From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: Chao Peng <chao.p.peng@linux.intel.com>,
Xiaoyao Li <xiaoyao.li@intel.com>
Subject: [PULL 50/63] kvm: Enable KVM_SET_USER_MEMORY_REGION2 for memslot
Date: Tue, 23 Apr 2024 17:09:38 +0200 [thread overview]
Message-ID: <20240423150951.41600-51-pbonzini@redhat.com> (raw)
In-Reply-To: <20240423150951.41600-1-pbonzini@redhat.com>
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>
Message-ID: <20240320083945.991426-10-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
include/sysemu/kvm_int.h | 2 ++
accel/kvm/kvm-all.c | 46 +++++++++++++++++++++++++++++++++-------
accel/kvm/trace-events | 2 +-
3 files changed, 41 insertions(+), 9 deletions(-)
diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
index 227b61fec3d..3f3d13f8166 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 {
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 1b7bbd838c4..0386d4901fa 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 9f599abc172..e8c52cb9e7a 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"
--
2.44.0
next prev parent reply other threads:[~2024-04-23 15:16 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-23 15:08 [PULL 00/63] First batch of i386 and build system patch for QEMU 9.1 Paolo Bonzini
2024-04-23 15:08 ` [PULL 01/63] meson: do not link pixman automatically into all targets Paolo Bonzini
2024-04-23 15:08 ` [PULL 02/63] tests: only build plugins if TCG is enabled Paolo Bonzini
2024-04-23 15:08 ` [PULL 03/63] ebpf: Restrict to system emulation Paolo Bonzini
2024-04-23 15:08 ` [PULL 04/63] tests/unit: match some unit tests to corresponding feature switches Paolo Bonzini
2024-04-23 15:08 ` [PULL 05/63] yank: only build if needed Paolo Bonzini
2024-04-23 15:08 ` [PULL 06/63] util/qemu-config: Extract QMP commands to qemu-config-qmp.c Paolo Bonzini
2024-04-23 15:08 ` [PULL 07/63] hw/core: Move system emulation files to system_ss Paolo Bonzini
2024-04-23 15:08 ` [PULL 08/63] hw: Include minimal source set in user emulation build Paolo Bonzini
2024-04-23 15:08 ` [PULL 09/63] stubs: remove obsolete stubs Paolo Bonzini
2024-04-23 15:08 ` [PULL 10/63] hw/usb: move stubs out of stubs/ Paolo Bonzini
2024-04-23 15:08 ` [PULL 11/63] hw/virtio: " Paolo Bonzini
2024-08-03 2:29 ` Michael Tokarev
2024-09-05 16:27 ` Paolo Bonzini
2024-09-06 7:08 ` Michael Tokarev
2024-09-06 7:30 ` Paolo Bonzini
2024-04-23 15:09 ` [PULL 12/63] semihosting: " Paolo Bonzini
2024-04-23 15:09 ` [PULL 13/63] ramfb: " Paolo Bonzini
2024-04-23 15:09 ` [PULL 14/63] memory-device: " Paolo Bonzini
2024-04-23 15:09 ` [PULL 15/63] colo: " Paolo Bonzini
2024-04-23 15:09 ` [PULL 16/63] stubs: split record/replay stubs further Paolo Bonzini
2024-04-23 15:09 ` [PULL 17/63] stubs: include stubs only if needed Paolo Bonzini
2024-06-04 10:07 ` Daniel P. Berrangé
2024-06-05 14:46 ` Zhao Liu
2024-04-23 15:09 ` [PULL 18/63] stubs: move monitor_fdsets_cleanup with other fdset stubs Paolo Bonzini
2024-04-23 15:09 ` [PULL 19/63] vga: optimize computation of dirty memory region Paolo Bonzini
2024-04-23 15:09 ` [PULL 20/63] vga: move dirty memory region code together Paolo Bonzini
2024-04-23 15:09 ` [PULL 21/63] kvm: use configs/ definition to conditionalize debug support Paolo Bonzini
2024-04-23 15:09 ` [PULL 22/63] hw: Add compat machines for 9.1 Paolo Bonzini
2024-04-23 15:09 ` [PULL 23/63] target/i386: add guest-phys-bits cpu property Paolo Bonzini
2024-04-23 15:09 ` [PULL 24/63] kvm: add support for guest physical bits Paolo Bonzini
2024-04-23 15:09 ` [PULL 25/63] i386/kvm: Move architectural CPUID leaf generation to separate helper Paolo Bonzini
2024-04-23 15:29 ` Xiaoyao Li
2024-04-23 15:09 ` [PULL 26/63] target/i386: Introduce Icelake-Server-v7 to enable TSX Paolo Bonzini
2024-04-23 15:09 ` [PULL 27/63] target/i386: Add new CPU model SierraForest Paolo Bonzini
2024-04-23 15:09 ` [PULL 28/63] target/i386: Export RFDS bit to guests Paolo Bonzini
2024-04-23 15:09 ` [PULL 29/63] pci-host/q35: Move PAM initialization above SMRAM initialization Paolo Bonzini
2025-08-12 14:20 ` Michael Tokarev
2025-08-12 14:40 ` Michael Tokarev
2024-04-23 15:09 ` [PULL 30/63] q35: Introduce smm_ranges property for q35-pci-host Paolo Bonzini
2025-08-12 14:45 ` Philippe Mathieu-Daudé
2025-08-12 15:27 ` Michael Tokarev
2025-09-17 14:23 ` Michael Tokarev
2025-09-18 9:20 ` Gerd Hoffmann
2025-09-18 9:27 ` Michael Tokarev
2025-09-18 10:25 ` Gerd Hoffmann
2024-04-23 15:09 ` [PULL 31/63] hw/i386/acpi: Set PCAT_COMPAT bit only when pic is not disabled Paolo Bonzini
2024-04-23 15:09 ` [PULL 32/63] confidential guest support: Add kvm_init() and kvm_reset() in class Paolo Bonzini
2024-04-23 15:09 ` [PULL 33/63] i386/sev: Switch to use confidential_guest_kvm_init() Paolo Bonzini
2024-04-23 15:09 ` [PULL 34/63] ppc/pef: switch to use confidential_guest_kvm_init/reset() Paolo Bonzini
2024-04-23 15:09 ` [PULL 35/63] s390: Switch to use confidential_guest_kvm_init() Paolo Bonzini
2024-04-23 15:09 ` [PULL 36/63] scripts/update-linux-headers: Add setup_data.h to import list Paolo Bonzini
2024-04-23 15:09 ` [PULL 37/63] scripts/update-linux-headers: Add bits.h to file imports Paolo Bonzini
2024-04-23 15:09 ` [PULL 38/63] linux-headers: update to current kvm/next Paolo Bonzini
2024-04-23 15:09 ` [PULL 39/63] runstate: skip initial CPU reset if reset is not actually possible Paolo Bonzini
2024-04-23 15:09 ` [PULL 40/63] KVM: track whether guest state is encrypted Paolo Bonzini
2024-04-23 15:09 ` [PULL 41/63] KVM: remove kvm_arch_cpu_check_are_resettable Paolo Bonzini
2024-04-23 15:09 ` [PULL 42/63] target/i386: introduce x86-confidential-guest Paolo Bonzini
2024-04-23 15:09 ` [PULL 43/63] target/i386: Implement mc->kvm_type() to get VM type Paolo Bonzini
2024-04-24 8:36 ` Xiaoyao Li
2024-04-23 15:09 ` [PULL 44/63] target/i386: SEV: use KVM_SEV_INIT2 if possible Paolo Bonzini
2024-04-23 15:09 ` [PULL 45/63] i386/sev: Add 'legacy-vm-type' parameter for SEV guest objects Paolo Bonzini
2024-04-23 15:09 ` [PULL 46/63] hw/i386/sev: Use legacy SEV VM types for older machine types Paolo Bonzini
2024-04-23 15:09 ` [PULL 47/63] trace/kvm: Split address space and slot id in trace_kvm_set_user_memory() Paolo Bonzini
2024-04-23 15:09 ` [PULL 48/63] kvm: Introduce support for memory_attributes Paolo Bonzini
2024-04-23 15:09 ` [PULL 49/63] RAMBlock: Add support of KVM private guest memfd Paolo Bonzini
2024-04-23 15:09 ` Paolo Bonzini [this message]
2024-04-23 15:09 ` [PULL 51/63] kvm/memory: Make memory type private by default if it has guest memfd backend Paolo Bonzini
2024-04-23 15:09 ` [PULL 52/63] HostMem: Add mechanism to opt in kvm guest memfd via MachineState Paolo Bonzini
2024-04-23 15:09 ` [PULL 53/63] RAMBlock: make guest_memfd require uncoordinated discard Paolo Bonzini
2024-04-23 15:09 ` [PULL 54/63] physmem: Introduce ram_block_discard_guest_memfd_range() Paolo Bonzini
2024-04-23 15:09 ` [PULL 55/63] kvm: handle KVM_EXIT_MEMORY_FAULT Paolo Bonzini
2024-04-26 13:40 ` Peter Maydell
2024-04-30 19:06 ` Paolo Bonzini
2024-04-23 15:09 ` [PULL 56/63] kvm/tdx: Don't complain when converting vMMIO region to shared Paolo Bonzini
2024-04-23 15:09 ` [PULL 57/63] kvm/tdx: Ignore memory conversion to shared of unassigned region Paolo Bonzini
2024-04-23 15:09 ` [PULL 58/63] target/i386/host-cpu: Consolidate the use of warn_report_once() Paolo Bonzini
2024-04-23 15:09 ` [PULL 59/63] target/i386/cpu: " Paolo Bonzini
2024-04-23 15:09 ` [PULL 60/63] target/i386/cpu: Merge the warning and error messages for AMD HT check Paolo Bonzini
2024-04-23 15:09 ` [PULL 61/63] accel/tcg/icount-common: Consolidate the use of warn_report_once() Paolo Bonzini
2024-04-23 15:09 ` [PULL 62/63] pythondeps.toml: warn about updates needed to docs/requirements.txt Paolo Bonzini
2024-04-23 15:09 ` [PULL 63/63] target/i386/translate.c: always write 32-bits for SGDT and SIDT Paolo Bonzini
2024-04-24 4:26 ` [PULL 00/63] First batch of i386 and build system patch for QEMU 9.1 Richard Henderson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240423150951.41600-51-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--cc=chao.p.peng@linux.intel.com \
--cc=qemu-devel@nongnu.org \
--cc=xiaoyao.li@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).