@@ -1204,7 +1204,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
*/
smp_rmb();
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
write_fault, &writable, NULL);
if (pfn == KVM_PFN_ERR_HWPOISON) {
kvm_send_hwpoison_signal(hva, vma_shift);
@@ -598,7 +598,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
write_ok = true;
} else {
/* Call KVM generic code to do the slow-path check */
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
writing, &write_ok, NULL);
if (is_error_noslot_pfn(pfn))
return -EFAULT;
@@ -845,7 +845,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
unsigned long pfn;
/* Call KVM generic code to do the slow-path check */
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
writing, upgrade_p, NULL);
if (is_error_noslot_pfn(pfn))
return -EFAULT;
@@ -3134,8 +3134,13 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *
send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk);
}
-static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
+static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
{
+ if (is_sigpending_pfn(pfn)) {
+ kvm_handle_signal_exit(vcpu);
+ return -EINTR;
+ }
+
/*
* Do not cache the mmio info caused by writing the readonly gfn
* into the spte otherwise read access on readonly gfn also can
@@ -3157,7 +3162,7 @@ static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fau
{
/* The pfn is invalid, report the error! */
if (unlikely(is_error_pfn(fault->pfn)))
- return kvm_handle_bad_page(vcpu, fault->gfn, fault->pfn);
+ return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn);
if (unlikely(!fault->slot)) {
gva_t gva = fault->is_tdp ? 0 : fault->addr;
@@ -4155,7 +4160,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
}
async = false;
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
+ fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
fault->write, &fault->map_writable,
&fault->hva);
if (!async)
@@ -4172,7 +4177,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
}
}
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, NULL,
+ fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, NULL,
fault->write, &fault->map_writable,
&fault->hva);
return RET_PF_CONTINUE;
@@ -96,6 +96,7 @@
#define KVM_PFN_ERR_FAULT (KVM_PFN_ERR_MASK)
#define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1)
#define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2)
+#define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3)
/*
* error pfns indicate that the gfn is in slot but faild to
@@ -106,6 +107,15 @@ static inline bool is_error_pfn(kvm_pfn_t pfn)
return !!(pfn & KVM_PFN_ERR_MASK);
}
+/*
+ * KVM_PFN_ERR_SIGPENDING indicates that fetching the PFN was interrupted
+ * by a pending signal. Note, the signal may or may not be fatal.
+ */
+static inline bool is_sigpending_pfn(kvm_pfn_t pfn)
+{
+ return pfn == KVM_PFN_ERR_SIGPENDING;
+}
+
/*
* error_noslot pfns indicate that the gfn can not be
* translated to pfn - it is not in slot or failed to
@@ -1141,8 +1151,8 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn);
kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn);
kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
- bool atomic, bool *async, bool write_fault,
- bool *writable, hva_t *hva);
+ bool atomic, bool interruptible, bool *async,
+ bool write_fault, bool *writable, hva_t *hva);
void kvm_release_pfn_clean(kvm_pfn_t pfn);
void kvm_release_pfn_dirty(kvm_pfn_t pfn);
@@ -2498,7 +2498,7 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
* 1 indicates success, -errno is returned if error is detected.
*/
static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
- bool *writable, kvm_pfn_t *pfn)
+ bool interruptible, bool *writable, kvm_pfn_t *pfn)
{
unsigned int flags = FOLL_HWPOISON;
struct page *page;
@@ -2513,6 +2513,8 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
flags |= FOLL_WRITE;
if (async)
flags |= FOLL_NOWAIT;
+ if (interruptible)
+ flags |= FOLL_INTERRUPTIBLE;
npages = get_user_pages_unlocked(addr, 1, &page, flags);
if (npages != 1)
@@ -2622,6 +2624,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
* Pin guest page in memory and return its pfn.
* @addr: host virtual address which maps memory to the guest
* @atomic: whether this function can sleep
+ * @interruptible: whether the process can be interrupted by non-fatal signals
* @async: whether this function need to wait IO complete if the
* host page is not in the memory
* @write_fault: whether we should get a writable host page
@@ -2632,8 +2635,8 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
* 2): @write_fault = false && @writable, @writable will tell the caller
* whether the mapping is writable.
*/
-kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
- bool write_fault, bool *writable)
+kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
+ bool *async, bool write_fault, bool *writable)
{
struct vm_area_struct *vma;
kvm_pfn_t pfn;
@@ -2648,9 +2651,12 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
if (atomic)
return KVM_PFN_ERR_FAULT;
- npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn);
+ npages = hva_to_pfn_slow(addr, async, write_fault, interruptible,
+ writable, &pfn);
if (npages == 1)
return pfn;
+ if (npages == -EINTR)
+ return KVM_PFN_ERR_SIGPENDING;
mmap_read_lock(current->mm);
if (npages == -EHWPOISON ||
@@ -2681,8 +2687,8 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
}
kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
- bool atomic, bool *async, bool write_fault,
- bool *writable, hva_t *hva)
+ bool atomic, bool interruptible, bool *async,
+ bool write_fault, bool *writable, hva_t *hva)
{
unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
@@ -2707,7 +2713,7 @@ kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
writable = NULL;
}
- return hva_to_pfn(addr, atomic, async, write_fault,
+ return hva_to_pfn(addr, atomic, interruptible, async, write_fault,
writable);
}
EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
@@ -2715,20 +2721,22 @@ EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable)
{
- return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
- write_fault, writable, NULL);
+ return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, false,
+ NULL, write_fault, writable, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
{
- return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL);
+ return __gfn_to_pfn_memslot(slot, gfn, false, false, NULL, true,
+ NULL, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn)
{
- return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL);
+ return __gfn_to_pfn_memslot(slot, gfn, true, false, NULL, true,
+ NULL, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
@@ -24,8 +24,8 @@
#define KVM_MMU_READ_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock)
#endif /* KVM_HAVE_MMU_RWLOCK */
-kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
- bool write_fault, bool *writable);
+kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
+ bool *async, bool write_fault, bool *writable);
#ifdef CONFIG_HAVE_KVM_PFNCACHE
void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
@@ -181,7 +181,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
}
/* We always request a writeable mapping */
- new_pfn = hva_to_pfn(gpc->uhva, false, NULL, true, NULL);
+ new_pfn = hva_to_pfn(gpc->uhva, false, false, NULL, true, NULL);
if (is_error_noslot_pfn(new_pfn))
goto out_error;
Add one new PFN error type to show when KVM got interrupted when fetching the PFN due to any kind of signal pending. Add a new "interruptible" flag showing that the caller is willing to be interrupted by signals during the __gfn_to_pfn_memslot() request. Wire it up with a FOLL_INTERRUPTIBLE flag that we've just introduced. This prepares KVM to be able to respond to SIGUSR1 (for QEMU that's the SIGIPI) even during e.g. handling an userfaultfd page fault. Since at it, renaming kvm_handle_bad_page to kvm_handle_error_pfn assuming that'll match better with what it does, e.g. KVM_PFN_ERR_SIGPENDING is not accurately a bad page but just one kind of errors. No functional change intended so far with the patch. Signed-off-by: Peter Xu <peterx@redhat.com> --- arch/arm64/kvm/mmu.c | 2 +- arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 +- arch/powerpc/kvm/book3s_64_mmu_radix.c | 2 +- arch/x86/kvm/mmu/mmu.c | 13 +++++++---- include/linux/kvm_host.h | 14 ++++++++++-- virt/kvm/kvm_main.c | 30 ++++++++++++++++---------- virt/kvm/kvm_mm.h | 4 ++-- virt/kvm/pfncache.c | 2 +- 8 files changed, 46 insertions(+), 23 deletions(-)