memory region. This ioctl returns the size of that region. See the
KVM_RUN documentation for details.
+Besides the size of the KVM_RUN communication region, other areas of
+the VCPU file descriptor can be mmap-ed, including:
+
+- if KVM_CAP_COALESCED_MMIO is available, a page at
+ KVM_COALESCED_MMIO_PAGE_OFFSET * PAGE_SIZE; for historical reasons,
+ this page is included in the result of KVM_GET_VCPU_MMAP_SIZE.
+ KVM_CAP_COALESCED_MMIO is not documented yet.
+
+- if KVM_CAP_DIRTY_LOG_RING is available, a number of pages at
+ KVM_DIRTY_LOG_PAGE_OFFSET * PAGE_SIZE. For more information on
+ KVM_CAP_DIRTY_LOG_RING, see section 8.3.
+
4.6 KVM_SET_MEMORY_REGION
-------------------------
guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf
(0x40000001). Otherwise, a guest may use the paravirtual features
regardless of what has actually been exposed through the CPUID leaf.
+
+
+8.29 KVM_CAP_DIRTY_LOG_RING
+---------------------------
+
+:Architectures: x86
+:Parameters: args[0] - size of the dirty log ring
+
+KVM is capable of tracking dirty memory using ring buffers that are
+mmaped into userspace; there is one dirty ring per vcpu.
+
+The dirty ring is available to userspace as an array of
+``struct kvm_dirty_gfn``. Each dirty entry it's defined as::
+
+ struct kvm_dirty_gfn {
+ __u32 flags;
+ __u32 slot; /* as_id | slot_id */
+ __u64 offset;
+ };
+
+The following values are defined for the flags field to define the
+current state of the entry::
+
+ #define KVM_DIRTY_GFN_F_DIRTY BIT(0)
+ #define KVM_DIRTY_GFN_F_RESET BIT(1)
+ #define KVM_DIRTY_GFN_F_MASK 0x3
+
+Userspace should call KVM_ENABLE_CAP ioctl right after KVM_CREATE_VM
+ioctl to enable this capability for the new guest and set the size of
+the rings. Enabling the capability is only allowed before creating any
+vCPU, and the size of the ring must be a power of two. The larger the
+ring buffer, the less likely the ring is full and the VM is forced to
+exit to userspace. The optimal size depends on the workload, but it is
+recommended that it be at least 64 KiB (4096 entries).
+
+Just like for dirty page bitmaps, the buffer tracks writes to
+all user memory regions for which the KVM_MEM_LOG_DIRTY_PAGES flag was
+set in KVM_SET_USER_MEMORY_REGION. Once a memory region is registered
+with the flag set, userspace can start harvesting dirty pages from the
+ring buffer.
+
+An entry in the ring buffer can be unused (flag bits ``00``),
+dirty (flag bits ``01``) or harvested (flag bits ``1X``). The
+state machine for the entry is as follows::
+
+ dirtied harvested reset
+ 00 -----------> 01 -------------> 1X -------+
+ ^ |
+ | |
+ +------------------------------------------+
+
+To harvest the dirty pages, userspace accesses the mmaped ring buffer
+to read the dirty GFNs. If the flags has the DIRTY bit set (at this stage
+the RESET bit must be cleared), then it means this GFN is a dirty GFN.
+The userspace should harvest this GFN and mark the flags from state
+``01b`` to ``1Xb`` (bit 0 will be ignored by KVM, but bit 1 must be set
+to show that this GFN is harvested and waiting for a reset), and move
+on to the next GFN. The userspace should continue to do this until the
+flags of a GFN have the DIRTY bit cleared, meaning that it has harvested
+all the dirty GFNs that were available.
+
+It's not necessary for userspace to harvest the all dirty GFNs at once.
+However it must collect the dirty GFNs in sequence, i.e., the userspace
+program cannot skip one dirty GFN to collect the one next to it.
+
+After processing one or more entries in the ring buffer, userspace
+calls the VM ioctl KVM_RESET_DIRTY_RINGS to notify the kernel about
+it, so that the kernel will reprotect those collected GFNs.
+Therefore, the ioctl must be called *before* reading the content of
+the dirty pages.
+
+The dirty ring can get full. When it happens, the KVM_RUN of the
+vcpu will return with exit reason KVM_EXIT_DIRTY_LOG_FULL.
+
+The dirty ring interface has a major difference comparing to the
+KVM_GET_DIRTY_LOG interface in that, when reading the dirty ring from
+userspace, it's still possible that the kernel has not yet flushed the
+processor's dirty page buffers into the kernel buffer (with dirty bitmaps, the
+flushing is done by the KVM_GET_DIRTY_LOG ioctl). To achieve that, one
+needs to kick the vcpu out of KVM_RUN using a signal. The resulting
+vmexit ensures that all dirty GFNs are flushed to the dirty rings.
void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t offset, unsigned long mask);
+ int (*cpu_dirty_log_size)(void);
/* pmu operations of sub-arch */
const struct kvm_pmu_ops *pmu_ops;
#define GET_SMSTATE(type, buf, offset) \
(*(type *)((buf) + (offset) - 0x7e00))
+int kvm_cpu_dirty_log_size(void);
+
#endif /* _ASM_X86_KVM_HOST_H */
#define KVM_PIO_PAGE_OFFSET 1
#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
#define DE_VECTOR 0
#define DB_VECTOR 1
KVM := ../../../virt/kvm
kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
- $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
+ $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \
+ $(KVM)/dirty_ring.o
kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
+int kvm_cpu_dirty_log_size(void)
+{
+ if (kvm_x86_ops.cpu_dirty_log_size)
+ return kvm_x86_ops.cpu_dirty_log_size();
+
+ return 0;
+}
+
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn)
{
if ((!is_writable_pte(old_spte) || pfn_changed) &&
is_writable_pte(new_spte)) {
slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn);
- mark_page_dirty_in_slot(slot, gfn);
+ mark_page_dirty_in_slot(kvm, slot, gfn);
}
}
return supported & BIT(bit);
}
+static int vmx_cpu_dirty_log_size(void)
+{
+ return enable_pml ? PML_ENTITY_NUM : 0;
+}
+
static struct kvm_x86_ops vmx_x86_ops __initdata = {
.hardware_unsetup = hardware_unsetup,
.migrate_timers = vmx_migrate_timers,
.msr_filter_changed = vmx_msr_filter_changed,
+ .cpu_dirty_log_size = vmx_cpu_dirty_log_size,
};
static __init int hardware_setup(void)
vmx_x86_ops.slot_disable_log_dirty = NULL;
vmx_x86_ops.flush_log_dirty = NULL;
vmx_x86_ops.enable_log_dirty_pt_masked = NULL;
+ vmx_x86_ops.cpu_dirty_log_size = NULL;
}
if (!cpu_has_vmx_preemption_timer())
bool req_immediate_exit = false;
+ /* Forbid vmenter if vcpu dirty ring is soft-full */
+ if (unlikely(vcpu->kvm->dirty_ring_size &&
+ kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) {
+ vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
+ trace_kvm_dirty_ring_exit(vcpu);
+ r = 0;
+ goto out;
+ }
+
if (kvm_request_pending(vcpu)) {
if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
--- /dev/null
+#ifndef KVM_DIRTY_RING_H
+#define KVM_DIRTY_RING_H
+
+#include <linux/kvm.h>
+
+/**
+ * kvm_dirty_ring: KVM internal dirty ring structure
+ *
+ * @dirty_index: free running counter that points to the next slot in
+ * dirty_ring->dirty_gfns, where a new dirty page should go
+ * @reset_index: free running counter that points to the next dirty page
+ * in dirty_ring->dirty_gfns for which dirty trap needs to
+ * be reenabled
+ * @size: size of the compact list, dirty_ring->dirty_gfns
+ * @soft_limit: when the number of dirty pages in the list reaches this
+ * limit, vcpu that owns this ring should exit to userspace
+ * to allow userspace to harvest all the dirty pages
+ * @dirty_gfns: the array to keep the dirty gfns
+ * @index: index of this dirty ring
+ */
+struct kvm_dirty_ring {
+ u32 dirty_index;
+ u32 reset_index;
+ u32 size;
+ u32 soft_limit;
+ struct kvm_dirty_gfn *dirty_gfns;
+ int index;
+};
+
+#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0)
+/*
+ * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should
+ * not be included as well, so define these nop functions for the arch.
+ */
+static inline u32 kvm_dirty_ring_get_rsvd_entries(void)
+{
+ return 0;
+}
+
+static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring,
+ int index, u32 size)
+{
+ return 0;
+}
+
+static inline struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm)
+{
+ return NULL;
+}
+
+static inline int kvm_dirty_ring_reset(struct kvm *kvm,
+ struct kvm_dirty_ring *ring)
+{
+ return 0;
+}
+
+static inline void kvm_dirty_ring_push(struct kvm_dirty_ring *ring,
+ u32 slot, u64 offset)
+{
+}
+
+static inline struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring,
+ u32 offset)
+{
+ return NULL;
+}
+
+static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
+{
+}
+
+static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+{
+ return true;
+}
+
+#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */
+
+u32 kvm_dirty_ring_get_rsvd_entries(void);
+int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
+struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm);
+
+/*
+ * called with kvm->slots_lock held, returns the number of
+ * processed pages.
+ */
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring);
+
+/*
+ * returns =0: successfully pushed
+ * <0: unable to push, need to wait
+ */
+void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset);
+
+/* for use in vm_operations_struct */
+struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset);
+
+void kvm_dirty_ring_free(struct kvm_dirty_ring *ring);
+bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring);
+
+#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */
+
+#endif /* KVM_DIRTY_RING_H */
#include <linux/kvm_types.h>
#include <asm/kvm_host.h>
+#include <linux/kvm_dirty_ring.h>
#ifndef KVM_MAX_VCPU_ID
#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS
bool preempted;
bool ready;
struct kvm_vcpu_arch arch;
+ struct kvm_dirty_ring dirty_ring;
};
static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
struct srcu_struct irq_srcu;
pid_t userspace_pid;
unsigned int max_halt_poll_ns;
+ u32 dirty_ring_size;
};
#define kvm_err(fmt, ...) \
}
#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
+/*
+ * This defines how many reserved entries we want to keep before we
+ * kick the vcpu to the userspace to avoid dirty ring full. This
+ * value can be tuned to higher if e.g. PML is enabled on the host.
+ */
+#define KVM_DIRTY_RING_RSVD_ENTRIES 64
+
+/* Max number of entries allowed for each kvm dirty ring */
+#define KVM_DIRTY_RING_MAX_ENTRIES 65536
+
#endif
#define trace_kvm_halt_poll_ns_shrink(vcpu_id, new, old) \
trace_kvm_halt_poll_ns(false, vcpu_id, new, old)
+TRACE_EVENT(kvm_dirty_ring_push,
+ TP_PROTO(struct kvm_dirty_ring *ring, u32 slot, u64 offset),
+ TP_ARGS(ring, slot, offset),
+
+ TP_STRUCT__entry(
+ __field(int, index)
+ __field(u32, dirty_index)
+ __field(u32, reset_index)
+ __field(u32, slot)
+ __field(u64, offset)
+ ),
+
+ TP_fast_assign(
+ __entry->index = ring->index;
+ __entry->dirty_index = ring->dirty_index;
+ __entry->reset_index = ring->reset_index;
+ __entry->slot = slot;
+ __entry->offset = offset;
+ ),
+
+ TP_printk("ring %d: dirty 0x%x reset 0x%x "
+ "slot %u offset 0x%llx (used %u)",
+ __entry->index, __entry->dirty_index,
+ __entry->reset_index, __entry->slot, __entry->offset,
+ __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_reset,
+ TP_PROTO(struct kvm_dirty_ring *ring),
+ TP_ARGS(ring),
+
+ TP_STRUCT__entry(
+ __field(int, index)
+ __field(u32, dirty_index)
+ __field(u32, reset_index)
+ ),
+
+ TP_fast_assign(
+ __entry->index = ring->index;
+ __entry->dirty_index = ring->dirty_index;
+ __entry->reset_index = ring->reset_index;
+ ),
+
+ TP_printk("ring %d: dirty 0x%x reset 0x%x (used %u)",
+ __entry->index, __entry->dirty_index, __entry->reset_index,
+ __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_exit,
+ TP_PROTO(struct kvm_vcpu *vcpu),
+ TP_ARGS(vcpu),
+
+ TP_STRUCT__entry(
+ __field(int, vcpu_id)
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu->vcpu_id;
+ ),
+
+ TP_printk("vcpu %d", __entry->vcpu_id)
+);
+
#endif /* _TRACE_KVM_MAIN_H */
/* This part must be outside protection */
#define KVM_EXIT_ARM_NISV 28
#define KVM_EXIT_X86_RDMSR 29
#define KVM_EXIT_X86_WRMSR 30
+#define KVM_EXIT_DIRTY_RING_FULL 31
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
#define KVM_CAP_X86_MSR_FILTER 189
#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
#define KVM_CAP_SYS_HYPERV_CPUID 191
+#define KVM_CAP_DIRTY_LOG_RING 192
#ifdef KVM_CAP_IRQ_ROUTING
/* Available with KVM_CAP_X86_MSR_FILTER */
#define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter)
+/* Available with KVM_CAP_DIRTY_LOG_RING */
+#define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7)
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
+/*
+ * Arch needs to define the macro after implementing the dirty ring
+ * feature. KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the
+ * starting page offset of the dirty ring structures.
+ */
+#ifndef KVM_DIRTY_LOG_PAGE_OFFSET
+#define KVM_DIRTY_LOG_PAGE_OFFSET 0
+#endif
+
+/*
+ * KVM dirty GFN flags, defined as:
+ *
+ * |---------------+---------------+--------------|
+ * | bit 1 (reset) | bit 0 (dirty) | Status |
+ * |---------------+---------------+--------------|
+ * | 0 | 0 | Invalid GFN |
+ * | 0 | 1 | Dirty GFN |
+ * | 1 | X | GFN to reset |
+ * |---------------+---------------+--------------|
+ *
+ * Lifecycle of a dirty GFN goes like:
+ *
+ * dirtied harvested reset
+ * 00 -----------> 01 -------------> 1X -------+
+ * ^ |
+ * | |
+ * +------------------------------------------+
+ *
+ * The userspace program is only responsible for the 01->1X state
+ * conversion after harvesting an entry. Also, it must not skip any
+ * dirty bits, so that dirty bits are always harvested in sequence.
+ */
+#define KVM_DIRTY_GFN_F_DIRTY BIT(0)
+#define KVM_DIRTY_GFN_F_RESET BIT(1)
+#define KVM_DIRTY_GFN_F_MASK 0x3
+
+/*
+ * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of
+ * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn. The
+ * size of the gfn buffer is decided by the first argument when
+ * enabling KVM_CAP_DIRTY_LOG_RING.
+ */
+struct kvm_dirty_gfn {
+ __u32 flags;
+ __u32 slot;
+ __u64 offset;
+};
+
#endif /* __LINUX_KVM_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * KVM dirty ring implementation
+ *
+ * Copyright 2019 Red Hat, Inc.
+ */
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/vmalloc.h>
+#include <linux/kvm_dirty_ring.h>
+#include <trace/events/kvm.h>
+
+int __weak kvm_cpu_dirty_log_size(void)
+{
+ return 0;
+}
+
+u32 kvm_dirty_ring_get_rsvd_entries(void)
+{
+ return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
+}
+
+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)
+{
+ return kvm_dirty_ring_used(ring) >= ring->soft_limit;
+}
+
+static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring)
+{
+ return kvm_dirty_ring_used(ring) >= ring->size;
+}
+
+struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+
+ WARN_ON_ONCE(vcpu->kvm != kvm);
+
+ return &vcpu->dirty_ring;
+}
+
+static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
+{
+ struct kvm_memory_slot *memslot;
+ int as_id, id;
+
+ as_id = slot >> 16;
+ id = (u16)slot;
+
+ if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+ return;
+
+ memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id);
+
+ if (!memslot || (offset + __fls(mask)) >= memslot->npages)
+ return;
+
+ spin_lock(&kvm->mmu_lock);
+ kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask);
+ spin_unlock(&kvm->mmu_lock);
+}
+
+int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size)
+{
+ ring->dirty_gfns = vmalloc(size);
+ if (!ring->dirty_gfns)
+ return -ENOMEM;
+ memset(ring->dirty_gfns, 0, size);
+
+ ring->size = size / sizeof(struct kvm_dirty_gfn);
+ ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries();
+ ring->dirty_index = 0;
+ ring->reset_index = 0;
+ ring->index = index;
+
+ return 0;
+}
+
+static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn)
+{
+ gfn->flags = 0;
+}
+
+static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn)
+{
+ gfn->flags = KVM_DIRTY_GFN_F_DIRTY;
+}
+
+static inline bool kvm_dirty_gfn_invalid(struct kvm_dirty_gfn *gfn)
+{
+ return gfn->flags == 0;
+}
+
+static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn)
+{
+ return gfn->flags & KVM_DIRTY_GFN_F_RESET;
+}
+
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
+{
+ u32 cur_slot, next_slot;
+ u64 cur_offset, next_offset;
+ unsigned long mask;
+ int count = 0;
+ struct kvm_dirty_gfn *entry;
+ bool first_round = true;
+
+ /* This is only needed to make compilers happy */
+ cur_slot = cur_offset = mask = 0;
+
+ while (true) {
+ entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)];
+
+ if (!kvm_dirty_gfn_harvested(entry))
+ break;
+
+ next_slot = READ_ONCE(entry->slot);
+ next_offset = READ_ONCE(entry->offset);
+
+ /* Update the flags to reflect that this GFN is reset */
+ kvm_dirty_gfn_set_invalid(entry);
+
+ ring->reset_index++;
+ count++;
+ /*
+ * Try to coalesce the reset operations when the guest is
+ * scanning pages in the same slot.
+ */
+ if (!first_round && next_slot == cur_slot) {
+ s64 delta = next_offset - cur_offset;
+
+ if (delta >= 0 && delta < BITS_PER_LONG) {
+ mask |= 1ull << delta;
+ continue;
+ }
+
+ /* Backwards visit, careful about overflows! */
+ if (delta > -BITS_PER_LONG && delta < 0 &&
+ (mask << -delta >> -delta) == mask) {
+ cur_offset = next_offset;
+ mask = (mask << -delta) | 1;
+ continue;
+ }
+ }
+ kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+ cur_slot = next_slot;
+ cur_offset = next_offset;
+ mask = 1;
+ first_round = false;
+ }
+
+ kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+
+ trace_kvm_dirty_ring_reset(ring);
+
+ return count;
+}
+
+void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
+{
+ struct kvm_dirty_gfn *entry;
+
+ /* It should never get full */
+ WARN_ON_ONCE(kvm_dirty_ring_full(ring));
+
+ entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)];
+
+ entry->slot = slot;
+ entry->offset = offset;
+ /*
+ * Make sure the data is filled in before we publish this to
+ * the userspace program. There's no paired kernel-side reader.
+ */
+ smp_wmb();
+ kvm_dirty_gfn_set_dirtied(entry);
+ ring->dirty_index++;
+ trace_kvm_dirty_ring_push(ring, slot, offset);
+}
+
+struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset)
+{
+ return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE);
+}
+
+void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
+{
+ vfree(ring->dirty_gfns);
+ ring->dirty_gfns = NULL;
+}
#define CREATE_TRACE_POINTS
#include <trace/events/kvm.h>
+#include <linux/kvm_dirty_ring.h>
+
/* Worst case buffer size needed for holding an integer. */
#define ITOA_MAX_LEN 12
void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
{
+ kvm_dirty_ring_free(&vcpu->dirty_ring);
kvm_arch_vcpu_destroy(vcpu);
/*
{
if (memslot && memslot->dirty_bitmap) {
unsigned long rel_gfn = gfn - memslot->base_gfn;
+ u32 slot = (memslot->as_id << 16) | memslot->id;
- set_bit_le(rel_gfn, memslot->dirty_bitmap);
+ if (kvm->dirty_ring_size)
+ kvm_dirty_ring_push(kvm_dirty_ring_get(kvm),
+ slot, rel_gfn);
+ else
+ set_bit_le(rel_gfn, memslot->dirty_bitmap);
}
}
EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
+static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff)
+{
+#if KVM_DIRTY_LOG_PAGE_OFFSET > 0
+ return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) &&
+ (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET +
+ kvm->dirty_ring_size / PAGE_SIZE);
+#else
+ return false;
+#endif
+}
+
static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
{
struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data;
else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
#endif
+ else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff))
+ page = kvm_dirty_ring_get_page(
+ &vcpu->dirty_ring,
+ vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET);
else
return kvm_arch_vcpu_fault(vcpu, vmf);
get_page(page);
static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
{
+ struct kvm_vcpu *vcpu = file->private_data;
+ unsigned long pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+
+ if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) ||
+ kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) &&
+ ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED)))
+ return -EINVAL;
+
vma->vm_ops = &kvm_vcpu_vm_ops;
return 0;
}
if (r)
goto vcpu_free_run_page;
+ if (kvm->dirty_ring_size) {
+ r = kvm_dirty_ring_alloc(&vcpu->dirty_ring,
+ id, kvm->dirty_ring_size);
+ if (r)
+ goto arch_vcpu_destroy;
+ }
+
mutex_lock(&kvm->lock);
if (kvm_get_vcpu_by_id(kvm, id)) {
r = -EEXIST;
unlock_vcpu_destroy:
mutex_unlock(&kvm->lock);
+ kvm_dirty_ring_free(&vcpu->dirty_ring);
+arch_vcpu_destroy:
kvm_arch_vcpu_destroy(vcpu);
vcpu_free_run_page:
free_page((unsigned long)vcpu->run);
#endif
case KVM_CAP_NR_MEMSLOTS:
return KVM_USER_MEM_SLOTS;
+ case KVM_CAP_DIRTY_LOG_RING:
+#if KVM_DIRTY_LOG_PAGE_OFFSET > 0
+ return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
+#else
+ return 0;
+#endif
default:
break;
}
return kvm_vm_ioctl_check_extension(kvm, arg);
}
+static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size)
+{
+ int r;
+
+ if (!KVM_DIRTY_LOG_PAGE_OFFSET)
+ return -EINVAL;
+
+ /* the size should be power of 2 */
+ if (!size || (size & (size - 1)))
+ return -EINVAL;
+
+ /* Should be bigger to keep the reserved entries, or a page */
+ if (size < kvm_dirty_ring_get_rsvd_entries() *
+ sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE)
+ return -EINVAL;
+
+ if (size > KVM_DIRTY_RING_MAX_ENTRIES *
+ sizeof(struct kvm_dirty_gfn))
+ return -E2BIG;
+
+ /* We only allow it to set once */
+ if (kvm->dirty_ring_size)
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+
+ if (kvm->created_vcpus) {
+ /* We don't allow to change this value after vcpu created */
+ r = -EINVAL;
+ } else {
+ kvm->dirty_ring_size = size;
+ r = 0;
+ }
+
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm)
+{
+ int i;
+ struct kvm_vcpu *vcpu;
+ int cleared = 0;
+
+ if (!kvm->dirty_ring_size)
+ return -EINVAL;
+
+ mutex_lock(&kvm->slots_lock);
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring);
+
+ mutex_unlock(&kvm->slots_lock);
+
+ if (cleared)
+ kvm_flush_remote_tlbs(kvm);
+
+ return cleared;
+}
+
int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
struct kvm_enable_cap *cap)
{
kvm->max_halt_poll_ns = cap->args[0];
return 0;
}
+ case KVM_CAP_DIRTY_LOG_RING:
+ return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
default:
return kvm_vm_ioctl_enable_cap(kvm, cap);
}
case KVM_CHECK_EXTENSION:
r = kvm_vm_ioctl_check_extension_generic(kvm, arg);
break;
+ case KVM_RESET_DIRTY_RINGS:
+ r = kvm_vm_ioctl_reset_dirty_pages(kvm);
+ break;
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
}
projects / users / hch / xfs.git / commitdiff