[PATCH V2 05/22] vl: memfd-alloc option

From: Steve Sistare <steven.sistare@oracle.com>
To: qemu-devel@nongnu.org
Cc: "Daniel P. Berrange" <berrange@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	"Jason Zeng" <jason.zeng@linux.intel.com>,
	"Alex Bennée" <alex.bennee@linaro.org>,
	"Juan Quintela" <quintela@redhat.com>,
	"Dr. David Alan Gilbert" <dgilbert@redhat.com>,
	"Markus Armbruster" <armbru@redhat.com>,
	"Alex Williamson" <alex.williamson@redhat.com>,
	"Steve Sistare" <steven.sistare@oracle.com>,
	"Stefan Hajnoczi" <stefanha@redhat.com>,
	"Marc-André Lureau" <marcandre.lureau@redhat.com>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Philippe Mathieu-Daudé" <philmd@redhat.com>
Subject: [PATCH V2 05/22] vl: memfd-alloc option
Date: Tue,  5 Jan 2021 07:41:53 -0800	[thread overview]
Message-ID: <1609861330-129855-6-git-send-email-steven.sistare@oracle.com> (raw)
In-Reply-To: <1609861330-129855-1-git-send-email-steven.sistare@oracle.com>

Allocate anonymous memory using memfd_create if the memfd-alloc option is
set.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
---
 exec.c                  | 38 ++++++++++++++++++++++++++++++--------
 include/sysemu/sysemu.h |  1 +
 qemu-options.hx         | 11 +++++++++++
 softmmu/vl.c            |  4 ++++
 trace-events            |  1 +
 5 files changed, 47 insertions(+), 8 deletions(-)

diff --git a/exec.c b/exec.c
index d1f31b4..6da6590 100644
--- a/exec.c
+++ b/exec.c
@@ -67,6 +67,7 @@
 #include "exec/log.h"
 
 #include "qemu/pmem.h"
+#include "qemu/memfd.h"
 
 #include "migration/vmstate.h"
 
@@ -2231,34 +2232,55 @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared)
 {
     RAMBlock *block;
     RAMBlock *last_block = NULL;
+    struct MemoryRegion *mr = new_block->mr;
     ram_addr_t old_ram_size, new_ram_size;
     Error *err = NULL;
+    const char *name;
+    void *addr = 0;
+    size_t maxlen;
 
     old_ram_size = last_ram_page();
 
     qemu_mutex_lock_ramlist();
-    new_block->offset = find_ram_offset(new_block->max_length);
+    maxlen = new_block->max_length;
+    new_block->offset = find_ram_offset(maxlen);
 
     if (!new_block->host) {
         if (xen_enabled()) {
-            xen_ram_alloc(new_block->offset, new_block->max_length,
-                          new_block->mr, &err);
+            xen_ram_alloc(new_block->offset, maxlen, new_block->mr, &err);
             if (err) {
                 error_propagate(errp, err);
                 qemu_mutex_unlock_ramlist();
                 return;
             }
         } else {
-            new_block->host = phys_mem_alloc(new_block->max_length,
-                                             &new_block->mr->align, shared);
-            if (!new_block->host) {
+            name = memory_region_name(new_block->mr);
+            if (memfd_alloc) {
+                int mfd = -1;          /* placeholder until next patch */
+                mr->align = QEMU_VMALLOC_ALIGN;
+                if (mfd < 0) {
+                    mfd = qemu_memfd_create(name, maxlen + mr->align,
+                                            0, 0, 0, &err);
+                    if (mfd < 0) {
+                        return;
+                    }
+                }
+                new_block->flags |= RAM_SHARED;
+                addr = file_ram_alloc(new_block, maxlen, mfd, false, errp);
+                trace_anon_memfd_alloc(name, maxlen, addr, mfd);
+            } else {
+                addr = phys_mem_alloc(maxlen, &mr->align, shared);
+            }
+
+            if (!addr) {
                 error_setg_errno(errp, errno,
                                  "cannot set up guest memory '%s'",
-                                 memory_region_name(new_block->mr));
+                                 name);
                 qemu_mutex_unlock_ramlist();
                 return;
             }
-            memory_try_enable_merging(new_block->host, new_block->max_length);
+            memory_try_enable_merging(addr, maxlen);
+            new_block->host = addr;
         }
     }
 
diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index 4b6a5c4..408eb56 100644
--- a/include/sysemu/sysemu.h
+++ b/include/sysemu/sysemu.h
@@ -13,6 +13,7 @@ extern int only_migratable;
 extern const char *qemu_name;
 extern QemuUUID qemu_uuid;
 extern bool qemu_uuid_set;
+extern bool memfd_alloc;
 
 void qemu_add_data_dir(const char *path);
 
diff --git a/qemu-options.hx b/qemu-options.hx
index 708583b..455b43b7 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4094,6 +4094,17 @@ SRST
     an unmigratable state.
 ERST
 
+#ifdef __linux__
+DEF("memfd-alloc", 0,  QEMU_OPTION_memfd_alloc, \
+    "-memfd-alloc         allocate anonymous memory using memfd_create\n",
+    QEMU_ARCH_ALL)
+#endif
+
+SRST
+``-memfd-alloc``
+    Allocate anonymous memory using memfd_create (Linux only).
+ERST
+
 DEF("nodefaults", 0, QEMU_OPTION_nodefaults, \
     "-nodefaults     don't create default devices\n", QEMU_ARCH_ALL)
 SRST
diff --git a/softmmu/vl.c b/softmmu/vl.c
index 4eb9d1f..5668e2b 100644
--- a/softmmu/vl.c
+++ b/softmmu/vl.c
@@ -164,6 +164,7 @@ bool boot_strict;
 uint8_t *boot_splash_filedata;
 int only_migratable; /* turn it off unless user states otherwise */
 bool wakeup_suspend_enabled;
+bool memfd_alloc;
 
 int icount_align_option;
 
@@ -3635,6 +3636,9 @@ void qemu_init(int argc, char **argv, char **envp)
             case QEMU_OPTION_only_migratable:
                 only_migratable = 1;
                 break;
+            case QEMU_OPTION_memfd_alloc:
+                memfd_alloc = true;
+                break;
             case QEMU_OPTION_nodefaults:
                 has_defaults = 0;
                 break;
diff --git a/trace-events b/trace-events
index 42107eb..ed46c4d 100644
--- a/trace-events
+++ b/trace-events
@@ -54,6 +54,7 @@ find_ram_offset_loop(uint64_t size, uint64_t candidate, uint64_t offset, uint64_
 ram_block_discard_range(const char *rbname, void *hva, size_t length, bool need_madvise, bool need_fallocate, int ret) "%s@%p + 0x%zx: madvise: %d fallocate: %d ret: %d"
 memory_notdirty_write_access(uint64_t vaddr, uint64_t ram_addr, unsigned size) "0x%" PRIx64 " ram_addr 0x%" PRIx64 " size %u"
 memory_notdirty_set_dirty(uint64_t vaddr) "0x%" PRIx64
+anon_memfd_alloc(const char *name, size_t size, void *ptr, int fd) "%s size %zu ptr %p fd %d"
 
 # memory.c
 memory_region_ops_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
-- 
1.8.3.1


