten.c resolves
this issue.
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
The helper xen_reboot will be called by the EFI code in a later patch.
Note that the ARM version does not yet exist and will be added in a
later patch too.
Signed-off-by: Julien Grall <julien.grall@arm.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Recent code rework that split handling ov PV, HVM and PVH guests into
separate files missed calling xen_smp_intr_init_pv() on CPU0.
Add this call.
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
Signed-off-by: Juergen Gross <jgross@suse.com>
Recent discussion (http://marc.info/?l=xen-devel&m=149192184523741)
established that commit 72a9b18629 ("xen: Remove event channel
notification through Xen PCI platform device") (and thus commit
da72ff5bfc ("partially revert "xen: Remove event channel
notification through Xen PCI platform device"")) are unnecessary and,
in fact, prevent HVM guests from booting on Xen releases prior to 4.0
Therefore we revert both of those commits.
The summary of that discussion is below:
Here is the brief summary of the current situation:
Before the offending commit (72a9b18629):
1) INTx does not work because of the reset_watches path.
2) The reset_watches path is only taken if you have Xen > 4.0
3) The Linux Kernel by default will use vector inject if the hypervisor
support. So even INTx does not work no body running the kernel with
Xen > 4.0 would notice. Unless he explicitly disabled this feature
either in the kernel or in Xen (and this can only be disabled by
modifying the code, not user-supported way to do it).
After the offending commit (+ partial revert):
1) INTx is no longer support for HVM (only for PV guests).
2) Any HVM guest The kernel will not boot on Xen < 4.0 which does
not have vector injection support. Since the only other mode
supported is INTx which.
So based on this summary, I think before commit (72a9b18629) we were
in much better position from a user point of view.
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
e820 map is updated with information from the zeropage (i.e. pvh_bootparams)
by default_machine_specific_memory_setup(). With the way things are done
now, we end up with a duplicated e820 map.
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When running as pv domain xen_cpuid() is being used instead of
native_cpuid(). In xen_cpuid() the xsave feature availability is
indicated by special casing the related cpuid leaf.
Instead of delivering fake cpuid values set or clear the cpu
capability bits for xsave instead.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When running as pv domain xen_cpuid() is being used instead of
native_cpuid(). In xen_cpuid() the x2apic feature is indicated as not
being present by special casing the related cpuid leaf.
Instead of delivering fake cpuid values clear the cpu capability bit
for x2apic instead.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When running as pv domain xen_cpuid() is being used instead of
native_cpuid(). In xen_cpuid() the mwait feature is indicated to be
present or not by special casing the related cpuid leaf.
Instead of delivering fake cpuid values use the cpu capability bit
for mwait instead.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When running as pv domain xen_cpuid() is being used instead of
native_cpuid(). In xen_cpuid() the acpi feature is indicated as not
being present by special casing the related cpuid leaf in case we
are not the initial domain.
Instead of delivering fake cpuid values clear the cpu capability bit
for acpi instead.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When running as pv domain xen_cpuid() is being used instead of
native_cpuid(). In xen_cpuid() the acc feature (thermal monitoring)
is indicated as not being present by special casing the related
cpuid leaf.
Instead of delivering fake cpuid values clear the cpu capability bit
for acc instead.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When running as pv domain xen_cpuid() is being used instead of
native_cpuid(). In xen_cpuid() the mtrr feature is indicated as not
being present by special casing the related cpuid leaf.
Instead of delivering fake cpuid values clear the cpu capability bit
for mtrr instead.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
When running as pv domain xen_cpuid() is being used instead of
native_cpuid(). In xen_cpuid() the aperf/mperf feature is indicated
as not being present by special casing the related cpuid leaf.
Instead of delivering fake cpuid values clear the cpu capability bit
for aperf/mperf instead.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
There is no need to set the same capabilities for each cpu
individually. This can easily be done for all cpus when starting the
kernel.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
For kdump to work correctly it needs the physical address of
vmcoreinfo_note. When running as dom0 this means the virtual address
has to be translated to the related machine address.
paddr_vmcoreinfo_note() is meant to do the translation via
__pa_symbol() only, but being attributed "weak" it can be replaced
easily in Xen case.
Signed-off-by: Juergen Gross <jgross@suse.com>
Tested-by: Petr Tesarik <ptesarik@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Daniel Kiper <daniel.kiper@oracle.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
After code split between PV and HVM some functions in xen_smp_ops have
xen_pv_ prefix and some only xen_ which makes them look like they're
common for both PV and HVM while they're not. Rename all the rest to
have xen_pv_ prefix.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Now everything is in place and we can move PV-only code under
CONFIG_XEN_PV. CONFIG_XEN_PV_SMP is created to support the change.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
xen_pmu_init/finish() functions are used in suspend.c and
enlighten.c, add stubs for now.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Basically, mmu.c is renamed to mmu_pv.c and some code moved out to common
mmu.c.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Basically, smp.c is renamed to smp_pv.c and some code moved out to common
smp.c. struct xen_common_irq delcaration ended up in smp.h.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Move PVHVM related code to smp_hvm.c. Drop 'static' qualifier from
xen_smp_send_reschedule(), xen_smp_send_call_function_ipi(),
xen_smp_send_call_function_single_ipi(), these functions will be moved to
common smp code when smp_pv.c is split.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Split xen_cpu_die() into xen_pv_cpu_die() and xen_hvm_cpu_die() to support
further splitting of smp.c.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Split xen_smp_prepare_boot_cpu() into xen_pv_smp_prepare_boot_cpu() and
xen_hvm_smp_prepare_boot_cpu() to support further splitting of smp.c.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
xen_smp_intr_init() and xen_smp_intr_free() have PV-specific code and as
a praparatory change to splitting smp.c we need to split these fucntions.
Create xen_smp_intr_init_pv()/xen_smp_intr_free_pv().
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Basically, enlighten.c is renamed to enlighten_pv.c and some code moved
out to common enlighten.c.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Move PVHVM related code to enlighten_hvm.c. Three functions:
xen_cpuhp_setup(), xen_reboot(), xen_emergency_restart() are shared, drop
static qualifier from them. These functions will go to common code once
it is split from enlighten.c.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Create enlighten_pvh.c by splitting off PVH related code from enlighten.c,
put it under CONFIG_XEN_PVH.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
All code to support Xen PV will get under this new option. For the
beginning, check for it in the common code.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
have_vcpu_info_placement applies to both PV and HVM and as we're going
to split the code we need to make it global.
Rename to xen_have_vcpu_info_placement.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
