linux/arch/x86/kvm/iommu.c
Linus Torvalds 221bb8a46e - ARM: GICv3 ITS emulation and various fixes. Removal of the old
VGIC implementation.
 
 - s390: support for trapping software breakpoints, nested virtualization
 (vSIE), the STHYI opcode, initial extensions for CPU model support.
 
 - MIPS: support for MIPS64 hosts (32-bit guests only) and lots of cleanups,
 preliminary to this and the upcoming support for hardware virtualization
 extensions.
 
 - x86: support for execute-only mappings in nested EPT; reduced vmexit
 latency for TSC deadline timer (by about 30%) on Intel hosts; support for
 more than 255 vCPUs.
 
 - PPC: bugfixes.
 
 The ugly bit is the conflicts.  A couple of them are simple conflicts due
 to 4.7 fixes, but most of them are with other trees. There was definitely
 too much reliance on Acked-by here.  Some conflicts are for KVM patches
 where _I_ gave my Acked-by, but the worst are for this pull request's
 patches that touch files outside arch/*/kvm.  KVM submaintainers should
 probably learn to synchronize better with arch maintainers, with the
 latter providing topic branches whenever possible instead of Acked-by.
 This is what we do with arch/x86.  And I should learn to refuse pull
 requests when linux-next sends scary signals, even if that means that
 submaintainers have to rebase their branches.
 
 Anyhow, here's the list:
 
 - arch/x86/kvm/vmx.c: handle_pcommit and EXIT_REASON_PCOMMIT was removed
 by the nvdimm tree.  This tree adds handle_preemption_timer and
 EXIT_REASON_PREEMPTION_TIMER at the same place.  In general all mentions
 of pcommit have to go.
 
 There is also a conflict between a stable fix and this patch, where the
 stable fix removed the vmx_create_pml_buffer function and its call.
 
 - virt/kvm/kvm_main.c: kvm_cpu_notifier was removed by the hotplug tree.
 This tree adds kvm_io_bus_get_dev at the same place.
 
 - virt/kvm/arm/vgic.c: a few final bugfixes went into 4.7 before the
 file was completely removed for 4.8.
 
 - include/linux/irqchip/arm-gic-v3.h: this one is entirely our fault;
 this is a change that should have gone in through the irqchip tree and
 pulled by kvm-arm.  I think I would have rejected this kvm-arm pull
 request.  The KVM version is the right one, except that it lacks
 GITS_BASER_PAGES_SHIFT.
 
 - arch/powerpc: what a mess.  For the idle_book3s.S conflict, the KVM
 tree is the right one; everything else is trivial.  In this case I am
 not quite sure what went wrong.  The commit that is causing the mess
 (fd7bacbca4, "KVM: PPC: Book3S HV: Fix TB corruption in guest exit
 path on HMI interrupt", 2016-05-15) touches both arch/powerpc/kernel/
 and arch/powerpc/kvm/.  It's large, but at 396 insertions/5 deletions
 I guessed that it wasn't really possible to split it and that the 5
 deletions wouldn't conflict.  That wasn't the case.
 
 - arch/s390: also messy.  First is hypfs_diag.c where the KVM tree
 moved some code and the s390 tree patched it.  You have to reapply the
 relevant part of commits 6c22c98637, plus all of e030c1125e, to
 arch/s390/kernel/diag.c.  Or pick the linux-next conflict
 resolution from http://marc.info/?l=kvm&m=146717549531603&w=2.
 Second, there is a conflict in gmap.c between a stable fix and 4.8.
 The KVM version here is the correct one.
 
 I have pushed my resolution at refs/heads/merge-20160802 (commit
 3d1f53419842) at git://git.kernel.org/pub/scm/virt/kvm/kvm.git.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQEcBAABAgAGBQJXoGm7AAoJEL/70l94x66DugQIAIj703ePAFepB/fCrKHkZZia
 SGrsBdvAtNsOhr7FQ5qvvjLxiv/cv7CymeuJivX8H+4kuUHUllDzey+RPHYHD9X7
 U6n1PdCH9F15a3IXc8tDjlDdOMNIKJixYuq1UyNZMU6NFwl00+TZf9JF8A2US65b
 x/41W98ilL6nNBAsoDVmCLtPNWAqQ3lajaZELGfcqRQ9ZGKcAYOaLFXHv2YHf2XC
 qIDMf+slBGSQ66UoATnYV2gAopNlWbZ7n0vO6tE2KyvhHZ1m399aBX1+k8la/0JI
 69r+Tz7ZHUSFtmlmyByi5IAB87myy2WQHyAPwj+4vwJkDGPcl0TrupzbG7+T05Y=
 =42ti
 -----END PGP SIGNATURE-----

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:

 - ARM: GICv3 ITS emulation and various fixes.  Removal of the
   old VGIC implementation.

 - s390: support for trapping software breakpoints, nested
   virtualization (vSIE), the STHYI opcode, initial extensions
   for CPU model support.

 - MIPS: support for MIPS64 hosts (32-bit guests only) and lots
   of cleanups, preliminary to this and the upcoming support for
   hardware virtualization extensions.

 - x86: support for execute-only mappings in nested EPT; reduced
   vmexit latency for TSC deadline timer (by about 30%) on Intel
   hosts; support for more than 255 vCPUs.

 - PPC: bugfixes.

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (302 commits)
  KVM: PPC: Introduce KVM_CAP_PPC_HTM
  MIPS: Select HAVE_KVM for MIPS64_R{2,6}
  MIPS: KVM: Reset CP0_PageMask during host TLB flush
  MIPS: KVM: Fix ptr->int cast via KVM_GUEST_KSEGX()
  MIPS: KVM: Sign extend MFC0/RDHWR results
  MIPS: KVM: Fix 64-bit big endian dynamic translation
  MIPS: KVM: Fail if ebase doesn't fit in CP0_EBase
  MIPS: KVM: Use 64-bit CP0_EBase when appropriate
  MIPS: KVM: Set CP0_Status.KX on MIPS64
  MIPS: KVM: Make entry code MIPS64 friendly
  MIPS: KVM: Use kmap instead of CKSEG0ADDR()
  MIPS: KVM: Use virt_to_phys() to get commpage PFN
  MIPS: Fix definition of KSEGX() for 64-bit
  KVM: VMX: Add VMCS to CPU's loaded VMCSs before VMPTRLD
  kvm: x86: nVMX: maintain internal copy of current VMCS
  KVM: PPC: Book3S HV: Save/restore TM state in H_CEDE
  KVM: PPC: Book3S HV: Pull out TM state save/restore into separate procedures
  KVM: arm64: vgic-its: Simplify MAPI error handling
  KVM: arm64: vgic-its: Make vgic_its_cmd_handle_mapi similar to other handlers
  KVM: arm64: vgic-its: Turn device_id validation into generic ID validation
  ...
2016-08-02 16:11:27 -04:00

357 lines
8.2 KiB
C

/*
* Copyright (c) 2006, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, write to the Free Software Foundation, Inc., 59 Temple
* Place - Suite 330, Boston, MA 02111-1307 USA.
*
* Copyright (C) 2006-2008 Intel Corporation
* Copyright IBM Corporation, 2008
* Copyright 2010 Red Hat, Inc. and/or its affiliates.
*
* Author: Allen M. Kay <allen.m.kay@intel.com>
* Author: Weidong Han <weidong.han@intel.com>
* Author: Ben-Ami Yassour <benami@il.ibm.com>
*/
#include <linux/list.h>
#include <linux/kvm_host.h>
#include <linux/moduleparam.h>
#include <linux/pci.h>
#include <linux/stat.h>
#include <linux/iommu.h>
#include "assigned-dev.h"
static bool allow_unsafe_assigned_interrupts;
module_param_named(allow_unsafe_assigned_interrupts,
allow_unsafe_assigned_interrupts, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(allow_unsafe_assigned_interrupts,
"Enable device assignment on platforms without interrupt remapping support.");
static int kvm_iommu_unmap_memslots(struct kvm *kvm);
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages);
static kvm_pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
unsigned long npages)
{
gfn_t end_gfn;
kvm_pfn_t pfn;
pfn = gfn_to_pfn_memslot(slot, gfn);
end_gfn = gfn + npages;
gfn += 1;
if (is_error_noslot_pfn(pfn))
return pfn;
while (gfn < end_gfn)
gfn_to_pfn_memslot(slot, gfn++);
return pfn;
}
static void kvm_unpin_pages(struct kvm *kvm, kvm_pfn_t pfn,
unsigned long npages)
{
unsigned long i;
for (i = 0; i < npages; ++i)
kvm_release_pfn_clean(pfn + i);
}
int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
{
gfn_t gfn, end_gfn;
kvm_pfn_t pfn;
int r = 0;
struct iommu_domain *domain = kvm->arch.iommu_domain;
int flags;
/* check if iommu exists and in use */
if (!domain)
return 0;
gfn = slot->base_gfn;
end_gfn = gfn + slot->npages;
flags = IOMMU_READ;
if (!(slot->flags & KVM_MEM_READONLY))
flags |= IOMMU_WRITE;
if (!kvm->arch.iommu_noncoherent)
flags |= IOMMU_CACHE;
while (gfn < end_gfn) {
unsigned long page_size;
/* Check if already mapped */
if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
gfn += 1;
continue;
}
/* Get the page size we could use to map */
page_size = kvm_host_page_size(kvm, gfn);
/* Make sure the page_size does not exceed the memslot */
while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
page_size >>= 1;
/* Make sure gfn is aligned to the page size we want to map */
while ((gfn << PAGE_SHIFT) & (page_size - 1))
page_size >>= 1;
/* Make sure hva is aligned to the page size we want to map */
while (__gfn_to_hva_memslot(slot, gfn) & (page_size - 1))
page_size >>= 1;
/*
* Pin all pages we are about to map in memory. This is
* important because we unmap and unpin in 4kb steps later.
*/
pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT);
if (is_error_noslot_pfn(pfn)) {
gfn += 1;
continue;
}
/* Map into IO address space */
r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
page_size, flags);
if (r) {
printk(KERN_ERR "kvm_iommu_map_address:"
"iommu failed to map pfn=%llx\n", pfn);
kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT);
goto unmap_pages;
}
gfn += page_size >> PAGE_SHIFT;
cond_resched();
}
return 0;
unmap_pages:
kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
return r;
}
static int kvm_iommu_map_memslots(struct kvm *kvm)
{
int idx, r = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
if (kvm->arch.iommu_noncoherent)
kvm_arch_register_noncoherent_dma(kvm);
idx = srcu_read_lock(&kvm->srcu);
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
r = kvm_iommu_map_pages(kvm, memslot);
if (r)
break;
}
srcu_read_unlock(&kvm->srcu, idx);
return r;
}
int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev)
{
struct iommu_domain *domain = kvm->arch.iommu_domain;
int r;
bool noncoherent;
/* check if iommu exists and in use */
if (!domain)
return 0;
if (pdev == NULL)
return -ENODEV;
r = iommu_attach_device(domain, &pdev->dev);
if (r) {
dev_err(&pdev->dev, "kvm assign device failed ret %d", r);
return r;
}
noncoherent = !iommu_capable(&pci_bus_type, IOMMU_CAP_CACHE_COHERENCY);
/* Check if need to update IOMMU page table for guest memory */
if (noncoherent != kvm->arch.iommu_noncoherent) {
kvm_iommu_unmap_memslots(kvm);
kvm->arch.iommu_noncoherent = noncoherent;
r = kvm_iommu_map_memslots(kvm);
if (r)
goto out_unmap;
}
kvm_arch_start_assignment(kvm);
pci_set_dev_assigned(pdev);
dev_info(&pdev->dev, "kvm assign device\n");
return 0;
out_unmap:
kvm_iommu_unmap_memslots(kvm);
return r;
}
int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev)
{
struct iommu_domain *domain = kvm->arch.iommu_domain;
/* check if iommu exists and in use */
if (!domain)
return 0;
if (pdev == NULL)
return -ENODEV;
iommu_detach_device(domain, &pdev->dev);
pci_clear_dev_assigned(pdev);
kvm_arch_end_assignment(kvm);
dev_info(&pdev->dev, "kvm deassign device\n");
return 0;
}
int kvm_iommu_map_guest(struct kvm *kvm)
{
int r;
if (!iommu_present(&pci_bus_type)) {
printk(KERN_ERR "%s: iommu not found\n", __func__);
return -ENODEV;
}
mutex_lock(&kvm->slots_lock);
kvm->arch.iommu_domain = iommu_domain_alloc(&pci_bus_type);
if (!kvm->arch.iommu_domain) {
r = -ENOMEM;
goto out_unlock;
}
if (!allow_unsafe_assigned_interrupts &&
!iommu_capable(&pci_bus_type, IOMMU_CAP_INTR_REMAP)) {
printk(KERN_WARNING "%s: No interrupt remapping support,"
" disallowing device assignment."
" Re-enable with \"allow_unsafe_assigned_interrupts=1\""
" module option.\n", __func__);
iommu_domain_free(kvm->arch.iommu_domain);
kvm->arch.iommu_domain = NULL;
r = -EPERM;
goto out_unlock;
}
r = kvm_iommu_map_memslots(kvm);
if (r)
kvm_iommu_unmap_memslots(kvm);
out_unlock:
mutex_unlock(&kvm->slots_lock);
return r;
}
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages)
{
struct iommu_domain *domain;
gfn_t end_gfn, gfn;
kvm_pfn_t pfn;
u64 phys;
domain = kvm->arch.iommu_domain;
end_gfn = base_gfn + npages;
gfn = base_gfn;
/* check if iommu exists and in use */
if (!domain)
return;
while (gfn < end_gfn) {
unsigned long unmap_pages;
size_t size;
/* Get physical address */
phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
if (!phys) {
gfn++;
continue;
}
pfn = phys >> PAGE_SHIFT;
/* Unmap address from IO address space */
size = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE);
unmap_pages = 1ULL << get_order(size);
/* Unpin all pages we just unmapped to not leak any memory */
kvm_unpin_pages(kvm, pfn, unmap_pages);
gfn += unmap_pages;
cond_resched();
}
}
void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
{
kvm_iommu_put_pages(kvm, slot->base_gfn, slot->npages);
}
static int kvm_iommu_unmap_memslots(struct kvm *kvm)
{
int idx;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
idx = srcu_read_lock(&kvm->srcu);
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots)
kvm_iommu_unmap_pages(kvm, memslot);
srcu_read_unlock(&kvm->srcu, idx);
if (kvm->arch.iommu_noncoherent)
kvm_arch_unregister_noncoherent_dma(kvm);
return 0;
}
int kvm_iommu_unmap_guest(struct kvm *kvm)
{
struct iommu_domain *domain = kvm->arch.iommu_domain;
/* check if iommu exists and in use */
if (!domain)
return 0;
mutex_lock(&kvm->slots_lock);
kvm_iommu_unmap_memslots(kvm);
kvm->arch.iommu_domain = NULL;
kvm->arch.iommu_noncoherent = false;
mutex_unlock(&kvm->slots_lock);
iommu_domain_free(domain);
return 0;
}