qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Xiaoyao Li <xiaoyao.li@intel.com>
To: Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	David Hildenbrand <david@redhat.com>,
	Igor Mammedov <imammedo@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Marcel Apfelbaum <marcel.apfelbaum@gmail.com>,
	Richard Henderson <richard.henderson@linaro.org>,
	Marcelo Tosatti <mtosatti@redhat.com>
Cc: "Markus Armbruster" <armbru@redhat.com>,
	"Eric Blake" <eblake@redhat.com>,
	"Daniel P. Berrangé" <berrange@redhat.com>,
	"Philippe Mathieu-Daudé" <philmd@linaro.org>,
	"Peter Xu" <peterx@redhat.com>,
	"Chao Peng" <chao.p.peng@linux.intel.com>,
	"Michael Roth" <michael.roth@amd.com>,
	isaku.yamahata@gmail.com, xiaoyao.li@intel.com,
	qemu-devel@nongnu.org, kvm@vger.kernel.org
Subject: [RFC PATCH 05/19] kvm: Enable KVM_SET_USER_MEMORY_REGION2 for memslot
Date: Mon, 31 Jul 2023 12:21:47 -0400	[thread overview]
Message-ID: <20230731162201.271114-6-xiaoyao.li@intel.com> (raw)
In-Reply-To: <20230731162201.271114-1-xiaoyao.li@intel.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
backen'ed both by hva-based shared memory and gmem fd based private
memory.

Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Codeveloped-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
---
 accel/kvm/kvm-all.c      | 57 +++++++++++++++++++++++++++++++++-------
 accel/kvm/trace-events   |  2 +-
 include/sysemu/kvm_int.h |  2 ++
 3 files changed, 51 insertions(+), 10 deletions(-)

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index d8eee405de24..7b1818334ba7 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -288,35 +288,68 @@ 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->fd >= 0) {
+        error_report("%s, KVM doesn't support gmem!", __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.gmem_fd = slot->fd;
+    mem.gmem_offset = slot->ofs;
 
-    if (slot->memory_size && !new && (mem.flags ^ slot->old_flags) & KVM_MEM_READONLY) {
+    if (slot->memory_size && !new && (slot->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.gmem_fd,
+			      mem.gmem_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 ","
+                        " gmem_fd=%" PRId32 ", gmem_offset=0x%" PRIx64 ": %s",
+                        __func__, mem.slot, slot->start_addr,
+                (uint64_t)mem.memory_size, mem.flags,
+                        mem.gmem_fd, (uint64_t)mem.gmem_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;
 }
@@ -472,6 +505,9 @@ static int kvm_mem_flags(MemoryRegion *mr)
     if (readonly && kvm_readonly_mem_allowed) {
         flags |= KVM_MEM_READONLY;
     }
+    if (memory_region_can_be_private(mr)) {
+        flags |= KVM_MEM_PRIVATE;
+    }
     return flags;
 }
 
@@ -1402,6 +1438,9 @@ 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->fd = mr->ram_block->gmem_fd;
+        mem->ofs = (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 14ebfa1b991c..80694683acea 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 " gmem_fd=%d" " gmem_fd_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 511b42bde5c4..48220c0793ac 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 fd;
+    hwaddr ofs;
 } KVMSlot;
 
 typedef struct KVMMemoryUpdate {
-- 
2.34.1



  parent reply	other threads:[~2023-07-31 16:33 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-31 16:21 [RFC PATCH 00/19] QEMU gmem implemention Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 01/19] trace/kvm: Split address space and slot id in trace_kvm_set_user_memory() Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 02/19] *** HACK *** linux-headers: Update headers to pull in gmem APIs Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 03/19] RAMBlock: Support KVM gmemory Xiaoyao Li
2023-08-01 16:33   ` David Hildenbrand
2023-07-31 16:21 ` [RFC PATCH 04/19] memory: Introduce memory_region_can_be_private() Xiaoyao Li
2023-07-31 21:23   ` Peter Xu
2023-07-31 21:33     ` Michael S. Tsirkin
2023-07-31 21:34     ` Sean Christopherson
2023-07-31 21:36       ` Michael S. Tsirkin
2023-08-01  0:21         ` Peter Xu
2023-08-01 16:23           ` Sean Christopherson
2023-08-01 16:48   ` Claudio Fontana
2023-08-01 16:52     ` Claudio Fontana
2023-08-02  8:05       ` Xiaoyao Li
2023-07-31 16:21 ` Xiaoyao Li [this message]
2023-08-01 17:10   ` [RFC PATCH 05/19] kvm: Enable KVM_SET_USER_MEMORY_REGION2 for memslot Claudio Fontana
2023-08-03  8:43     ` Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 06/19] i386/pc: Drop pc_machine_kvm_type() Xiaoyao Li
2023-08-02 23:00   ` Isaku Yamahata
2023-07-31 16:21 ` [RFC PATCH 07/19] target/i386: Implement mc->kvm_type() to get VM type Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 08/19] HostMem: Add private property to indicate to use kvm gmem Xiaoyao Li
2023-07-31 17:22   ` Markus Armbruster
2023-08-01 14:54     ` Xiaoyao Li
2023-08-01 14:57     ` Daniel P. Berrangé
2023-08-02  8:04       ` Xiaoyao Li
2023-08-01 17:21   ` David Hildenbrand
2023-08-02  8:03     ` Xiaoyao Li
2023-08-02 14:14       ` David Hildenbrand
2023-08-02 22:53         ` Isaku Yamahata
2023-08-03 13:05           ` David Hildenbrand
2023-07-31 16:21 ` [RFC PATCH 09/19] i386/kvm: Create gmem fd for KVM_X86_SW_PROTECTED_VM Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 10/19] kvm: Introduce support for memory_attributes Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 11/19] kvm/memory: Introduce the infrastructure to set the default shared/private value Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 12/19] i386/kvm: Set memory to default private for KVM_X86_SW_PROTECTED_VM Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 13/19] physmem: replace function name with __func__ in ram_block_discard_range() Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 14/19] physmem: Add ram_block_convert_range Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 15/19] kvm: handle KVM_EXIT_MEMORY_FAULT Xiaoyao Li
2023-08-02 22:25   ` Isaku Yamahata
2023-09-13  6:59     ` Xiaoyao Li
2023-08-09 15:02   ` Xu Yilun
2023-09-13  7:00     ` Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 16/19] trace/kvm: Add trace for page convertion between shared and private Xiaoyao Li
2023-07-31 16:21 ` [RFC PATCH 17/19] pci-host/q35: Move PAM initialization above SMRAM initialization Xiaoyao Li
2023-07-31 16:22 ` [RFC PATCH 18/19] q35: Introduce smm_ranges property for q35-pci-host Xiaoyao Li
2023-07-31 16:22 ` [RFC PATCH 19/19] i386: Disable SMM mode for X86_SW_PROTECTED_VM Xiaoyao Li
2023-08-02 22:27   ` Isaku Yamahata
2023-07-31 16:51 ` [RFC PATCH 00/19] QEMU gmem implemention Daniel P. Berrangé
2023-08-01  1:45   ` Xiaoyao Li
2023-08-10 15:58     ` Michael Roth via
2023-08-14 21:45       ` Isaku Yamahata
2023-07-31 17:10 ` Isaku Yamahata
2023-08-01  1:55   ` Xiaoyao Li

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=20230731162201.271114-6-xiaoyao.li@intel.com \
    --to=xiaoyao.li@intel.com \
    --cc=armbru@redhat.com \
    --cc=berrange@redhat.com \
    --cc=chao.p.peng@linux.intel.com \
    --cc=david@redhat.com \
    --cc=eblake@redhat.com \
    --cc=imammedo@redhat.com \
    --cc=isaku.yamahata@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=marcel.apfelbaum@gmail.com \
    --cc=michael.roth@amd.com \
    --cc=mst@redhat.com \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=philmd@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=seanjc@google.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).