Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

* Various fixes
* libdaxctl support to correctly align devdax character devices (Jingqi)
* initial-all-set support for live migration (Jay)
* forbid '-numa node, mem' for 5.1 and newer machine types (Igor)
* x87 fixes (Joseph)
* Tighten memory_region_access_valid (Michael) and fix fallout (myself)
* Replay fixes (Pavel)

# gpg: Signature made Fri 26 Jun 2020 14:42:17 BST
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "[email protected]"
# gpg: Good signature from "Paolo Bonzini <[email protected]>" [full]
# gpg:                 aka "Paolo Bonzini <[email protected]>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream: (31 commits)
  i386: Mask SVM features if nested SVM is disabled
  ibex_uart: fix XOR-as-pow
  vmport: move compat properties to hw_compat_5_0
  hyperv: vmbus: Remove the 2nd IRQ
  kvm: i386: allow TSC to differ by NTP correction bounds without TSC scaling
  numa: forbid '-numa node, mem' for 5.1 and newer machine types
  osdep: Make MIN/MAX evaluate arguments only once
  target/i386: Add notes for versioned CPU models
  target/i386: reimplement fpatan using floatx80 operations
  target/i386: reimplement fyl2x using floatx80 operations
  target/i386: reimplement fyl2xp1 using floatx80 operations
  target/i386: reimplement fprem, fprem1 using floatx80 operations
  softfloat: return low bits of quotient from floatx80_modrem
  softfloat: do not set denominator high bit for floatx80 remainder
  softfloat: do not return pseudo-denormal from floatx80 remainder
  softfloat: fix floatx80 remainder pseudo-denormal check for zero
  softfloat: merge floatx80_mod and floatx80_rem
  target/i386: reimplement f2xm1 using floatx80 operations
  xen: Actually fix build without passthrough
  Makefile: Install qemu-[qmp/ga]-ref.* into the directory "interop"
  ...

Signed-off-by: Peter Maydell <[email protected]>

Author: pm215

Makefile

@@ -873,8 +873,9 @@ install-sphinxdocs: sphinxdocs
 install-doc: $(DOCS) install-sphinxdocs
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)"
 	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/index.html "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.html "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.txt "$(DESTDIR)$(qemu_docdir)"
+	$(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)/interop"
+	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.html "$(DESTDIR)$(qemu_docdir)/interop"
+	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.txt "$(DESTDIR)$(qemu_docdir)/interop"
 ifdef CONFIG_POSIX
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
 	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/system/qemu.1 "$(DESTDIR)$(mandir)/man1"
@@ -892,8 +893,9 @@ ifdef CONFIG_TRACE_SYSTEMTAP
 endif
 ifneq (,$(findstring qemu-ga,$(TOOLS)))
 	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/interop/qemu-ga.8 "$(DESTDIR)$(mandir)/man8"
-	$(INSTALL_DATA) docs/interop/qemu-ga-ref.html "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) docs/interop/qemu-ga-ref.txt "$(DESTDIR)$(qemu_docdir)"
+	$(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)/interop"
+	$(INSTALL_DATA) docs/interop/qemu-ga-ref.html "$(DESTDIR)$(qemu_docdir)/interop"
+	$(INSTALL_DATA) docs/interop/qemu-ga-ref.txt "$(DESTDIR)$(qemu_docdir)/interop"
 	$(INSTALL_DATA) docs/interop/qemu-ga-ref.7 "$(DESTDIR)$(mandir)/man7"
 endif
 endif

accel/kvm/kvm-all.c

@@ -101,7 +101,7 @@ struct KVMState
     bool kernel_irqchip_required;
     OnOffAuto kernel_irqchip_split;
     bool sync_mmu;
-    bool manual_dirty_log_protect;
+    uint64_t manual_dirty_log_protect;
     /* The man page (and posix) say ioctl numbers are signed int, but
      * they're not.  Linux, glibc and *BSD all treat ioctl numbers as
      * unsigned, and treating them as signed here can break things */
@@ -1995,6 +1995,7 @@ static int kvm_init(MachineState *ms)
     int ret;
     int type = 0;
     const char *kvm_type;
+    uint64_t dirty_log_manual_caps;
 
     s = KVM_STATE(ms->accelerator);
 
@@ -2120,14 +2121,20 @@ static int kvm_init(MachineState *ms)
     s->coalesced_pio = s->coalesced_mmio &&
                        kvm_check_extension(s, KVM_CAP_COALESCED_PIO);
 
-    s->manual_dirty_log_protect =
+    dirty_log_manual_caps =
         kvm_check_extension(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
-    if (s->manual_dirty_log_protect) {
-        ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0, 1);
+    dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+                              KVM_DIRTY_LOG_INITIALLY_SET);
+    s->manual_dirty_log_protect = dirty_log_manual_caps;
+    if (dirty_log_manual_caps) {
+        ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0,
+                                   dirty_log_manual_caps);
         if (ret) {
-            warn_report("Trying to enable KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 "
-                        "but failed.  Falling back to the legacy mode. ");
-            s->manual_dirty_log_protect = false;
+            warn_report("Trying to enable capability %"PRIu64" of "
+                        "KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 but failed. "
+                        "Falling back to the legacy mode. ",
+                        dirty_log_manual_caps);
+            s->manual_dirty_log_protect = 0;
         }
     }
 

accel/tcg/translate-all.c

@@ -2582,9 +2582,9 @@ int page_check_range(target_ulong start, target_ulong len, int flags)
     /* This function should never be called with addresses outside the
        guest address space.  If this assert fires, it probably indicates
        a missing call to h2g_valid.  */
-#if TARGET_ABI_BITS > L1_MAP_ADDR_SPACE_BITS
-    assert(start < ((target_ulong)1 << L1_MAP_ADDR_SPACE_BITS));
-#endif
+    if (TARGET_ABI_BITS > L1_MAP_ADDR_SPACE_BITS) {
+        assert(start < ((target_ulong)1 << L1_MAP_ADDR_SPACE_BITS));
+    }
 
     if (len == 0) {
         return 0;

configure

@@ -518,6 +518,7 @@ plugins="no"
 fuzzing="no"
 rng_none="no"
 secret_keyring=""
+libdaxctl=""
 
 supported_cpu="no"
 supported_os="no"
@@ -1626,6 +1627,10 @@ for opt do
   ;;
   --disable-keyring) secret_keyring="no"
   ;;
+  --enable-libdaxctl) libdaxctl=yes
+  ;;
+  --disable-libdaxctl) libdaxctl=no
+  ;;
   *)
       echo "ERROR: unknown option $opt"
       echo "Try '$0 --help' for more information"
@@ -1927,6 +1932,7 @@ disabled with --disable-FEATURE, default is enabled if available:
   libpmem         libpmem support
   xkbcommon       xkbcommon support
   rng-none        dummy RNG, avoid using /dev/(u)random and getrandom()
+  libdaxctl       libdaxctl support
 
 NOTE: The object files are built at the place where configure is launched
 EOF
@@ -6360,6 +6366,24 @@ if test "$libpmem" != "no"; then
 	fi
 fi
 
+##########################################
+# check for libdaxctl
+
+if test "$libdaxctl" != "no"; then
+	if $pkg_config --atleast-version=57 "libdaxctl"; then
+		libdaxctl="yes"
+		libdaxctl_libs=$($pkg_config --libs libdaxctl)
+		libdaxctl_cflags=$($pkg_config --cflags libdaxctl)
+		libs_softmmu="$libs_softmmu $libdaxctl_libs"
+		QEMU_CFLAGS="$QEMU_CFLAGS $libdaxctl_cflags"
+	else
+		if test "$libdaxctl" = "yes" ; then
+			feature_not_found "libdaxctl" "Install libdaxctl"
+		fi
+		libdaxctl="no"
+	fi
+fi
+
 ##########################################
 # check for slirp
 
@@ -6967,6 +6991,7 @@ echo "parallels support $parallels"
 echo "sheepdog support  $sheepdog"
 echo "capstone          $capstone"
 echo "libpmem support   $libpmem"
+echo "libdaxctl support $libdaxctl"
 echo "libudev           $libudev"
 echo "default devices   $default_devices"
 echo "plugin support    $plugins"
@@ -7800,6 +7825,10 @@ if test "$libpmem" = "yes" ; then
   echo "CONFIG_LIBPMEM=y" >> $config_host_mak
 fi
 
+if test "$libdaxctl" = "yes" ; then
+  echo "CONFIG_LIBDAXCTL=y" >> $config_host_mak
+fi
+
 if test "$bochs" = "yes" ; then
   echo "CONFIG_BOCHS=y" >> $config_host_mak
 fi

cpus.c

@@ -1374,6 +1374,13 @@ static int64_t tcg_get_icount_limit(void)
     }
 }
 
+static void notify_aio_contexts(void)
+{
+    /* Wake up other AioContexts.  */
+    qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
+    qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
+}
+
 static void handle_icount_deadline(void)
 {
     assert(qemu_in_vcpu_thread());
@@ -1382,9 +1389,7 @@ static void handle_icount_deadline(void)
                                                       QEMU_TIMER_ATTR_ALL);
 
         if (deadline == 0) {
-            /* Wake up other AioContexts.  */
-            qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
-            qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
+            notify_aio_contexts();
         }
     }
 }
@@ -1407,6 +1412,10 @@ static void prepare_icount_for_run(CPUState *cpu)
         cpu->icount_extra = cpu->icount_budget - insns_left;
 
         replay_mutex_lock();
+
+        if (cpu->icount_budget == 0 && replay_has_checkpoint()) {
+            notify_aio_contexts();
+        }
     }
 }
 

docs/index.html.in

@@ -12,8 +12,8 @@
             <li><a href="tools/index.html">Tools Guide</a></li>
             <li><a href="interop/index.html">System Emulation Management and Interoperability Guide</a></li>
             <li><a href="specs/index.html">System Emulation Guest Hardware Specifications</a></li>
-            <li><a href="qemu-qmp-ref.html">QMP Reference Manual</a></li>
-            <li><a href="qemu-ga-ref.html">Guest Agent Protocol Reference</a></li>
+            <li><a href="interop/qemu-qmp-ref.html">QMP Reference Manual</a></li>
+            <li><a href="interop/qemu-ga-ref.html">Guest Agent Protocol Reference</a></li>
         </ul>
     </body>
 </html>

docs/nvdimm.txt

@@ -132,6 +132,16 @@ address to the page size (getpagesize(2)) by default. However, some
 types of backends may require an alignment different than the page
 size. In that case, QEMU v2.12.0 and later provide 'align' option to
 memory-backend-file to allow users to specify the proper alignment.
+For device dax (e.g., /dev/dax0.0), this alignment needs to match the
+alignment requirement of the device dax. The NUM of 'align=NUM' option
+must be larger than or equal to the 'align' of device dax.
+We can use one of the following commands to show the 'align' of device dax.
+
+    ndctl list -X
+    daxctl list -R
+
+In order to get the proper 'align' of device dax, you need to install
+the library 'libdaxctl'.
 
 For example, device dax require the 2 MB alignment, so we can use
 following QEMU command line options to use it (/dev/dax0.0) as the

docs/system/deprecated.rst

@@ -95,23 +95,6 @@ error in the future.
 The ``-realtime mlock=on|off`` argument has been replaced by the
 ``-overcommit mem-lock=on|off`` argument.
 
-``-numa node,mem=``\ *size* (since 4.1)
-'''''''''''''''''''''''''''''''''''''''
-
-The parameter ``mem`` of ``-numa node`` is used to assign a part of
-guest RAM to a NUMA node. But when using it, it's impossible to manage specified
-RAM chunk on the host side (like bind it to a host node, setting bind policy, ...),
-so guest end-ups with the fake NUMA configuration with suboptiomal performance.
-However since 2014 there is an alternative way to assign RAM to a NUMA node
-using parameter ``memdev``, which does the same as ``mem`` and adds
-means to actualy manage node RAM on the host side. Use parameter ``memdev``
-with *memory-backend-ram* backend as an replacement for parameter ``mem``
-to achieve the same fake NUMA effect or a properly configured
-*memory-backend-file* backend to actually benefit from NUMA configuration.
-In future new machine versions will not accept the option but it will still
-work with old machine types. User can check QAPI schema to see if the legacy
-option is supported by looking at MachineInfo::numa-mem-supported property.
-
 ``-numa`` node (without memory specified) (since 4.1)
 '''''''''''''''''''''''''''''''''''''''''''''''''''''
 
@@ -553,3 +536,23 @@ long starting at 1MiB, the old command::
 can be rewritten as::
 
   qemu-nbd -t --image-opts driver=raw,offset=1M,size=100M,file.driver=qcow2,file.file.driver=file,file.file.filename=file.qcow2
+
+Command line options
+--------------------
+
+``-numa node,mem=``\ *size* (removed in 5.1)
+''''''''''''''''''''''''''''''''''''''''''''
+
+The parameter ``mem`` of ``-numa node`` was used to assign a part of
+guest RAM to a NUMA node. But when using it, it's impossible to manage a specified
+RAM chunk on the host side (like bind it to a host node, setting bind policy, ...),
+so the guest ends up with the fake NUMA configuration with suboptiomal performance.
+However since 2014 there is an alternative way to assign RAM to a NUMA node
+using parameter ``memdev``, which does the same as ``mem`` and adds
+means to actually manage node RAM on the host side. Use parameter ``memdev``
+with *memory-backend-ram* backend as replacement for parameter ``mem``
+to achieve the same fake NUMA effect or a properly configured
+*memory-backend-file* backend to actually benefit from NUMA configuration.
+New machine versions (since 5.1) will not accept the option but it will still
+work with old machine types. User can check the QAPI schema to see if the legacy
+option is supported by looking at MachineInfo::numa-mem-supported property.

exec.c

@@ -77,6 +77,10 @@
 
 #include "monitor/monitor.h"
 
+#ifdef CONFIG_LIBDAXCTL
+#include <daxctl/libdaxctl.h>
+#endif
+
 //#define DEBUG_SUBPAGE
 
 #if !defined(CONFIG_USER_ONLY)
@@ -1745,6 +1749,46 @@ static int64_t get_file_size(int fd)
     return size;
 }
 
+static int64_t get_file_align(int fd)
+{
+    int64_t align = -1;
+#if defined(__linux__) && defined(CONFIG_LIBDAXCTL)
+    struct stat st;
+
+    if (fstat(fd, &st) < 0) {
+        return -errno;
+    }
+
+    /* Special handling for devdax character devices */
+    if (S_ISCHR(st.st_mode)) {
+        g_autofree char *path = NULL;
+        g_autofree char *rpath = NULL;
+        struct daxctl_ctx *ctx;
+        struct daxctl_region *region;
+        int rc = 0;
+
+        path = g_strdup_printf("/sys/dev/char/%d:%d",
+                    major(st.st_rdev), minor(st.st_rdev));
+        rpath = realpath(path, NULL);
+
+        rc = daxctl_new(&ctx);
+        if (rc) {
+            return -1;
+        }
+
+        daxctl_region_foreach(ctx, region) {
+            if (strstr(rpath, daxctl_region_get_path(region))) {
+                align = daxctl_region_get_align(region);
+                break;
+            }
+        }
+        daxctl_unref(ctx);
+    }
+#endif /* defined(__linux__) && defined(CONFIG_LIBDAXCTL) */
+
+    return align;
+}
+
 static int file_ram_open(const char *path,
                          const char *region_name,
                          bool *created,
@@ -2296,7 +2340,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
 {
     RAMBlock *new_block;
     Error *local_err = NULL;
-    int64_t file_size;
+    int64_t file_size, file_align;
 
     /* Just support these ram flags by now. */
     assert((ram_flags & ~(RAM_SHARED | RAM_PMEM)) == 0);
@@ -2332,6 +2376,14 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
         return NULL;
     }
 
+    file_align = get_file_align(fd);
+    if (file_align > 0 && mr && file_align > mr->align) {
+        error_setg(errp, "backing store align 0x%" PRIx64
+                   " is larger than 'align' option 0x%" PRIx64,
+                   file_align, mr->align);
+        return NULL;
+    }
+
     new_block = g_malloc0(sizeof(*new_block));
     new_block->mr = mr;
     new_block->used_length = size;