From: Chao Peng <chao.p.peng@linux.intel.com>
Switch to KVM_SET_USER_MEMORY_REGION2 when supported by KVM.
With KVM_SET_USER_MEMORY_REGION2, QEMU can set up memory region that
backend'ed both by hva-based shared memory and guest memfd based private
memory.
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
---
Changes in v4:
- update KVM_MEM_PRIVATE to KVM_MEM_GUEST_MEMFD; (Isaku)
---
accel/kvm/kvm-all.c | 56 ++++++++++++++++++++++++++++++++++------
accel/kvm/trace-events | 2 +-
include/sysemu/kvm_int.h | 2 ++
3 files changed, 51 insertions(+), 9 deletions(-)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 56b41a4ea8dc..50c10becf772 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -283,35 +283,69 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram,
static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot, bool new)
{
KVMState *s = kvm_state;
- struct kvm_userspace_memory_region mem;
+ struct kvm_userspace_memory_region2 mem;
+ static int cap_user_memory2 = -1;
int ret;
+ if (cap_user_memory2 == -1) {
+ cap_user_memory2 = kvm_check_extension(s, KVM_CAP_USER_MEMORY2);
+ }
+
+ if (!cap_user_memory2 && slot->guest_memfd >= 0) {
+ error_report("%s, KVM doesn't support KVM_CAP_USER_MEMORY2,"
+ " which is required by guest memfd!", __func__);
+ exit(1);
+ }
+
mem.slot = slot->slot | (kml->as_id << 16);
mem.guest_phys_addr = slot->start_addr;
mem.userspace_addr = (unsigned long)slot->ram;
mem.flags = slot->flags;
+ mem.guest_memfd = slot->guest_memfd;
+ mem.guest_memfd_offset = slot->guest_memfd_offset;
if (slot->memory_size && !new && (mem.flags ^ slot->old_flags) & KVM_MEM_READONLY) {
/* Set the slot size to 0 before setting the slot to the desired
* value. This is needed based on KVM commit 75d61fbc. */
mem.memory_size = 0;
- ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
+
+ if (cap_user_memory2) {
+ ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION2, &mem);
+ } else {
+ ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
+ }
if (ret < 0) {
goto err;
}
}
mem.memory_size = slot->memory_size;
- ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
+ if (cap_user_memory2) {
+ ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION2, &mem);
+ } else {
+ ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
+ }
slot->old_flags = mem.flags;
err:
trace_kvm_set_user_memory(mem.slot >> 16, (uint16_t)mem.slot, mem.flags,
mem.guest_phys_addr, mem.memory_size,
- mem.userspace_addr, ret);
+ mem.userspace_addr, mem.guest_memfd,
+ mem.guest_memfd_offset, ret);
if (ret < 0) {
- error_report("%s: KVM_SET_USER_MEMORY_REGION failed, slot=%d,"
- " start=0x%" PRIx64 ", size=0x%" PRIx64 ": %s",
- __func__, mem.slot, slot->start_addr,
- (uint64_t)mem.memory_size, strerror(errno));
+ if (cap_user_memory2) {
+ error_report("%s: KVM_SET_USER_MEMORY_REGION2 failed, slot=%d,"
+ " start=0x%" PRIx64 ", size=0x%" PRIx64 ","
+ " flags=0x%" PRIx32 ", guest_memfd=%" PRId32 ","
+ " guest_memfd_offset=0x%" PRIx64 ": %s",
+ __func__, mem.slot, slot->start_addr,
+ (uint64_t)mem.memory_size, mem.flags,
+ mem.guest_memfd, (uint64_t)mem.guest_memfd_offset,
+ strerror(errno));
+ } else {
+ error_report("%s: KVM_SET_USER_MEMORY_REGION failed, slot=%d,"
+ " start=0x%" PRIx64 ", size=0x%" PRIx64 ": %s",
+ __func__, mem.slot, slot->start_addr,
+ (uint64_t)mem.memory_size, strerror(errno));
+ }
}
return ret;
}
@@ -466,6 +500,9 @@ static int kvm_mem_flags(MemoryRegion *mr)
if (readonly && kvm_readonly_mem_allowed) {
flags |= KVM_MEM_READONLY;
}
+ if (memory_region_has_guest_memfd(mr)) {
+ flags |= KVM_MEM_GUEST_MEMFD;
+ }
return flags;
}
@@ -1353,6 +1390,9 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
mem->ram_start_offset = ram_start_offset;
mem->ram = ram;
mem->flags = kvm_mem_flags(mr);
+ mem->guest_memfd = mr->ram_block->guest_memfd;
+ mem->guest_memfd_offset = (uint8_t*)ram - mr->ram_block->host;
+
kvm_slot_init_dirty_bitmap(mem);
err = kvm_set_user_memory_region(kml, mem, true);
if (err) {
diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events
index 9f599abc172c..e8c52cb9e7a1 100644
--- a/accel/kvm/trace-events
+++ b/accel/kvm/trace-events
@@ -15,7 +15,7 @@ kvm_irqchip_update_msi_route(int virq) "Updating MSI route virq=%d"
kvm_irqchip_release_virq(int virq) "virq %d"
kvm_set_ioeventfd_mmio(int fd, uint64_t addr, uint32_t val, bool assign, uint32_t size, bool datamatch) "fd: %d @0x%" PRIx64 " val=0x%x assign: %d size: %d match: %d"
kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint32_t val, bool assign, uint32_t size, bool datamatch) "fd: %d @0x%x val=0x%x assign: %d size: %d match: %d"
-kvm_set_user_memory(uint16_t as, uint16_t slot, uint32_t flags, uint64_t guest_phys_addr, uint64_t memory_size, uint64_t userspace_addr, int ret) "AddrSpace#%d Slot#%d flags=0x%x gpa=0x%"PRIx64 " size=0x%"PRIx64 " ua=0x%"PRIx64 " ret=%d"
+kvm_set_user_memory(uint16_t as, uint16_t slot, uint32_t flags, uint64_t guest_phys_addr, uint64_t memory_size, uint64_t userspace_addr, uint32_t fd, uint64_t fd_offset, int ret) "AddrSpace#%d Slot#%d flags=0x%x gpa=0x%"PRIx64 " size=0x%"PRIx64 " ua=0x%"PRIx64 " guest_memfd=%d" " guest_memfd_offset=0x%" PRIx64 " ret=%d"
kvm_clear_dirty_log(uint32_t slot, uint64_t start, uint32_t size) "slot#%"PRId32" start 0x%"PRIx64" size 0x%"PRIx32
kvm_resample_fd_notify(int gsi) "gsi %d"
kvm_dirty_ring_full(int id) "vcpu %d"
diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
index 882e37e12c5b..cad763e240c1 100644
--- a/include/sysemu/kvm_int.h
+++ b/include/sysemu/kvm_int.h
@@ -30,6 +30,8 @@ typedef struct KVMSlot
int as_id;
/* Cache of the offset in ram address space */
ram_addr_t ram_start_offset;
+ int guest_memfd;
+ hwaddr guest_memfd_offset;
} KVMSlot;
typedef struct KVMMemoryUpdate {
--
2.34.1