Permalink
Browse files

Merge tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Avi Kivity:
 "Highlights of the changes for this release include support for vfio
  level triggered interrupts, improved big real mode support on older
  Intels, a streamlines guest page table walker, guest APIC speedups,
  PIO optimizations, better overcommit handling, and read-only memory."

* tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits)
  KVM: s390: Fix vcpu_load handling in interrupt code
  KVM: x86: Fix guest debug across vcpu INIT reset
  KVM: Add resampling irqfds for level triggered interrupts
  KVM: optimize apic interrupt delivery
  KVM: MMU: Eliminate pointless temporary 'ac'
  KVM: MMU: Avoid access/dirty update loop if all is well
  KVM: MMU: Eliminate eperm temporary
  KVM: MMU: Optimize is_last_gpte()
  KVM: MMU: Simplify walk_addr_generic() loop
  KVM: MMU: Optimize pte permission checks
  KVM: MMU: Update accessed and dirty bits after guest pagetable walk
  KVM: MMU: Move gpte_access() out of paging_tmpl.h
  KVM: MMU: Optimize gpte_access() slightly
  KVM: MMU: Push clean gpte write protection out of gpte_access()
  KVM: clarify kvmclock documentation
  KVM: make processes waiting on vcpu mutex killable
  KVM: SVM: Make use of asm.h
  KVM: VMX: Make use of asm.h
  KVM: VMX: Make lto-friendly
  KVM: x86: lapic: Clean up find_highest_vector() and count_vectors()
  ...

Conflicts:
	arch/s390/include/asm/processor.h
	arch/x86/kvm/i8259.c
  • Loading branch information...
torvalds committed Oct 4, 2012
2 parents ce57e98 + 3d11df7 commit ecefbd94b834fa32559d854646d777c56749ef1c
Showing with 3,006 additions and 1,466 deletions.
  1. +25 −8 Documentation/virtual/kvm/api.txt
  2. +66 −0 Documentation/virtual/kvm/hypercalls.txt
  3. +20 −12 Documentation/virtual/kvm/msr.txt
  4. +22 −0 Documentation/virtual/kvm/ppc-pv.txt
  5. +17 −24 arch/ia64/kvm/kvm-ia64.c
  6. +3 −0 arch/powerpc/include/asm/kvm_host.h
  7. +0 −1 arch/powerpc/kvm/44x_tlb.c
  8. +39 −12 arch/powerpc/kvm/book3s_64_mmu_hv.c
  9. +3 −3 arch/powerpc/kvm/book3s_hv_rm_mmu.c
  10. +1 −3 arch/powerpc/kvm/book3s_pr.c
  11. +1 −2 arch/powerpc/kvm/e500_tlb.c
  12. +13 −1 arch/powerpc/kvm/powerpc.c
  13. +1 −0 arch/s390/include/asm/processor.h
  14. +27 −0 arch/s390/kernel/dis.c
  15. +1 −0 arch/s390/kvm/Kconfig
  16. +4 −0 arch/s390/kvm/diag.c
  17. +11 −0 arch/s390/kvm/intercept.c
  18. +23 −2 arch/s390/kvm/interrupt.c
  19. +16 −1 arch/s390/kvm/kvm-s390.c
  20. +8 −1 arch/s390/kvm/priv.c
  21. +2 −0 arch/s390/kvm/sigp.c
  22. +210 −0 arch/s390/kvm/trace-s390.h
  23. +341 −0 arch/s390/kvm/trace.h
  24. +8 −13 arch/x86/Kconfig
  25. +1 −0 arch/x86/include/asm/kvm.h
  26. +33 −15 arch/x86/include/asm/kvm_emulate.h
  27. +33 −3 arch/x86/include/asm/kvm_host.h
  28. +3 −3 arch/x86/include/asm/kvm_para.h
  29. +1 −2 arch/x86/kernel/Makefile
  30. +1 −2 arch/x86/kernel/kvm.c
  31. +1 −1 arch/x86/kernel/setup.c
  32. +2 −0 arch/x86/kvm/Kconfig
  33. +1 −1 arch/x86/kvm/Makefile
  34. +7 −7 arch/x86/kvm/cpuid.c
  35. +309 −229 arch/x86/kvm/emulate.c
  36. +25 −39 arch/x86/kvm/i8254.c
  37. +5 −1 arch/x86/kvm/i8254.h
  38. +20 −50 arch/x86/kvm/i8259.c
  39. +1 −1 arch/x86/kvm/irq.h
  40. +0 −18 arch/x86/kvm/kvm_timer.h
  41. +349 −135 arch/x86/kvm/lapic.c
  42. +57 −4 arch/x86/kvm/lapic.h
  43. +184 −56 arch/x86/kvm/mmu.c
  44. +12 −13 arch/x86/kvm/mmu.h
  45. +2 −6 arch/x86/kvm/mmu_audit.c
  46. +83 −116 arch/x86/kvm/paging_tmpl.h
  47. +1 −1 arch/x86/kvm/pmu.c
  48. +30 −52 arch/x86/kvm/svm.c
  49. +0 −47 arch/x86/kvm/timer.c
  50. +97 −136 arch/x86/kvm/vmx.c
  51. +222 −162 arch/x86/kvm/x86.c
  52. +1 −0 arch/x86/kvm/x86.h
  53. +21 −4 include/linux/kvm.h
  54. +116 −29 include/linux/kvm_host.h
  55. +1 −0 kernel/jump_label.c
  56. +3 −0 virt/kvm/Kconfig
  57. +5 −6 virt/kvm/async_pf.c
  58. +146 −4 virt/kvm/eventfd.c
  59. +19 −18 virt/kvm/ioapic.c
  60. +11 −5 virt/kvm/iommu.c
  61. +14 −3 virt/kvm/irq_comm.c
  62. +327 −214 virt/kvm/kvm_main.c
@@ -857,7 +857,8 @@ struct kvm_userspace_memory_region {
};
/* for kvm_memory_region::flags */
-#define KVM_MEM_LOG_DIRTY_PAGES 1UL
+#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
+#define KVM_MEM_READONLY (1UL << 1)
This ioctl allows the user to create or modify a guest physical memory
slot. When changing an existing slot, it may be moved in the guest
@@ -873,14 +874,17 @@ It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
be identical. This allows large pages in the guest to be backed by large
pages in the host.
-The flags field supports just one flag, KVM_MEM_LOG_DIRTY_PAGES, which
-instructs kvm to keep track of writes to memory within the slot. See
-the KVM_GET_DIRTY_LOG ioctl.
+The flags field supports two flag, KVM_MEM_LOG_DIRTY_PAGES, which instructs
+kvm to keep track of writes to memory within the slot. See KVM_GET_DIRTY_LOG
+ioctl. The KVM_CAP_READONLY_MEM capability indicates the availability of the
+KVM_MEM_READONLY flag. When this flag is set for a memory region, KVM only
+allows read accesses. Writes will be posted to userspace as KVM_EXIT_MMIO
+exits.
-When the KVM_CAP_SYNC_MMU capability, changes in the backing of the memory
-region are automatically reflected into the guest. For example, an mmap()
-that affects the region will be made visible immediately. Another example
-is madvise(MADV_DROP).
+When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
+the memory region are automatically reflected into the guest. For example, an
+mmap() that affects the region will be made visible immediately. Another
+example is madvise(MADV_DROP).
It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
@@ -1946,6 +1950,19 @@ the guest using the specified gsi pin. The irqfd is removed using
the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
and kvm_irqfd.gsi.
+With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
+mechanism allowing emulation of level-triggered, irqfd-based
+interrupts. When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an
+additional eventfd in the kvm_irqfd.resamplefd field. When operating
+in resample mode, posting of an interrupt through kvm_irq.fd asserts
+the specified gsi in the irqchip. When the irqchip is resampled, such
+as from an EOI, the gsi is de-asserted and the user is notifed via
+kvm_irqfd.resamplefd. It is the user's responsibility to re-queue
+the interrupt if the device making use of it still requires service.
+Note that closing the resamplefd is not sufficient to disable the
+irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
+and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
+
4.76 KVM_PPC_ALLOCATE_HTAB
Capability: KVM_CAP_PPC_ALLOC_HTAB
@@ -0,0 +1,66 @@
+Linux KVM Hypercall:
+===================
+X86:
+ KVM Hypercalls have a three-byte sequence of either the vmcall or the vmmcall
+ instruction. The hypervisor can replace it with instructions that are
+ guaranteed to be supported.
+
+ Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
+ The hypercall number should be placed in rax and the return value will be
+ placed in rax. No other registers will be clobbered unless explicitly stated
+ by the particular hypercall.
+
+S390:
+ R2-R7 are used for parameters 1-6. In addition, R1 is used for hypercall
+ number. The return value is written to R2.
+
+ S390 uses diagnose instruction as hypercall (0x500) along with hypercall
+ number in R1.
+
+ PowerPC:
+ It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers.
+ Return value is placed in R3.
+
+ KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions'
+ property inside the device tree's /hypervisor node.
+ For more information refer to Documentation/virtual/kvm/ppc-pv.txt
+
+KVM Hypercalls Documentation
+===========================
+The template for each hypercall is:
+1. Hypercall name.
+2. Architecture(s)
+3. Status (deprecated, obsolete, active)
+4. Purpose
+
+1. KVM_HC_VAPIC_POLL_IRQ
+------------------------
+Architecture: x86
+Status: active
+Purpose: Trigger guest exit so that the host can check for pending
+interrupts on reentry.
+
+2. KVM_HC_MMU_OP
+------------------------
+Architecture: x86
+Status: deprecated.
+Purpose: Support MMU operations such as writing to PTE,
+flushing TLB, release PT.
+
+3. KVM_HC_FEATURES
+------------------------
+Architecture: PPC
+Status: active
+Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid
+used to enumerate which hypercalls are available. On PPC, either device tree
+based lookup ( which is also what EPAPR dictates) OR KVM specific enumeration
+mechanism (which is this hypercall) can be used.
+
+4. KVM_HC_PPC_MAP_MAGIC_PAGE
+------------------------
+Architecture: PPC
+Status: active
+Purpose: To enable communication between the hypervisor and guest there is a
+shared page that contains parts of supervisor visible register state.
+The guest can map this shared page to access its supervisor register through
+memory using this hypercall.
@@ -34,9 +34,12 @@ MSR_KVM_WALL_CLOCK_NEW: 0x4b564d00
time information and check that they are both equal and even.
An odd version indicates an in-progress update.
- sec: number of seconds for wallclock.
+ sec: number of seconds for wallclock at time of boot.
- nsec: number of nanoseconds for wallclock.
+ nsec: number of nanoseconds for wallclock at time of boot.
+
+ In order to get the current wallclock time, the system_time from
+ MSR_KVM_SYSTEM_TIME_NEW needs to be added.
Note that although MSRs are per-CPU entities, the effect of this
particular MSR is global.
@@ -82,20 +85,25 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01
time at the time this structure was last updated. Unit is
nanoseconds.
- tsc_to_system_mul: a function of the tsc frequency. One has
- to multiply any tsc-related quantity by this value to get
- a value in nanoseconds, besides dividing by 2^tsc_shift
+ tsc_to_system_mul: multiplier to be used when converting
+ tsc-related quantity to nanoseconds
- tsc_shift: cycle to nanosecond divider, as a power of two, to
- allow for shift rights. One has to shift right any tsc-related
- quantity by this value to get a value in nanoseconds, besides
- multiplying by tsc_to_system_mul.
+ tsc_shift: shift to be used when converting tsc-related
+ quantity to nanoseconds. This shift will ensure that
+ multiplication with tsc_to_system_mul does not overflow.
+ A positive value denotes a left shift, a negative value
+ a right shift.
- With this information, guests can derive per-CPU time by
- doing:
+ The conversion from tsc to nanoseconds involves an additional
+ right shift by 32 bits. With this information, guests can
+ derive per-CPU time by doing:
time = (current_tsc - tsc_timestamp)
- time = (time * tsc_to_system_mul) >> tsc_shift
+ if (tsc_shift >= 0)
+ time <<= tsc_shift;
+ else
+ time >>= -tsc_shift;
+ time = (time * tsc_to_system_mul) >> 32
time = time + system_time
flags: bits in this field indicate extended capabilities
@@ -174,3 +174,25 @@ following:
That way we can inject an arbitrary amount of code as replacement for a single
instruction. This allows us to check for pending interrupts when setting EE=1
for example.
+
+Hypercall ABIs in KVM on PowerPC
+=================================
+1) KVM hypercalls (ePAPR)
+
+These are ePAPR compliant hypercall implementation (mentioned above). Even
+generic hypercalls are implemented here, like the ePAPR idle hcall. These are
+available on all targets.
+
+2) PAPR hypercalls
+
+PAPR hypercalls are needed to run server PowerPC PAPR guests (-M pseries in QEMU).
+These are the same hypercalls that pHyp, the POWER hypervisor implements. Some of
+them are handled in the kernel, some are handled in user space. This is only
+available on book3s_64.
+
+3) OSI hypercalls
+
+Mac-on-Linux is another user of KVM on PowerPC, which has its own hypercall (long
+before KVM). This is supported to maintain compatibility. All these hypercalls get
+forwarded to user space. This is only useful on book3s_32, but can be used with
+book3s_64 as well.
View
@@ -924,6 +924,16 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
return 0;
}
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event)
+{
+ if (!irqchip_in_kernel(kvm))
+ return -ENXIO;
+
+ irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+ irq_event->irq, irq_event->level);
+ return 0;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -963,29 +973,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
goto out;
}
break;
- case KVM_IRQ_LINE_STATUS:
- case KVM_IRQ_LINE: {
- struct kvm_irq_level irq_event;
-
- r = -EFAULT;
- if (copy_from_user(&irq_event, argp, sizeof irq_event))
- goto out;
- r = -ENXIO;
- if (irqchip_in_kernel(kvm)) {
- __s32 status;
- status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
- irq_event.irq, irq_event.level);
- if (ioctl == KVM_IRQ_LINE_STATUS) {
- r = -EFAULT;
- irq_event.status = status;
- if (copy_to_user(argp, &irq_event,
- sizeof irq_event))
- goto out;
- }
- r = 0;
- }
- break;
- }
case KVM_GET_IRQCHIP: {
/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
struct kvm_irqchip chip;
@@ -1626,11 +1613,17 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
return;
}
-void kvm_arch_flush_shadow(struct kvm *kvm)
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
kvm_flush_remote_tlbs(kvm);
}
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *slot)
+{
+ kvm_arch_flush_shadow_all();
+}
+
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -53,6 +53,8 @@
struct kvm;
extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+extern int kvm_unmap_hva_range(struct kvm *kvm,
+ unsigned long start, unsigned long end);
extern int kvm_age_hva(struct kvm *kvm, unsigned long hva);
extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
@@ -220,6 +222,7 @@ struct revmap_entry {
#define KVMPPC_GOT_PAGE 0x80
struct kvm_arch_memory_slot {
+ unsigned long *rmap;
};
struct kvm_arch {
@@ -319,7 +319,6 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
if (is_error_page(new_page)) {
printk(KERN_ERR "Couldn't get guest page for gfn %llx!\n",
(unsigned long long)gfn);
- kvm_release_page_clean(new_page);
return;
}
hpaddr = page_to_phys(new_page);
@@ -705,7 +705,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
goto out_unlock;
hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
- rmap = &memslot->rmap[gfn - memslot->base_gfn];
+ rmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
lock_rmap(rmap);
/* Check if we might have been invalidated; let the guest retry if so */
@@ -756,9 +756,12 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
goto out_put;
}
-static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
- int (*handler)(struct kvm *kvm, unsigned long *rmapp,
- unsigned long gfn))
+static int kvm_handle_hva_range(struct kvm *kvm,
+ unsigned long start,
+ unsigned long end,
+ int (*handler)(struct kvm *kvm,
+ unsigned long *rmapp,
+ unsigned long gfn))
{
int ret;
int retval = 0;
@@ -767,22 +770,39 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
- unsigned long start = memslot->userspace_addr;
- unsigned long end;
+ unsigned long hva_start, hva_end;
+ gfn_t gfn, gfn_end;
- end = start + (memslot->npages << PAGE_SHIFT);
- if (hva >= start && hva < end) {
- gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
+ hva_start = max(start, memslot->userspace_addr);
+ hva_end = min(end, memslot->userspace_addr +
+ (memslot->npages << PAGE_SHIFT));
+ if (hva_start >= hva_end)
+ continue;
+ /*
+ * {gfn(page) | page intersects with [hva_start, hva_end)} =
+ * {gfn, gfn+1, ..., gfn_end-1}.
+ */
+ gfn = hva_to_gfn_memslot(hva_start, memslot);
+ gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
+
+ for (; gfn < gfn_end; ++gfn) {
+ gfn_t gfn_offset = gfn - memslot->base_gfn;
- ret = handler(kvm, &memslot->rmap[gfn_offset],
- memslot->base_gfn + gfn_offset);
+ ret = handler(kvm, &memslot->arch.rmap[gfn_offset], gfn);
retval |= ret;
}
}
return retval;
}
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+ int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long gfn))
+{
+ return kvm_handle_hva_range(kvm, hva, hva + 1, handler);
+}
+
static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
unsigned long gfn)
{
@@ -850,6 +870,13 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
return 0;
}
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+ if (kvm->arch.using_mmu_notifiers)
+ kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp);
+ return 0;
+}
+
static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
unsigned long gfn)
{
@@ -1009,7 +1036,7 @@ long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
unsigned long *rmapp, *map;
preempt_disable();
- rmapp = memslot->rmap;
+ rmapp = memslot->arch.rmap;
map = memslot->dirty_bitmap;
for (i = 0; i < memslot->npages; ++i) {
if (kvm_test_clear_dirty(kvm, rmapp))
Oops, something went wrong.

0 comments on commit ecefbd9

Please sign in to comment.