From 120157257ac239050779fdddc9abb56bd39958b3 Mon Sep 17 00:00:00 2001 From: Chao Peng Date: Wed, 20 Mar 2024 03:39:05 -0500 Subject: [PATCH 029/100] kvm: Enable KVM_SET_USER_MEMORY_REGION2 for memslot RH-Author: Paolo Bonzini RH-MergeRequest: 245: SEV-SNP support RH-Jira: RHEL-39544 RH-Acked-by: Thomas Huth RH-Acked-by: Bandan Das RH-Acked-by: Vitaly Kuznetsov RH-Commit: [29/91] 9a08c8699f632cd046a6307e33bd053a7cc7db46 (bonzini/rhel-qemu-kvm) 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 Co-developed-by: Xiaoyao Li Signed-off-by: Xiaoyao Li Message-ID: <20240320083945.991426-10-michael.roth@amd.com> Signed-off-by: Paolo Bonzini (cherry picked from commit ce5a983233b4ca94ced88c9581014346509b5c71) Signed-off-by: Paolo Bonzini --- accel/kvm/kvm-all.c | 46 +++++++++++++++++++++++++++++++++------- accel/kvm/trace-events | 2 +- include/sysemu/kvm_int.h | 2 ++ 3 files changed, 41 insertions(+), 9 deletions(-) diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index a7b9a127dd..5ef55e4dd7 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -284,35 +284,58 @@ 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; int ret; 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 (kvm_guest_memfd_supported) { + 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 (kvm_guest_memfd_supported) { + 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 (kvm_guest_memfd_supported) { + 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; } @@ -467,6 +490,10 @@ static int kvm_mem_flags(MemoryRegion *mr) if (readonly && kvm_readonly_mem_allowed) { flags |= KVM_MEM_READONLY; } + if (memory_region_has_guest_memfd(mr)) { + assert(kvm_guest_memfd_supported); + flags |= KVM_MEM_GUEST_MEMFD; + } return flags; } @@ -1394,6 +1421,9 @@ 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 9f599abc17..e8c52cb9e7 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 3496be7997..a5a3fee411 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 { -- 2.39.3