summaryrefslogtreecommitdiffstats
path: root/virt
diff options
context:
space:
mode:
authorPaolo Bonzini <pbonzini@redhat.com>2022-12-06 12:27:39 -0500
committerPaolo Bonzini <pbonzini@redhat.com>2022-12-09 09:12:12 +0100
commiteb5618911af0ac069d2313b289d4c19ca3379401 (patch)
tree55f00bfaccf7aa55e0a8c074317d7e0b00a253b9 /virt
parent1e79a9e3ab96ecf8dbb8b6d237b3ae824bd79074 (diff)
parent753d734f3f347e7fc49b819472bbf61dcfc1a16f (diff)
downloadlinux-eb5618911af0ac069d2313b289d4c19ca3379401.tar.gz
linux-eb5618911af0ac069d2313b289d4c19ca3379401.tar.bz2
linux-eb5618911af0ac069d2313b289d4c19ca3379401.zip
Merge tag 'kvmarm-6.2' of https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for 6.2 - Enable the per-vcpu dirty-ring tracking mechanism, together with an option to keep the good old dirty log around for pages that are dirtied by something other than a vcpu. - Switch to the relaxed parallel fault handling, using RCU to delay page table reclaim and giving better performance under load. - Relax the MTE ABI, allowing a VMM to use the MAP_SHARED mapping option, which multi-process VMMs such as crosvm rely on. - Merge the pKVM shadow vcpu state tracking that allows the hypervisor to have its own view of a vcpu, keeping that state private. - Add support for the PMUv3p5 architecture revision, bringing support for 64bit counters on systems that support it, and fix the no-quite-compliant CHAIN-ed counter support for the machines that actually exist out there. - Fix a handful of minor issues around 52bit VA/PA support (64kB pages only) as a prefix of the oncoming support for 4kB and 16kB pages. - Add/Enable/Fix a bunch of selftests covering memslots, breakpoints, stage-2 faults and access tracking. You name it, we got it, we probably broke it. - Pick a small set of documentation and spelling fixes, because no good merge window would be complete without those. As a side effect, this tag also drags: - The 'kvmarm-fixes-6.1-3' tag as a dependency to the dirty-ring series - A shared branch with the arm64 tree that repaints all the system registers to match the ARM ARM's naming, and resulting in interesting conflicts
Diffstat (limited to 'virt')
-rw-r--r--virt/kvm/Kconfig6
-rw-r--r--virt/kvm/dirty_ring.c46
-rw-r--r--virt/kvm/kvm_main.c65
3 files changed, 103 insertions, 14 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 800f9470e36b..9fb1ff6f19e5 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -33,6 +33,12 @@ config HAVE_KVM_DIRTY_RING_ACQ_REL
bool
select HAVE_KVM_DIRTY_RING
+# Allow enabling both the dirty bitmap and dirty ring. Only architectures
+# that need to dirty memory outside of a vCPU context should select this.
+config NEED_KVM_DIRTY_RING_WITH_BITMAP
+ bool
+ depends on HAVE_KVM_DIRTY_RING
+
config HAVE_KVM_EVENTFD
bool
select EVENTFD
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index d6fabf238032..c1cd7dfe4a90 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -21,12 +21,26 @@ u32 kvm_dirty_ring_get_rsvd_entries(void)
return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
}
+bool kvm_use_dirty_bitmap(struct kvm *kvm)
+{
+ lockdep_assert_held(&kvm->slots_lock);
+
+ return !kvm->dirty_ring_size || kvm->dirty_ring_with_bitmap;
+}
+
+#ifndef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP
+bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm)
+{
+ return false;
+}
+#endif
+
static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring)
{
return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index);
}
-bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+static bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
{
return kvm_dirty_ring_used(ring) >= ring->soft_limit;
}
@@ -142,13 +156,19 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+ /*
+ * The request KVM_REQ_DIRTY_RING_SOFT_FULL will be cleared
+ * by the VCPU thread next time when it enters the guest.
+ */
+
trace_kvm_dirty_ring_reset(ring);
return count;
}
-void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
+void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset)
{
+ struct kvm_dirty_ring *ring = &vcpu->dirty_ring;
struct kvm_dirty_gfn *entry;
/* It should never get full */
@@ -166,6 +186,28 @@ void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
kvm_dirty_gfn_set_dirtied(entry);
ring->dirty_index++;
trace_kvm_dirty_ring_push(ring, slot, offset);
+
+ if (kvm_dirty_ring_soft_full(ring))
+ kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu);
+}
+
+bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu)
+{
+ /*
+ * The VCPU isn't runnable when the dirty ring becomes soft full.
+ * The KVM_REQ_DIRTY_RING_SOFT_FULL event is always set to prevent
+ * the VCPU from running until the dirty pages are harvested and
+ * the dirty ring is reset by userspace.
+ */
+ if (kvm_check_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu) &&
+ kvm_dirty_ring_soft_full(&vcpu->dirty_ring)) {
+ kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu);
+ vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
+ trace_kvm_dirty_ring_exit(vcpu);
+ return true;
+ }
+
+ return false;
}
struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1782c4555d94..3ee537eb0bab 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1617,7 +1617,7 @@ static int kvm_prepare_memory_region(struct kvm *kvm,
new->dirty_bitmap = NULL;
else if (old && old->dirty_bitmap)
new->dirty_bitmap = old->dirty_bitmap;
- else if (!kvm->dirty_ring_size) {
+ else if (kvm_use_dirty_bitmap(kvm)) {
r = kvm_alloc_dirty_bitmap(new);
if (r)
return r;
@@ -2068,8 +2068,8 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
unsigned long n;
unsigned long any = 0;
- /* Dirty ring tracking is exclusive to dirty log tracking */
- if (kvm->dirty_ring_size)
+ /* Dirty ring tracking may be exclusive to dirty log tracking */
+ if (!kvm_use_dirty_bitmap(kvm))
return -ENXIO;
*memslot = NULL;
@@ -2133,8 +2133,8 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
unsigned long *dirty_bitmap_buffer;
bool flush;
- /* Dirty ring tracking is exclusive to dirty log tracking */
- if (kvm->dirty_ring_size)
+ /* Dirty ring tracking may be exclusive to dirty log tracking */
+ if (!kvm_use_dirty_bitmap(kvm))
return -ENXIO;
as_id = log->slot >> 16;
@@ -2245,8 +2245,8 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
unsigned long *dirty_bitmap_buffer;
bool flush;
- /* Dirty ring tracking is exclusive to dirty log tracking */
- if (kvm->dirty_ring_size)
+ /* Dirty ring tracking may be exclusive to dirty log tracking */
+ if (!kvm_use_dirty_bitmap(kvm))
return -ENXIO;
as_id = log->slot >> 16;
@@ -3321,18 +3321,19 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
#ifdef CONFIG_HAVE_KVM_DIRTY_RING
- if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm))
+ if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm))
return;
+
+ WARN_ON_ONCE(!vcpu && !kvm_arch_allow_write_without_running_vcpu(kvm));
#endif
if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
unsigned long rel_gfn = gfn - memslot->base_gfn;
u32 slot = (memslot->as_id << 16) | memslot->id;
- if (kvm->dirty_ring_size)
- kvm_dirty_ring_push(&vcpu->dirty_ring,
- slot, rel_gfn);
- else
+ if (kvm->dirty_ring_size && vcpu)
+ kvm_dirty_ring_push(vcpu, slot, rel_gfn);
+ else if (memslot->dirty_bitmap)
set_bit_le(rel_gfn, memslot->dirty_bitmap);
}
}
@@ -4500,6 +4501,9 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
#else
return 0;
#endif
+#ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP
+ case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP:
+#endif
case KVM_CAP_BINARY_STATS_FD:
case KVM_CAP_SYSTEM_EVENT_DATA:
return 1;
@@ -4575,6 +4579,20 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
return -EINVAL;
}
+static bool kvm_are_all_memslots_empty(struct kvm *kvm)
+{
+ int i;
+
+ lockdep_assert_held(&kvm->slots_lock);
+
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ if (!kvm_memslots_empty(__kvm_memslots(kvm, i)))
+ return false;
+ }
+
+ return true;
+}
+
static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
struct kvm_enable_cap *cap)
{
@@ -4605,6 +4623,29 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
return -EINVAL;
return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
+ case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: {
+ int r = -EINVAL;
+
+ if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) ||
+ !kvm->dirty_ring_size || cap->flags)
+ return r;
+
+ mutex_lock(&kvm->slots_lock);
+
+ /*
+ * For simplicity, allow enabling ring+bitmap if and only if
+ * there are no memslots, e.g. to ensure all memslots allocate
+ * a bitmap after the capability is enabled.
+ */
+ if (kvm_are_all_memslots_empty(kvm)) {
+ kvm->dirty_ring_with_bitmap = true;
+ r = 0;
+ }
+
+ mutex_unlock(&kvm->slots_lock);
+
+ return r;
+ }
default:
return kvm_vm_ioctl_enable_cap(kvm, cap);
}