rpms/qemu-kvm
7
0
Fork 0
Code Issues Pull Requests Releases Activity

Mass import patches from 2.12.0

Browse Source
This commit is contained in:
Danilo C. L. de Paula 2018-11-08 15:02:33 -02:00
parent 58305efc05
commit ec15be19f0
105 changed files with 10496 additions and 3255 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3017
0003-Add-RHEL-machine-types.patch
View File

File diff suppressed because it is too large Load Diff

154
0001-Initial-redhat-build.patch → 0004-Initial-redhat-build.patch
View File

@ -1,10 +1,10 @@
From f03d3b79bc1908b0b6e257ee7aaa6567ecb91e38 Mon Sep 17 00:00:00 2001
From a1f1313c0c96b2a159647aabc6a4b0f3a3f4424a Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Mon, 11 Sep 2017 07:11:00 +0200
Date: Thu, 8 Nov 2018 11:17:08 +0100
Subject: Initial redhat build
This patch introduces redhat build structure in redhat subdirectory.
In addition, several issues are fixed in QEMU tree:
This patch introduces redhat build structure in redhat subdirectory. In addition,
several issues are fixed in QEMU tree:
- Change of app name for sasl_server_init in VNC code from qemu to qemu-kvm
- As we use qemu-kvm as name in all places, this is updated to be consistent
@ -12,134 +12,24 @@ In addition, several issues are fixed in QEMU tree:
- man page is installed using make install so we have to fix it in qemu tree
- Use "/share/qemu-kvm" as SHARE_SUFFIX
- We reconfigured our share to qemu-kvm to be consistent with used name
- Added .gitpublish configuration file
- Support for git publish has to be stored in repository root
Rebase changes (3.0.0):
- python detection changed
- added --disable-debug-mutex
This commit is synchronized with qemu-kvm-2.12.0-42.el8 build.
Merged patches (3.0.0):
- 9997a46 Fix annocheck issues
- 35230f9 redhat: remove extra % in rhel_rhev_conflicts macro(
- c747d3f redhat: syncronizing specfile
- e6abfc4 rpm: Add nvme VFIO driver to rw whitelist
- 7043465 rpm: Whitelist copy-on-read block driver
- f9a897c rpm: add throttle driver to rw whitelist
- b9ea80f redhat: replacing %pkname by %name
- eeeea85 redhat: Remove unused ApplyPatch macro
- b42c578 redhat:removing disable code for libcacard
- cee6bd5 redhat: improve packaging layout with modularization of the block layer
- 0cb4c60 redhat: Introducing qemu-kvm-core package
- 1ff4106 Add qemu-keymap to qemu-kvm-common
- 47838a5 redhat: Make gitpublish profile the default one
- a82f87b redhat: s390x: add hpage=1 to kvm.conf
- 3d52169 Enabling vhost_user
- 57aa228 spec: Enable Native Ceph support on all architectures
- 5f9ea03 Thu Jun 21 2018 Danilo C. L. de Paula <ddepaula@redhat.com> - 2.12.0-13.el8
- ed4d62a spec: Fix ambiguous 'python' interpreter name
- 74b3e6c qemu-ga: blacklisting guest-exec and guest-exec-status RPCs
- 2fd2cf7 redhat: rewrap "build_configure.sh" cmdline for the "rh-env-prep" target
- f48dc7f redhat: remove the VTD, LIVE_BLOCK_OPS, and RHV options in local builds too
- ccdf46b redhat: fix the "rh-env-prep" target's dependency on the SRPM_NAME macro
- f258fbf redhat: remove dead code related to s390 (not s390x)
- d186100 redhat: sync compiler flags from the spec file to "rh-env-prep"
- 727aa86 redhat: sync guest agent enablement and tcmalloc usage from spec to local
- b5d47e2 redhat: fix up Python 3 dependency for building QEMU
- 70c64dd redhat: fix up Python dependency for SRPM generation
- 96aca9f redhat: disable glusterfs dependency/support temporarily
- e9aff9d block/vxhs: modularize VXHS via g_module
- ecf40bf Defining a shebang for python scripts
- 55e3177 redhat: changing the prefix and blurb scheme to support rhel8-like handling
- 571e4ac Removing "rh-srpm-rhel" make target
- 9db09ef redhat: enforce python3 usage
- 56cda0b spec: Re-add dependency to seavgabios and ipxe for ppc64 architectures
- c780848 Drop build_configure.sh and Makefile.local files
- cca9118 Fix subject line in .gitpublish
- 9745e27 redhat: Update build configuration
- 193830c redhat: Disable vhost crypto
- 9dc30cb redhat: Make rh-local actually work in a RHEL-8 environment
- 99011c9 redhat: enable opengl, add build and runtime deps
- 7290e3f redhat: Improve python check
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
.gitpublish | 61 +-
Makefile | 3 +-
block/Makefile.objs | 2 +-
block/vxhs.c | 119 ++-
configure | 33 +-
configure | 40 +-
os-posix.c | 2 +-
redhat/.gitignore | 5 +
redhat/85-kvm.preset | 5 +
redhat/95-kvm-memlock.conf | 10 +
redhat/99-qemu-guest-agent.rules | 2 +
redhat/Makefile | 82 ++
redhat/Makefile.common | 47 ++
redhat/bridge.conf | 1 +
redhat/ksm.service | 13 +
redhat/ksm.sysconfig | 4 +
redhat/ksmctl.c | 77 ++
redhat/ksmtuned | 139 ++++
redhat/ksmtuned.conf | 21 +
redhat/ksmtuned.service | 12 +
redhat/kvm-s390x.conf | 19 +
redhat/kvm-setup | 40 +
redhat/kvm-setup.service | 14 +
redhat/kvm-x86.conf | 12 +
redhat/kvm.conf | 3 +
redhat/kvm.modules | 18 +
redhat/qemu-ga.sysconfig | 19 +
redhat/qemu-guest-agent.service | 20 +
redhat/qemu-kvm.spec.template | 1531 ++++++++++++++++++++++++++++++++++++
redhat/qemu-pr-helper.service | 15 +
redhat/qemu-pr-helper.socket | 9 +
redhat/rpmbuild/BUILD/.gitignore | 2 +
redhat/rpmbuild/RPMS/.gitignore | 2 +
redhat/rpmbuild/SOURCES/.gitignore | 2 +
redhat/rpmbuild/SPECS/.gitignore | 2 +
redhat/rpmbuild/SRPMS/.gitignore | 2 +
redhat/scripts/frh.py | 24 +
redhat/scripts/git-backport-diff | 327 ++++++++
redhat/scripts/git-compile-check | 215 +++++
redhat/scripts/process-patches.sh | 92 +++
redhat/scripts/tarball_checksum.sh | 3 +
redhat/vhost.conf | 3 +
redhat/Makefile.common | 49 ++
redhat/qemu-kvm.spec.template | 1721 +++++++++++++++++++++++++++++++++++++++++
ui/vnc.c | 2 +-
42 files changed, 2921 insertions(+), 93 deletions(-)
create mode 100644 redhat/.gitignore
create mode 100644 redhat/85-kvm.preset
create mode 100644 redhat/95-kvm-memlock.conf
create mode 100644 redhat/99-qemu-guest-agent.rules
9 files changed, 1972 insertions(+), 48 deletions(-)
create mode 100644 redhat/Makefile
create mode 100644 redhat/Makefile.common
create mode 100644 redhat/bridge.conf
create mode 100644 redhat/ksm.service
create mode 100644 redhat/ksm.sysconfig
create mode 100644 redhat/ksmctl.c
create mode 100644 redhat/ksmtuned
create mode 100644 redhat/ksmtuned.conf
create mode 100644 redhat/ksmtuned.service
create mode 100644 redhat/kvm-s390x.conf
create mode 100644 redhat/kvm-setup
create mode 100644 redhat/kvm-setup.service
create mode 100644 redhat/kvm-x86.conf
create mode 100644 redhat/kvm.conf
create mode 100644 redhat/kvm.modules
create mode 100644 redhat/qemu-ga.sysconfig
create mode 100644 redhat/qemu-guest-agent.service
create mode 100644 redhat/qemu-kvm.spec.template
create mode 100644 redhat/qemu-pr-helper.service
create mode 100644 redhat/qemu-pr-helper.socket
create mode 100644 redhat/rpmbuild/BUILD/.gitignore
create mode 100644 redhat/rpmbuild/RPMS/.gitignore
create mode 100644 redhat/rpmbuild/SOURCES/.gitignore
create mode 100644 redhat/rpmbuild/SPECS/.gitignore
create mode 100644 redhat/rpmbuild/SRPMS/.gitignore
create mode 100755 redhat/scripts/frh.py
create mode 100755 redhat/scripts/git-backport-diff
create mode 100755 redhat/scripts/git-compile-check
create mode 100755 redhat/scripts/process-patches.sh
create mode 100755 redhat/scripts/tarball_checksum.sh
create mode 100644 redhat/vhost.conf
diff --git a/Makefile b/Makefile
index 2da686b..eb4c57a 100644
@ -367,10 +257,26 @@ index 0cb0a00..9164b3e 100644
trace_vxhs_get_vdisk_stat_err(s->vdisk_guid, ret, errno);
return -EIO;
diff --git a/configure b/configure
index 2a7796e..0314d53 100755
index 2a7796e..0a27137 100755
--- a/configure
+++ b/configure
@@ -3460,7 +3460,7 @@ fi
@@ -2216,13 +2216,10 @@ fi
##########################################
# libseccomp check
+libseccomp_minver="2.2.0"
if test "$seccomp" != "no" ; then
case "$cpu" in
- i386|x86_64)
- libseccomp_minver="2.1.0"
- ;;
- mips)
- libseccomp_minver="2.2.0"
+ i386|x86_64|mips)
;;
arm|aarch64)
libseccomp_minver="2.2.3"
@@ -3460,7 +3457,7 @@ fi
glib_req_ver=2.40
glib_modules=gthread-2.0
@ -379,7 +285,7 @@ index 2a7796e..0314d53 100755
glib_modules="$glib_modules gmodule-export-2.0"
fi
@@ -5435,33 +5435,6 @@ if compile_prog "" "" ; then
@@ -5435,33 +5432,6 @@ if compile_prog "" "" ; then
fi
##########################################
@ -413,7 +319,7 @@ index 2a7796e..0314d53 100755
# check for _Static_assert()
have_static_assert=no
@@ -6759,8 +6732,8 @@ if test "$pthread_setname_np" = "yes" ; then
@@ -6759,8 +6729,8 @@ if test "$pthread_setname_np" = "yes" ; then
fi
if test "$vxhs" = "yes" ; then

22
0002-Enable-disable-devices-for-RHEL-7.patch → 0005-Enable-disable-devices-for-RHEL-7.patch
View File

@ -1,10 +1,10 @@
From 7472ed73f89c81f1ca4c86129eed0f5874d82c41 Mon Sep 17 00:00:00 2001
From b4a5b95153ca86eba72ff4a368a24ac31b77bbe5 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Mon, 11 Jan 2016 11:53:33 +0100
Subject: Enable/disable devices for RHEL 7
This commit adds all changes related to changes in supported devices
up to qemu-kvm-2.12.0-32.el8.
up to qemu-kvm-2.12.0-42.el8.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
@ -28,15 +28,16 @@ Merged patches (3.0.0):
- 747643c Disable new pvrdma device
- 0d4f38c s390x: Re-enable CONFIG_TERMINAL3270
- 0f725e9 AArch64: Enable CONFIG_FW_CFG_DMA for aarch64
- 67c5a8c Disable ivshmem
---
default-configs/aarch64-softmmu.mak | 37 +++++++++++++++++++++++++++++--------
default-configs/pci.mak | 36 ++++++++++++++++++------------------
default-configs/ppc64-softmmu.mak | 25 +++++++++++++++++++------
default-configs/aarch64-softmmu.mak | 37 ++++++++++++++++++++++++++++--------
default-configs/pci.mak | 38 ++++++++++++++++++-------------------
default-configs/ppc64-softmmu.mak | 25 ++++++++++++++++++------
default-configs/s390x-softmmu.mak | 5 +++--
default-configs/sound.mak | 8 ++++----
default-configs/usb.mak | 14 +++++++-------
default-configs/virtio.mak | 5 ++---
default-configs/x86_64-softmmu.mak | 28 ++++++++++++++--------------
default-configs/x86_64-softmmu.mak | 28 +++++++++++++--------------
hw/acpi/ich9.c | 4 ++--
hw/arm/Makefile.objs | 2 +-
hw/block/fdc.c | 1 +
@ -67,12 +68,12 @@ Merged patches (3.0.0):
stubs/Makefile.objs | 1 +
stubs/ide-isa.c | 13 +++++++++++++
target/arm/cpu.c | 4 +++-
target/i386/cpu.c | 35 +++++++++++++++++++++++++++--------
target/i386/cpu.c | 35 ++++++++++++++++++++++++++--------
target/ppc/cpu-models.c | 17 ++++++++++++++++-
target/s390x/cpu_models.c | 3 +++
target/s390x/kvm.c | 8 ++++++++
vl.c | 2 +-
43 files changed, 240 insertions(+), 98 deletions(-)
43 files changed, 241 insertions(+), 99 deletions(-)
create mode 100644 stubs/ide-isa.c
diff --git a/default-configs/aarch64-softmmu.mak b/default-configs/aarch64-softmmu.mak
@ -121,7 +122,7 @@ index 6f790f0..3f27540 100644
+CONFIG_I2C=y
+CONFIG_FW_CFG_DMA=y
diff --git a/default-configs/pci.mak b/default-configs/pci.mak
index de53d20..5cbe3e4 100644
index de53d20..70e40ad 100644
--- a/default-configs/pci.mak
+++ b/default-configs/pci.mak
@@ -4,22 +4,22 @@ CONFIG_ISA_BUS=y
@ -185,8 +186,9 @@ index de53d20..5cbe3e4 100644
CONFIG_EDU=y
CONFIG_VGA=y
CONFIG_VGA_PCI=y
CONFIG_IVSHMEM_DEVICE=$(CONFIG_IVSHMEM)
-CONFIG_IVSHMEM_DEVICE=$(CONFIG_IVSHMEM)
-CONFIG_ROCKER=y
+#CONFIG_IVSHMEM_DEVICE=$(CONFIG_IVSHMEM)
+#CONFIG_ROCKER=y
diff --git a/default-configs/ppc64-softmmu.mak b/default-configs/ppc64-softmmu.mak
index b94af6c..30ca76d 100644

764
0006-Machine-type-related-general-changes.patch Normal file
View File

@ -0,0 +1,764 @@
From e34179d713443601a16936e2e80b8fbd044429be Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 8 Nov 2018 11:59:55 +0100
Subject: Machine type related general changes
This patch is first part of original "Add RHEL machine types" patch we
split to allow easier review. It contains changes not related to any
architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
hw/acpi/ich9.c | 16 +++
hw/acpi/piix4.c | 6 +-
hw/char/serial.c | 16 +++
hw/display/cirrus_vga.c | 2 +-
hw/display/vga-isa.c | 2 +-
hw/net/e1000.c | 18 ++-
hw/net/e1000e.c | 21 ++++
hw/net/rtl8139.c | 4 +-
hw/smbios/smbios.c | 1 +
hw/timer/i8254_common.c | 2 +-
hw/timer/mc146818rtc.c | 6 +
hw/usb/hcd-uhci.c | 4 +-
hw/usb/hcd-xhci.c | 20 ++++
hw/usb/hcd-xhci.h | 2 +
include/hw/acpi/ich9.h | 3 +
include/hw/compat.h | 229 ++++++++++++++++++++++++++++++++++++++
include/hw/usb.h | 4 +
migration/migration.c | 2 +
migration/migration.h | 5 +
qdev-monitor.c | 1 -
scripts/vmstate-static-checker.py | 1 -
21 files changed, 354 insertions(+), 11 deletions(-)
diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c
index a4e87b8..23a7baa 100644
--- a/hw/acpi/ich9.c
+++ b/hw/acpi/ich9.c
@@ -441,6 +441,18 @@ static void ich9_pm_set_enable_tco(Object *obj, bool value, Error **errp)
s->pm.enable_tco = value;
}
+static bool ich9_pm_get_force_rev1_fadt(Object *obj, Error **errp)
+{
+ ICH9LPCState *s = ICH9_LPC_DEVICE(obj);
+ return s->pm.force_rev1_fadt;
+}
+
+static void ich9_pm_set_force_rev1_fadt(Object *obj, bool value, Error **errp)
+{
+ ICH9LPCState *s = ICH9_LPC_DEVICE(obj);
+ s->pm.force_rev1_fadt = value;
+}
+
void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm, Error **errp)
{
static const uint32_t gpe0_len = ICH9_PMIO_GPE0_LEN;
@@ -465,6 +477,10 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm, Error **errp)
ich9_pm_get_cpu_hotplug_legacy,
ich9_pm_set_cpu_hotplug_legacy,
NULL);
+ object_property_add_bool(obj, "__com.redhat_force-rev1-fadt",
+ ich9_pm_get_force_rev1_fadt,
+ ich9_pm_set_force_rev1_fadt,
+ NULL);
object_property_add(obj, ACPI_PM_PROP_S3_DISABLED, "uint8",
ich9_pm_get_disable_s3,
ich9_pm_set_disable_s3,
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index 6404af5..0f1f9e2 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -310,7 +310,7 @@ static const VMStateDescription vmstate_cpuhp_state = {
static const VMStateDescription vmstate_acpi = {
.name = "piix4_pm",
.version_id = 3,
- .minimum_version_id = 3,
+ .minimum_version_id = 2,
.minimum_version_id_old = 1,
.load_state_old = acpi_load_old,
.post_load = vmstate_acpi_post_load,
@@ -670,8 +670,8 @@ static void piix4_send_gpe(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
static Property piix4_pm_properties[] = {
DEFINE_PROP_UINT32("smb_io_base", PIIX4PMState, smb_io_base, 0),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 0),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 0),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 1),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 1),
DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_VAL, PIIX4PMState, s4_val, 2),
DEFINE_PROP_BOOL("acpi-pci-hotplug-with-bridge-support", PIIX4PMState,
use_acpi_pci_hotplug, true),
diff --git a/hw/char/serial.c b/hw/char/serial.c
index 251f40f..8e3520c 100644
--- a/hw/char/serial.c
+++ b/hw/char/serial.c
@@ -30,6 +30,7 @@
#include "qemu/timer.h"
#include "qemu/error-report.h"
#include "trace.h"
+#include "migration/migration.h"
//#define DEBUG_SERIAL
@@ -699,6 +700,9 @@ static int serial_post_load(void *opaque, int version_id)
static bool serial_thr_ipending_needed(void *opaque)
{
SerialState *s = opaque;
+ if (migrate_pre_2_2) {
+ return false;
+ }
if (s->ier & UART_IER_THRI) {
bool expected_value = ((s->iir & UART_IIR_ID) == UART_IIR_THRI);
@@ -780,6 +784,10 @@ static const VMStateDescription vmstate_serial_xmit_fifo = {
static bool serial_fifo_timeout_timer_needed(void *opaque)
{
SerialState *s = (SerialState *)opaque;
+ if (migrate_pre_2_2) {
+ return false;
+ }
+
return timer_pending(s->fifo_timeout_timer);
}
@@ -797,6 +805,10 @@ static const VMStateDescription vmstate_serial_fifo_timeout_timer = {
static bool serial_timeout_ipending_needed(void *opaque)
{
SerialState *s = (SerialState *)opaque;
+ if (migrate_pre_2_2) {
+ return false;
+ }
+
return s->timeout_ipending != 0;
}
@@ -814,6 +826,10 @@ static const VMStateDescription vmstate_serial_timeout_ipending = {
static bool serial_poll_needed(void *opaque)
{
SerialState *s = (SerialState *)opaque;
+ if (migrate_pre_2_2) {
+ return false;
+ }
+
return s->poll_msl >= 0;
}
diff --git a/hw/display/cirrus_vga.c b/hw/display/cirrus_vga.c
index 9fd5665..6910014 100644
--- a/hw/display/cirrus_vga.c
+++ b/hw/display/cirrus_vga.c
@@ -3061,7 +3061,7 @@ static void isa_cirrus_vga_realizefn(DeviceState *dev, Error **errp)
static Property isa_cirrus_vga_properties[] = {
DEFINE_PROP_UINT32("vgamem_mb", struct ISACirrusVGAState,
- cirrus_vga.vga.vram_size_mb, 4),
+ cirrus_vga.vga.vram_size_mb, 16),
DEFINE_PROP_BOOL("blitter", struct ISACirrusVGAState,
cirrus_vga.enable_blitter, true),
DEFINE_PROP_END_OF_LIST(),
diff --git a/hw/display/vga-isa.c b/hw/display/vga-isa.c
index fa44242..7835c83 100644
--- a/hw/display/vga-isa.c
+++ b/hw/display/vga-isa.c
@@ -80,7 +80,7 @@ static void vga_isa_realizefn(DeviceState *dev, Error **errp)
}
static Property vga_isa_properties[] = {
- DEFINE_PROP_UINT32("vgamem_mb", ISAVGAState, state.vram_size_mb, 8),
+ DEFINE_PROP_UINT32("vgamem_mb", ISAVGAState, state.vram_size_mb, 16),
DEFINE_PROP_END_OF_LIST(),
};
diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index 742cd0a..7d568da 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -1663,6 +1663,16 @@ static void pci_e1000_realize(PCIDevice *pci_dev, Error **errp)
pci_conf = pci_dev->config;
+ if (!(d->compat_flags & E1000_FLAG_AUTONEG)) {
+ /*
+ * We have no capabilities, so capability list bit should normally be 0.
+ * Keep it on for compat machine types to avoid breaking migration.
+ * HACK: abuse E1000_FLAG_AUTONEG, which is off exactly for
+ * the machine types that need this.
+ */
+ pci_set_word(pci_conf + PCI_STATUS, PCI_STATUS_CAP_LIST);
+ }
+
/* TODO: RST# value should be 0, PCI spec 6.2.4 */
pci_conf[PCI_CACHE_LINE_SIZE] = 0x10;
@@ -1763,7 +1773,7 @@ static const TypeInfo e1000_base_info = {
static const E1000Info e1000_devices[] = {
{
- .name = "e1000",
+ .name = "e1000-82540em",
.device_id = E1000_DEV_ID_82540EM,
.revision = 0x03,
.phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT,
@@ -1784,6 +1794,11 @@ static const E1000Info e1000_devices[] = {
#endif
};
+static const TypeInfo e1000_default_info = {
+ .name = "e1000",
+ .parent = "e1000-82540em",
+};
+
static void e1000_register_types(void)
{
int i;
@@ -1801,6 +1816,7 @@ static void e1000_register_types(void)
type_register(&type_info);
}
+ type_register_static(&e1000_default_info);
}
type_init(e1000_register_types)
diff --git a/hw/net/e1000e.c b/hw/net/e1000e.c
index 510ddb3..f1de9e5 100644
--- a/hw/net/e1000e.c
+++ b/hw/net/e1000e.c
@@ -75,6 +75,11 @@ typedef struct E1000EState {
E1000ECore core;
+ /* 7.3 had the intr_state field that was in the original e1000e code
+ * but that was removed prior to 2.7's release
+ */
+ bool redhat_7_3_intr_state_enable;
+ uint32_t redhat_7_3_intr_state;
} E1000EState;
#define E1000E_MMIO_IDX 0
@@ -90,6 +95,10 @@ typedef struct E1000EState {
#define E1000E_MSIX_TABLE (0x0000)
#define E1000E_MSIX_PBA (0x2000)
+/* Values as in RHEL 7.3 build and original upstream */
+#define RH_E1000E_USE_MSI BIT(0)
+#define RH_E1000E_USE_MSIX BIT(1)
+
static uint64_t
e1000e_mmio_read(void *opaque, hwaddr addr, unsigned size)
{
@@ -301,6 +310,8 @@ e1000e_init_msix(E1000EState *s)
} else {
if (!e1000e_use_msix_vectors(s, E1000E_MSIX_VEC_NUM)) {
msix_uninit(d, &s->msix, &s->msix);
+ } else {
+ s->redhat_7_3_intr_state |= RH_E1000E_USE_MSIX;
}
}
}
@@ -472,6 +483,8 @@ static void e1000e_pci_realize(PCIDevice *pci_dev, Error **errp)
ret = msi_init(PCI_DEVICE(s), 0xD0, 1, true, false, NULL);
if (ret) {
trace_e1000e_msi_init_fail(ret);
+ } else {
+ s->redhat_7_3_intr_state |= RH_E1000E_USE_MSI;
}
if (e1000e_add_pm_capability(pci_dev, e1000e_pmrb_offset,
@@ -595,6 +608,11 @@ static const VMStateDescription e1000e_vmstate_intr_timer = {
VMSTATE_STRUCT_ARRAY(_f, _s, _num, 0, \
e1000e_vmstate_intr_timer, E1000IntrDelayTimer)
+static bool rhel_7_3_check(void *opaque, int version_id)
+{
+ return ((E1000EState *)opaque)->redhat_7_3_intr_state_enable;
+}
+
static const VMStateDescription e1000e_vmstate = {
.name = "e1000e",
.version_id = 1,
@@ -606,6 +624,7 @@ static const VMStateDescription e1000e_vmstate = {
VMSTATE_MSIX(parent_obj, E1000EState),
VMSTATE_UINT32(ioaddr, E1000EState),
+ VMSTATE_UINT32_TEST(redhat_7_3_intr_state, E1000EState, rhel_7_3_check),
VMSTATE_UINT32(core.rxbuf_min_shift, E1000EState),
VMSTATE_UINT8(core.rx_desc_len, E1000EState),
VMSTATE_UINT32_ARRAY(core.rxbuf_sizes, E1000EState,
@@ -654,6 +673,8 @@ static PropertyInfo e1000e_prop_disable_vnet,
static Property e1000e_properties[] = {
DEFINE_NIC_PROPERTIES(E1000EState, conf),
+ DEFINE_PROP_BOOL("__redhat_e1000e_7_3_intr_state", E1000EState,
+ redhat_7_3_intr_state_enable, false),
DEFINE_PROP_SIGNED("disable_vnet_hdr", E1000EState, disable_vnet, false,
e1000e_prop_disable_vnet, bool),
DEFINE_PROP_SIGNED("subsys_ven", E1000EState, subsys_ven,
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 46daa16..05453e7 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -3174,7 +3174,7 @@ static int rtl8139_pre_save(void *opaque)
static const VMStateDescription vmstate_rtl8139 = {
.name = "rtl8139",
- .version_id = 5,
+ .version_id = 4,
.minimum_version_id = 3,
.post_load = rtl8139_post_load,
.pre_save = rtl8139_pre_save,
@@ -3255,7 +3255,9 @@ static const VMStateDescription vmstate_rtl8139 = {
VMSTATE_UINT32(tally_counters.TxMCol, RTL8139State),
VMSTATE_UINT64(tally_counters.RxOkPhy, RTL8139State),
VMSTATE_UINT64(tally_counters.RxOkBrd, RTL8139State),
+#if 0 /* Disabled for Red Hat Enterprise Linux bz 1420195 */
VMSTATE_UINT32_V(tally_counters.RxOkMul, RTL8139State, 5),
+#endif
VMSTATE_UINT16(tally_counters.TxAbt, RTL8139State),
VMSTATE_UINT16(tally_counters.TxUndrn, RTL8139State),
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index a27e54b..144e6e9 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -775,6 +775,7 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
SMBIOS_SET_DEFAULT(type1.manufacturer, manufacturer);
SMBIOS_SET_DEFAULT(type1.product, product);
SMBIOS_SET_DEFAULT(type1.version, version);
+ SMBIOS_SET_DEFAULT(type1.family, "Red Hat Enterprise Linux");
SMBIOS_SET_DEFAULT(type2.manufacturer, manufacturer);
SMBIOS_SET_DEFAULT(type2.product, product);
SMBIOS_SET_DEFAULT(type2.version, version);
diff --git a/hw/timer/i8254_common.c b/hw/timer/i8254_common.c
index 6190b6f..ad2ad2d 100644
--- a/hw/timer/i8254_common.c
+++ b/hw/timer/i8254_common.c
@@ -268,7 +268,7 @@ static const VMStateDescription vmstate_pit_common = {
.pre_save = pit_dispatch_pre_save,
.post_load = pit_dispatch_post_load,
.fields = (VMStateField[]) {
- VMSTATE_UINT32_V(channels[0].irq_disabled, PITCommonState, 3),
+ VMSTATE_UINT32(channels[0].irq_disabled, PITCommonState), /* qemu-kvm's v2 had 'flags' here */
VMSTATE_STRUCT_ARRAY(channels, PITCommonState, 3, 2,
vmstate_pit_channel, PITChannelState),
VMSTATE_INT64(channels[0].next_transition_time,
diff --git a/hw/timer/mc146818rtc.c b/hw/timer/mc146818rtc.c
index 6f1f723..68c353f 100644
--- a/hw/timer/mc146818rtc.c
+++ b/hw/timer/mc146818rtc.c
@@ -34,6 +34,7 @@
#include "qapi/qapi-commands-misc.h"
#include "qapi/qapi-events-misc.h"
#include "qapi/visitor.h"
+#include "migration/migration.h"
#ifdef TARGET_I386
#include "hw/i386/apic.h"
@@ -839,6 +840,11 @@ static int rtc_post_load(void *opaque, int version_id)
static bool rtc_irq_reinject_on_ack_count_needed(void *opaque)
{
RTCState *s = (RTCState *)opaque;
+
+ if (migrate_pre_2_2) {
+ return false;
+ }
+
return s->irq_reinject_on_ack_count != 0;
}
diff --git a/hw/usb/hcd-uhci.c b/hw/usb/hcd-uhci.c
index 836b11f..9d7b9df 100644
--- a/hw/usb/hcd-uhci.c
+++ b/hw/usb/hcd-uhci.c
@@ -1214,12 +1214,14 @@ static void usb_uhci_common_realize(PCIDevice *dev, Error **errp)
UHCIState *s = UHCI(dev);
uint8_t *pci_conf = s->dev.config;
int i;
+ int irq_pin;
pci_conf[PCI_CLASS_PROG] = 0x00;
/* TODO: reset value should be 0. */
pci_conf[USB_SBRN] = USB_RELEASE_1; // release number
- pci_config_set_interrupt_pin(pci_conf, u->info.irq_pin + 1);
+ irq_pin = u->info.irq_pin;
+ pci_config_set_interrupt_pin(pci_conf, irq_pin + 1);
if (s->masterbus) {
USBPort *ports[NB_PORTS];
diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c
index 8f1a01a..ca19474 100644
--- a/hw/usb/hcd-xhci.c
+++ b/hw/usb/hcd-xhci.c
@@ -3560,9 +3560,27 @@ static const VMStateDescription vmstate_xhci_slot = {
}
};
+static int xhci_event_pre_save(void *opaque)
+{
+ XHCIEvent *s = opaque;
+
+ s->cve_2014_5263_a = ((uint8_t *)&s->type)[0];
+ s->cve_2014_5263_b = ((uint8_t *)&s->type)[1];
+
+ return 0;
+}
+
+bool migrate_cve_2014_5263_xhci_fields;
+
+static bool xhci_event_cve_2014_5263(void *opaque, int version_id)
+{
+ return migrate_cve_2014_5263_xhci_fields;
+}
+
static const VMStateDescription vmstate_xhci_event = {
.name = "xhci-event",
.version_id = 1,
+ .pre_save = xhci_event_pre_save,
.fields = (VMStateField[]) {
VMSTATE_UINT32(type, XHCIEvent),
VMSTATE_UINT32(ccode, XHCIEvent),
@@ -3571,6 +3589,8 @@ static const VMStateDescription vmstate_xhci_event = {
VMSTATE_UINT32(flags, XHCIEvent),
VMSTATE_UINT8(slotid, XHCIEvent),
VMSTATE_UINT8(epid, XHCIEvent),
+ VMSTATE_UINT8_TEST(cve_2014_5263_a, XHCIEvent, xhci_event_cve_2014_5263),
+ VMSTATE_UINT8_TEST(cve_2014_5263_b, XHCIEvent, xhci_event_cve_2014_5263),
VMSTATE_END_OF_LIST()
}
};
diff --git a/hw/usb/hcd-xhci.h b/hw/usb/hcd-xhci.h
index fc36a4c..89d4cf7 100644
--- a/hw/usb/hcd-xhci.h
+++ b/hw/usb/hcd-xhci.h
@@ -153,6 +153,8 @@ typedef struct XHCIEvent {
uint32_t flags;
uint8_t slotid;
uint8_t epid;
+ uint8_t cve_2014_5263_a;
+ uint8_t cve_2014_5263_b;
} XHCIEvent;
typedef struct XHCIInterrupter {
diff --git a/include/hw/acpi/ich9.h b/include/hw/acpi/ich9.h
index 59aeb06..7b5cc25 100644
--- a/include/hw/acpi/ich9.h
+++ b/include/hw/acpi/ich9.h
@@ -61,6 +61,9 @@ typedef struct ICH9LPCPMRegs {
uint8_t smm_enabled;
bool enable_tco;
TCOIORegs tco_regs;
+
+ /* RH addition, see bz 1489800 */
+ bool force_rev1_fadt;
} ICH9LPCPMRegs;
#define ACPI_PM_PROP_TCO_ENABLED "enable_tco"
diff --git a/include/hw/compat.h b/include/hw/compat.h
index c08f404..22262c7 100644
--- a/include/hw/compat.h
+++ b/include/hw/compat.h
@@ -282,4 +282,233 @@
.value = "on",\
},
+/* Mostly like HW_COMPAT_2_1 but:
+ * we don't need virtio-scsi-pci since 7.0 already had that on
+ *
+ * RH: Note, qemu-extended-regs should have been enabled in the 7.1
+ * machine type, but was accidentally turned off in 7.2 onwards.
+ *
+ */
+#define HW_COMPAT_RHEL7_1 \
+ { /* COMPAT_RHEL7.1 */ \
+ .driver = "intel-hda-generic",\
+ .property = "old_msi_addr",\
+ .value = "on",\
+ },{\
+ .driver = "VGA",\
+ .property = "qemu-extended-regs",\
+ .value = "off",\
+ },{\
+ .driver = "secondary-vga",\
+ .property = "qemu-extended-regs",\
+ .value = "off",\
+ },{\
+ .driver = "usb-mouse",\
+ .property = "usb_version",\
+ .value = stringify(1),\
+ },{\
+ .driver = "usb-kbd",\
+ .property = "usb_version",\
+ .value = stringify(1),\
+ },{\
+ .driver = "virtio-pci",\
+ .property = "virtio-pci-bus-master-bug-migration",\
+ .value = "on",\
+ },{\
+ .driver = "virtio-blk-pci",\
+ .property = "any_layout",\
+ .value = "off",\
+ },{\
+ .driver = "virtio-balloon-pci",\
+ .property = "any_layout",\
+ .value = "off",\
+ },{\
+ .driver = "virtio-serial-pci",\
+ .property = "any_layout",\
+ .value = "off",\
+ },{\
+ .driver = "virtio-9p-pci",\
+ .property = "any_layout",\
+ .value = "off",\
+ },{\
+ .driver = "virtio-rng-pci",\
+ .property = "any_layout",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_1 - introduced with 2.10.0 */ \
+ .driver = "migration",\
+ .property = "send-configuration",\
+ .value = "off",\
+ },
+
+/* Mostly like HW_COMPAT_2_4 + 2_3 but:
+ * we don't need "any_layout" as it has been backported to 7.2
+ */
+
+#define HW_COMPAT_RHEL7_2 \
+ {\
+ .driver = "virtio-blk-device",\
+ .property = "scsi",\
+ .value = "true",\
+ },{\
+ .driver = "e1000-82540em",\
+ .property = "extra_mac_registers",\
+ .value = "off",\
+ },{\
+ .driver = "virtio-pci",\
+ .property = "x-disable-pcie",\
+ .value = "on",\
+ },{\
+ .driver = "virtio-pci",\
+ .property = "migrate-extra",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_2 */ \
+ .driver = "fw_cfg_mem",\
+ .property = "dma_enabled",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_2 */ \
+ .driver = "fw_cfg_io",\
+ .property = "dma_enabled",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_2 */ \
+ .driver = "isa-fdc",\
+ .property = "fallback",\
+ .value = "144",\
+ },{ /* HW_COMPAT_RHEL7_2 */ \
+ .driver = "virtio-pci",\
+ .property = "disable-modern",\
+ .value = "on",\
+ },{ /* HW_COMPAT_RHEL7_2 */ \
+ .driver = "virtio-pci",\
+ .property = "disable-legacy",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_2 */ \
+ .driver = TYPE_PCI_DEVICE,\
+ .property = "x-pcie-lnksta-dllla",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_2 */ \
+ .driver = "virtio-pci",\
+ .property = "page-per-vq",\
+ .value = "on",\
+ },{ /* HW_COMPAT_RHEL7_2 - introduced with 2.10.0 */ \
+ .driver = "migration",\
+ .property = "send-section-footer",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_2 - introduced with 2.10.0 */ \
+ .driver = "migration",\
+ .property = "store-global-state",\
+ .value = "off",\
+ },
+
+/* Mostly like HW_COMPAT_2_6 + HW_COMPAT_2_7 + HW_COMPAT_2_8 except
+ * disable-modern, disable-legacy, page-per-vq have already been
+ * backported to RHEL7.3
+ */
+#define HW_COMPAT_RHEL7_3 \
+ { /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "virtio-mmio",\
+ .property = "format_transport_address",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "virtio-serial-device",\
+ .property = "emergency-write",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "ioapic",\
+ .property = "version",\
+ .value = "0x11",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "intel-iommu",\
+ .property = "x-buggy-eim",\
+ .value = "true",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "virtio-pci",\
+ .property = "x-ignore-backend-features",\
+ .value = "on",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "fw_cfg_mem",\
+ .property = "x-file-slots",\
+ .value = stringify(0x10),\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "fw_cfg_io",\
+ .property = "x-file-slots",\
+ .value = stringify(0x10),\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "pflash_cfi01",\
+ .property = "old-multiple-chip-handling",\
+ .value = "on",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = TYPE_PCI_DEVICE,\
+ .property = "x-pcie-extcap-init",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "virtio-pci",\
+ .property = "x-pcie-deverr-init",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "virtio-pci",\
+ .property = "x-pcie-lnkctl-init",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "virtio-pci",\
+ .property = "x-pcie-pm-init",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "virtio-net-device",\
+ .property = "x-mtu-bypass-backend",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_3 */ \
+ .driver = "e1000e",\
+ .property = "__redhat_e1000e_7_3_intr_state",\
+ .value = "on",\
+ },
+
+/* Mostly like HW_COMPAT_2_9 except
+ * x-mtu-bypass-backend, x-migrate-msix has already been
+ * backported to RHEL7.4. shpc was already on in 7.4.
+ */
+#define HW_COMPAT_RHEL7_4 \
+ { /* HW_COMPAT_RHEL7_4 */ \
+ .driver = "intel-iommu",\
+ .property = "pt",\
+ .value = "off",\
+ },
+
+/* The same as HW_COMPAT_2_11 + HW_COMPAT_2_10 */
+#define HW_COMPAT_RHEL7_5 \
+ { /* HW_COMPAT_RHEL7_5 from HW_COMPAT_2_11 */ \
+ .driver = "hpet",\
+ .property = "hpet-offset-saved",\
+ .value = "false",\
+ },{ /* HW_COMPAT_RHEL7_5 from HW_COMPAT_2_11 */ \
+ .driver = "virtio-blk-pci",\
+ .property = "vectors",\
+ .value = "2",\
+ },{ /* HW_COMPAT_RHEL7_5 from HW_COMPAT_2_11 */ \
+ .driver = "vhost-user-blk-pci",\
+ .property = "vectors",\
+ .value = "2",\
+ },{ /* HW_COMPAT_RHEL7_5 from HW_COMPAT_2_11 but \
+ bz 1608778 modified for our naming */ \
+ .driver = "e1000-82540em",\
+ .property = "migrate_tso_props",\
+ .value = "off",\
+ },{ /* HW_COMPAT_RHEL7_5 from HW_COMPAT_2_10 */ \
+ .driver = "virtio-mouse-device",\
+ .property = "wheel-axis",\
+ .value = "false",\
+ },{ /* HW_COMPAT_RHEL7_5 from HW_COMPAT_2_10 */ \
+ .driver = "virtio-tablet-device",\
+ .property = "wheel-axis",\
+ .value = "false",\
+ },{ /* HW_COMPAT_RHEL7_5 */ \
+ .driver = "cirrus-vga",\
+ .property = "vgamem_mb",\
+ .value = "16",\
+ },{ /* HW_COMPAT_RHEL7_5 */ \
+ .driver = "migration",\
+ .property = "decompress-error-check",\
+ .value = "off",\
+ },
+
+
#endif /* HW_COMPAT_H */
diff --git a/include/hw/usb.h b/include/hw/usb.h
index a5080ad..b943ec9 100644
--- a/include/hw/usb.h
+++ b/include/hw/usb.h
@@ -606,4 +606,8 @@ int usb_get_quirks(uint16_t vendor_id, uint16_t product_id,
uint8_t interface_class, uint8_t interface_subclass,
uint8_t interface_protocol);
+
+/* hcd-xhci.c -- rhel7.0.0 machine type compatibility */
+extern bool migrate_cve_2014_5263_xhci_fields;
+
#endif
diff --git a/migration/migration.c b/migration/migration.c
index b7d9854..381039c 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -106,6 +106,8 @@ enum mig_rp_message_type {
MIG_RP_MSG_MAX
};
+bool migrate_pre_2_2;
+
/* When we add fault tolerance, we could have several
migrations at once. For now we don't need to add
dynamic creation of migration */
diff --git a/migration/migration.h b/migration/migration.h
index 64a7b33..405d984 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -288,6 +288,11 @@ void migrate_send_rp_resume_ack(MigrationIncomingState *mis, uint32_t value);
void dirty_bitmap_mig_before_vm_start(void);
void init_dirty_bitmap_incoming_migration(void);
+/*
+ * Disables a load of subsections that were added in 2.2/rh7.2 for backwards
+ * migration compatibility.
+ */
+extern bool migrate_pre_2_2;
#define qemu_ram_foreach_block \
#warning "Use qemu_ram_foreach_block_migratable in migration code"
diff --git a/qdev-monitor.c b/qdev-monitor.c
index 61e0300..f439b83 100644
--- a/qdev-monitor.c
+++ b/qdev-monitor.c
@@ -47,7 +47,6 @@ typedef struct QDevAlias
/* Please keep this table sorted by typename. */
static const QDevAlias qdev_alias_table[] = {
- { "e1000", "e1000-82540em" },
{ "ich9-ahci", "ahci" },
{ "lsi53c895a", "lsi" },
{ "virtio-9p-ccw", "virtio-9p", QEMU_ARCH_S390X },
diff --git a/scripts/vmstate-static-checker.py b/scripts/vmstate-static-checker.py
index d346728..4bca2bf 100755
--- a/scripts/vmstate-static-checker.py
+++ b/scripts/vmstate-static-checker.py
@@ -105,7 +105,6 @@ def get_changed_sec_name(sec):
# Section names can change -- see commit 292b1634 for an example.
changes = {
"ICH9 LPC": "ICH9-LPC",
- "e1000-82540em": "e1000",
}
for item in changes:
--
1.8.3.1

246
0007-Add-aarch64-machine-types.patch Normal file
View File

@ -0,0 +1,246 @@
From 2c0d79871ccb5383b1a91e5fc9139b6f8e8ed8e0 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 8 Nov 2018 12:00:54 +0100
Subject: Add aarch64 machine types
Adding changes to add RHEL machine types for aarch64 architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
hw/arm/virt.c | 126 +++++++++++++++++++++++++++++++++++++++++++++++++-
include/hw/arm/virt.h | 22 +++++++++
2 files changed, 147 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 281ddcd..b02e4a0 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -60,6 +60,7 @@
#include "standard-headers/linux/input.h"
#include "hw/arm/smmuv3.h"
+#if 0 /* disabled Red Hat Enterprise Linux */
#define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \
static void virt_##major##_##minor##_class_init(ObjectClass *oc, \
void *data) \
@@ -87,7 +88,36 @@
DEFINE_VIRT_MACHINE_LATEST(major, minor, true)
#define DEFINE_VIRT_MACHINE(major, minor) \
DEFINE_VIRT_MACHINE_LATEST(major, minor, false)
-
+#endif /* disabled for RHEL */
+
+#define DEFINE_RHEL_MACHINE_LATEST(m, n, s, latest) \
+ static void rhel##m##n##s##_virt_class_init(ObjectClass *oc, \
+ void *data) \
+ { \
+ MachineClass *mc = MACHINE_CLASS(oc); \
+ rhel##m##n##s##_virt_options(mc); \
+ mc->desc = "RHEL " # m "." # n "." # s " ARM Virtual Machine"; \
+ if (latest) { \
+ mc->alias = "virt"; \
+ mc->is_default = 1; \
+ } \
+ } \
+ static const TypeInfo rhel##m##n##s##_machvirt_info = { \
+ .name = MACHINE_TYPE_NAME("virt-rhel" # m "." # n "." # s), \
+ .parent = TYPE_RHEL_MACHINE, \
+ .instance_init = rhel##m##n##s##_virt_instance_init, \
+ .class_init = rhel##m##n##s##_virt_class_init, \
+ }; \
+ static void rhel##m##n##s##_machvirt_init(void) \
+ { \
+ type_register_static(&rhel##m##n##s##_machvirt_info); \
+ } \
+ type_init(rhel##m##n##s##_machvirt_init);
+
+#define DEFINE_RHEL_MACHINE_AS_LATEST(major, minor, subminor) \
+ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, true)
+#define DEFINE_RHEL_MACHINE(major, minor, subminor) \
+ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, false)
/* Number of external interrupt lines to configure the GIC with */
#define NUM_IRQS 256
@@ -1539,6 +1569,7 @@ static void machvirt_init(MachineState *machine)
qemu_add_machine_init_done_notifier(&vms->machine_done);
}
+#if 0 /* disabled for RHEL */
static bool virt_get_secure(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -1567,6 +1598,7 @@ static void virt_set_virt(Object *obj, bool value, Error **errp)
vms->virt = value;
}
+#endif /* disabled for RHEL */
static bool virt_get_highmem(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -1621,6 +1653,7 @@ static void virt_set_gic_version(Object *obj, const char *value, Error **errp)
}
}
+#if 0
static char *virt_get_iommu(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -1648,6 +1681,7 @@ static void virt_set_iommu(Object *obj, const char *value, Error **errp)
error_append_hint(errp, "Valid values are none, smmuv3.\n");
}
}
+#endif
static CpuInstanceProperties
virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index)
@@ -1687,6 +1721,7 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
return ms->possible_cpus;
}
+#if 0 /* disabled for RHEL */
static void virt_machine_device_plug_cb(HotplugHandler *hotplug_dev,
DeviceState *dev, Error **errp)
{
@@ -1835,6 +1870,9 @@ static void virt_machine_3_0_options(MachineClass *mc)
}
DEFINE_VIRT_MACHINE_AS_LATEST(3, 0)
+#define VIRT_COMPAT_2_12 \
+ HW_COMPAT_2_12
+
static void virt_2_12_instance_init(Object *obj)
{
virt_3_0_instance_init(obj);
@@ -1960,3 +1998,89 @@ static void virt_machine_2_6_options(MachineClass *mc)
vmc->no_pmu = true;
}
DEFINE_VIRT_MACHINE(2, 6)
+#endif /* disabled for RHEL */
+
+static void rhel_machine_class_init(ObjectClass *oc, void *data)
+{
+ MachineClass *mc = MACHINE_CLASS(oc);
+
+ mc->family = "virt-rhel-Z";
+ mc->init = machvirt_init;
+ /* Start max_cpus at the maximum QEMU supports. We'll further restrict
+ * it later in machvirt_init, where we have more information about the
+ * configuration of the particular instance.
+ */
+ mc->max_cpus = 255;
+ mc->block_default_type = IF_VIRTIO;
+ mc->no_cdrom = 1;
+ mc->pci_allow_0_address = true;
+ /* We know we will never create a pre-ARMv7 CPU which needs 1K pages */
+ mc->minimum_page_bits = 12;
+ mc->possible_cpu_arch_ids = virt_possible_cpu_arch_ids;
+ mc->cpu_index_to_instance_props = virt_cpu_index_to_props;
+ mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a57");
+ mc->get_default_cpu_node_id = virt_get_default_cpu_node_id;
+}
+
+static const TypeInfo rhel_machine_info = {
+ .name = TYPE_RHEL_MACHINE,
+ .parent = TYPE_MACHINE,
+ .abstract = true,
+ .instance_size = sizeof(VirtMachineState),
+ .class_size = sizeof(VirtMachineClass),
+ .class_init = rhel_machine_class_init,
+};
+
+static void rhel_machine_init(void)
+{
+ type_register_static(&rhel_machine_info);
+}
+type_init(rhel_machine_init);
+
+static void rhel760_virt_instance_init(Object *obj)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+ VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
+
+ /* EL3 is disabled by default and non-configurable for RHEL */
+ vms->secure = false;
+ /* EL2 is disabled by default and non-configurable for RHEL */
+ vms->virt = false;
+ /* High memory is enabled by default for RHEL */
+ vms->highmem = true;
+ object_property_add_bool(obj, "highmem", virt_get_highmem,
+ virt_set_highmem, NULL);
+ object_property_set_description(obj, "highmem",
+ "Set on/off to enable/disable using "
+ "physical address space above 32 bits",
+ NULL);
+ /* Default GIC type is still v2, but became configurable for RHEL */
+ vms->gic_version = 2;
+ object_property_add_str(obj, "gic-version", virt_get_gic_version,
+ virt_set_gic_version, NULL);
+ object_property_set_description(obj, "gic-version",
+ "Set GIC version. "
+ "Valid values are 2, 3 and host", NULL);
+
+ if (vmc->no_its) {
+ vms->its = false;
+ } else {
+ /* Default allows ITS instantiation */
+ vms->its = true;
+ object_property_add_bool(obj, "its", virt_get_its,
+ virt_set_its, NULL);
+ object_property_set_description(obj, "its",
+ "Set on/off to enable/disable "
+ "ITS instantiation",
+ NULL);
+ }
+
+ vms->memmap=a15memmap;
+ vms->irqmap=a15irqmap;
+}
+
+static void rhel760_virt_options(MachineClass *mc)
+{
+ SET_MACHINE_COMPAT(mc, ARM_RHEL_COMPAT);
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(7, 6, 0)
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 9a870cc..2293315 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -128,6 +128,7 @@ typedef struct {
#define VIRT_ECAM_ID(high) (high ? VIRT_PCIE_ECAM_HIGH : VIRT_PCIE_ECAM)
+#if 0 /* disabled for Red Hat Enterprise Linux */
#define TYPE_VIRT_MACHINE MACHINE_TYPE_NAME("virt")
#define VIRT_MACHINE(obj) \
OBJECT_CHECK(VirtMachineState, (obj), TYPE_VIRT_MACHINE)
@@ -136,6 +137,27 @@ typedef struct {
#define VIRT_MACHINE_CLASS(klass) \
OBJECT_CLASS_CHECK(VirtMachineClass, klass, TYPE_VIRT_MACHINE)
+#else
+#define TYPE_RHEL_MACHINE MACHINE_TYPE_NAME("virt-rhel")
+#define VIRT_MACHINE(obj) \
+ OBJECT_CHECK(VirtMachineState, (obj), TYPE_RHEL_MACHINE)
+#define VIRT_MACHINE_GET_CLASS(obj) \
+ OBJECT_GET_CLASS(VirtMachineClass, obj, TYPE_RHEL_MACHINE)
+#define VIRT_MACHINE_CLASS(klass) \
+ OBJECT_CLASS_CHECK(VirtMachineClass, klass, TYPE_RHEL_MACHINE)
+#endif
+
+/* This macro is for changes to properties that are RHEL specific,
+ * different to the current upstream and to be applied to the latest
+ * machine type.
+ */
+#define ARM_RHEL_COMPAT \
+ {\
+ .driver = "virtio-net-pci",\
+ .property = "romfile",\
+ .value = "",\
+ },
+
void virt_acpi_setup(VirtMachineState *vms);
/* Return the number of used redistributor regions */
--
1.8.3.1

397
0008-Add-ppc64-machine-types.patch Normal file
View File

@ -0,0 +1,397 @@
From b6c41d9cfe7ae58455737c967f2e47d6bc99d21e Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 8 Nov 2018 12:01:38 +0100
Subject: Add ppc64 machine types
Adding changes to add RHEL machine types for ppc64 architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
hw/ppc/spapr.c | 252 ++++++++++++++++++++++++++++++++++++++++++++++++
hw/ppc/spapr_cpu_core.c | 13 +++
include/hw/ppc/spapr.h | 1 +
target/ppc/compat.c | 13 ++-
target/ppc/cpu.h | 1 +
5 files changed, 279 insertions(+), 1 deletion(-)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 2f8c304..b8bdb69 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -4009,6 +4009,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_BROKEN;
smc->default_caps.caps[SPAPR_CAP_HPT_MAXPAGESIZE] = 16; /* 64kiB */
spapr_caps_add_properties(smc, &error_abort);
+ smc->has_power9_support = true;
}
static const TypeInfo spapr_machine_info = {
@@ -4059,6 +4060,7 @@ static const TypeInfo spapr_machine_info = {
} \
type_init(spapr_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/*
* pseries-3.0
*/
@@ -4248,6 +4250,7 @@ DEFINE_SPAPR_MACHINE(2_8, "2.8", false);
.property = "pre-2.8-migration", \
.value = "on", \
},
+#endif
static void phb_placement_2_7(sPAPRMachineState *spapr, uint32_t index,
uint64_t *buid, hwaddr *pio,
@@ -4298,6 +4301,7 @@ static void phb_placement_2_7(sPAPRMachineState *spapr, uint32_t index,
*/
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void spapr_machine_2_7_instance_options(MachineState *machine)
{
sPAPRMachineState *spapr = SPAPR_MACHINE(machine);
@@ -4457,6 +4461,254 @@ static void spapr_machine_2_1_class_options(MachineClass *mc)
SET_MACHINE_COMPAT(mc, SPAPR_COMPAT_2_1);
}
DEFINE_SPAPR_MACHINE(2_1, "2.1", false);
+#endif
+
+/*
+ * pseries-rhel7.6.0
+ */
+
+static void spapr_machine_rhel760_instance_options(MachineState *machine)
+{
+}
+
+static void spapr_machine_rhel760_class_options(MachineClass *mc)
+{
+ /* Defaults for the latest behaviour inherited from the base class */
+}
+
+DEFINE_SPAPR_MACHINE(rhel760, "rhel7.6.0", true);
+
+/*
+ * pseries-rhel7.6.0-sxxm
+ *
+ * pseries-rhel7.6.0 with speculative execution exploit mitigations enabled by default
+ */
+static void spapr_machine_rhel760sxxm_instance_options(MachineState *machine)
+{
+ spapr_machine_rhel760_instance_options(machine);
+}
+
+static void spapr_machine_rhel760sxxm_class_options(MachineClass *mc)
+{
+ sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel760_class_options(mc);
+ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_FIXED_CCD;
+}
+
+DEFINE_SPAPR_MACHINE(rhel760sxxm, "rhel7.6.0-sxxm", false);
+
+/*
+ * pseries-rhel7.5.0
+ * like SPAPR_COMPAT_2_11 and SPAPR_COMPAT_2_10
+ * SPAPR_CAP_HTM already enabled in 7.4
+ *
+ */
+#define SPAPR_COMPAT_RHEL7_5 \
+ HW_COMPAT_RHEL7_5 \
+
+static void spapr_machine_rhel750_instance_options(MachineState *machine)
+{
+ spapr_machine_rhel760_instance_options(machine);
+}
+
+static void spapr_machine_rhel750_class_options(MachineClass *mc)
+{
+ spapr_machine_rhel760_class_options(mc);
+ SET_MACHINE_COMPAT(mc, SPAPR_COMPAT_RHEL7_5);
+}
+
+DEFINE_SPAPR_MACHINE(rhel750, "rhel7.5.0", false);
+
+/*
+ * pseries-rhel7.5.0-sxxm
+ *
+ * pseries-rhel7.5.0 with speculative execution exploit mitigations enabled by default
+ */
+static void spapr_machine_rhel750sxxm_instance_options(MachineState *machine)
+{
+ spapr_machine_rhel750_instance_options(machine);
+}
+
+static void spapr_machine_rhel750sxxm_class_options(MachineClass *mc)
+{
+ sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel750_class_options(mc);
+ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_FIXED_CCD;
+}
+
+DEFINE_SPAPR_MACHINE(rhel750sxxm, "rhel7.5.0-sxxm", false);
+
+/*
+ * pseries-rhel7.4.0
+ * like SPAPR_COMPAT_2_9
+ */
+
+#define SPAPR_COMPAT_RHEL7_4 \
+ HW_COMPAT_RHEL7_4 \
+ { \
+ .driver = TYPE_POWERPC_CPU, \
+ .property = "pre-2.10-migration", \
+ .value = "on", \
+ }, \
+
+static void spapr_machine_rhel740_instance_options(MachineState *machine)
+{
+ spapr_machine_rhel750_instance_options(machine);
+}
+
+static void spapr_machine_rhel740_class_options(MachineClass *mc)
+{
+ sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel750_class_options(mc);
+ SET_MACHINE_COMPAT(mc, SPAPR_COMPAT_RHEL7_4);
+ mc->numa_auto_assign_ram = numa_legacy_auto_assign_ram;
+ smc->has_power9_support = false;
+ smc->pre_2_10_has_unused_icps = true;
+ smc->resize_hpt_default = SPAPR_RESIZE_HPT_DISABLED;
+ smc->default_caps.caps[SPAPR_CAP_HTM] = SPAPR_CAP_ON;
+}
+
+DEFINE_SPAPR_MACHINE(rhel740, "rhel7.4.0", false);
+
+/*
+ * pseries-rhel7.4.0-sxxm
+ *
+ * pseries-rhel7.4.0 with speculative execution exploit mitigations enabled by default
+ */
+static void spapr_machine_rhel740sxxm_instance_options(MachineState *machine)
+{
+ spapr_machine_rhel740_instance_options(machine);
+}
+
+static void spapr_machine_rhel740sxxm_class_options(MachineClass *mc)
+{
+ sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel740_class_options(mc);
+ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_FIXED_CCD;
+}
+
+DEFINE_SPAPR_MACHINE(rhel740sxxm, "rhel7.4.0-sxxm", false);
+
+/*
+ * pseries-rhel7.3.0
+ * like SPAPR_COMPAT_2_6/_2_7/_2_8 but "ddw" has been backported to RHEL7_3
+ */
+#define SPAPR_COMPAT_RHEL7_3 \
+ HW_COMPAT_RHEL7_3 \
+ { \
+ .driver = TYPE_SPAPR_PCI_HOST_BRIDGE, \
+ .property = "mem_win_size", \
+ .value = stringify(SPAPR_PCI_2_7_MMIO_WIN_SIZE),\
+ }, \
+ { \
+ .driver = TYPE_SPAPR_PCI_HOST_BRIDGE, \
+ .property = "mem64_win_size", \
+ .value = "0", \
+ }, \
+ { \
+ .driver = TYPE_POWERPC_CPU, \
+ .property = "pre-2.8-migration", \
+ .value = "on", \
+ }, \
+ { \
+ .driver = TYPE_SPAPR_PCI_HOST_BRIDGE, \
+ .property = "pre-2.8-migration", \
+ .value = "on", \
+ }, \
+ { \
+ .driver = TYPE_SPAPR_PCI_HOST_BRIDGE, \
+ .property = "pcie-extended-configuration-space",\
+ .value = "off", \
+ },
+
+static void spapr_machine_rhel730_instance_options(MachineState *machine)
+{
+ sPAPRMachineState *spapr = SPAPR_MACHINE(machine);
+
+ spapr_machine_rhel740_instance_options(machine);
+ spapr->use_hotplug_event_source = false;
+}
+
+static void spapr_machine_rhel730_class_options(MachineClass *mc)
+{
+ sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel740_class_options(mc);
+ mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power7_v2.3");
+ SET_MACHINE_COMPAT(mc, SPAPR_COMPAT_RHEL7_3);
+ smc->phb_placement = phb_placement_2_7;
+}
+
+DEFINE_SPAPR_MACHINE(rhel730, "rhel7.3.0", false);
+
+/*
+ * pseries-rhel7.3.0-sxxm
+ *
+ * pseries-rhel7.3.0 with speculative execution exploit mitigations enabled by default
+ */
+static void spapr_machine_rhel730sxxm_instance_options(MachineState *machine)
+{
+ spapr_machine_rhel730_instance_options(machine);
+}
+
+static void spapr_machine_rhel730sxxm_class_options(MachineClass *mc)
+{
+ sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel730_class_options(mc);
+ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_FIXED_CCD;
+}
+
+DEFINE_SPAPR_MACHINE(rhel730sxxm, "rhel7.3.0-sxxm", false);
+
+/*
+ * pseries-rhel7.2.0
+ */
+/* Should be like SPAPR_COMPAT_2_5 + 2_4 + 2_3, but "dynamic-reconfiguration"
+ * has been backported to RHEL7_2 so we don't need it here.
+ */
+
+#define SPAPR_COMPAT_RHEL7_2 \
+ HW_COMPAT_RHEL7_2 \
+ { \
+ .driver = "spapr-vlan", \
+ .property = "use-rx-buffer-pools", \
+ .value = "off", \
+ },{ \
+ .driver = TYPE_SPAPR_PCI_HOST_BRIDGE,\
+ .property = "ddw",\
+ .value = stringify(off),\
+ },
+
+
+static void spapr_machine_rhel720_instance_options(MachineState *machine)
+{
+ spapr_machine_rhel730_instance_options(machine);
+}
+
+static void spapr_machine_rhel720_class_options(MachineClass *mc)
+{
+ sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel730_class_options(mc);
+ smc->use_ohci_by_default = true;
+ mc->has_hotpluggable_cpus = NULL;
+ SET_MACHINE_COMPAT(mc, SPAPR_COMPAT_RHEL7_2);
+}
+
+DEFINE_SPAPR_MACHINE(rhel720, "rhel7.2.0", false);
static void spapr_machine_register_types(void)
{
diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
index fb29eec..a081b01 100644
--- a/hw/ppc/spapr_cpu_core.c
+++ b/hw/ppc/spapr_cpu_core.c
@@ -21,6 +21,7 @@
#include "sysemu/numa.h"
#include "sysemu/hw_accel.h"
#include "qemu/error-report.h"
+#include "cpu-models.h"
static void spapr_cpu_reset(void *opaque)
{
@@ -212,6 +213,7 @@ static void spapr_realize_vcpu(PowerPCCPU *cpu, sPAPRMachineState *spapr,
{
CPUPPCState *env = &cpu->env;
Error *local_err = NULL;
+ sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
object_property_set_bool(OBJECT(cpu), true, "realized", &local_err);
if (local_err) {
@@ -224,6 +226,17 @@ static void spapr_realize_vcpu(PowerPCCPU *cpu, sPAPRMachineState *spapr,
cpu_ppc_set_vhyp(cpu, PPC_VIRTUAL_HYPERVISOR(spapr));
kvmppc_set_papr(cpu);
+ if (!smc->has_power9_support &&
+ (((spapr->max_compat_pvr &&
+ ppc_compat_cmp(spapr->max_compat_pvr,
+ CPU_POWERPC_LOGICAL_3_00) >= 0)) ||
+ (!spapr->max_compat_pvr &&
+ ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0, 0)))) {
+ error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
+ "POWER9 CPU is not supported by this machine class");
+ return;
+ }
+
qemu_register_reset(spapr_cpu_reset, cpu);
spapr_cpu_reset(cpu);
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 7e5de1a..330c370 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -101,6 +101,7 @@ struct sPAPRMachineClass {
bool dr_lmb_enabled; /* enable dynamic-reconfig/hotplug of LMBs */
bool use_ohci_by_default; /* use USB-OHCI instead of XHCI */
bool pre_2_10_has_unused_icps;
+ bool has_power9_support;
void (*phb_placement)(sPAPRMachineState *spapr, uint32_t index,
uint64_t *buid, hwaddr *pio,
hwaddr *mmio32, hwaddr *mmio64,
diff --git a/target/ppc/compat.c b/target/ppc/compat.c
index 7de4bf3..3e2e353 100644
--- a/target/ppc/compat.c
+++ b/target/ppc/compat.c
@@ -105,8 +105,19 @@ static const CompatInfo *compat_by_pvr(uint32_t pvr)
return NULL;
}
+long ppc_compat_cmp(uint32_t pvr1, uint32_t pvr2)
+{
+ const CompatInfo *compat1 = compat_by_pvr(pvr1);
+ const CompatInfo *compat2 = compat_by_pvr(pvr2);
+
+ g_assert(compat1);
+ g_assert(compat2);
+
+ return compat1 - compat2;
+}
+
static bool pcc_compat(PowerPCCPUClass *pcc, uint32_t compat_pvr,
- uint32_t min_compat_pvr, uint32_t max_compat_pvr)
+ uint32_t min_compat_pvr, uint32_t max_compat_pvr)
{
const CompatInfo *compat = compat_by_pvr(compat_pvr);
const CompatInfo *min = compat_by_pvr(min_compat_pvr);
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index 4edcf62..532f0d5 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -1365,6 +1365,7 @@ static inline int cpu_mmu_index (CPUPPCState *env, bool ifetch)
/* Compatibility modes */
#if defined(TARGET_PPC64)
+long ppc_compat_cmp(uint32_t pvr1, uint32_t pvr2);
bool ppc_check_compat(PowerPCCPU *cpu, uint32_t compat_pvr,
uint32_t min_compat_pvr, uint32_t max_compat_pvr);
bool ppc_type_check_compat(const char *cputype, uint32_t compat_pvr,
--
1.8.3.1

86
0009-Add-s390x-machine-types.patch Normal file
View File

@ -0,0 +1,86 @@
From 05b950dccdf9e8f58f3358730aa4705642d0196f Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 8 Nov 2018 12:02:37 +0100
Subject: Add s390x machine types
Adding changes to add RHEL machine types for s390x architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
hw/s390x/s390-virtio-ccw.c | 46 +++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 45 insertions(+), 1 deletion(-)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 7983185..0f135c9 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -649,7 +649,7 @@ bool css_migration_enabled(void)
{ \
MachineClass *mc = MACHINE_CLASS(oc); \
ccw_machine_##suffix##_class_options(mc); \
- mc->desc = "VirtIO-ccw based S390 machine v" verstr; \
+ mc->desc = "VirtIO-ccw based S390 machine " verstr; \
if (latest) { \
mc->alias = "s390-ccw-virtio"; \
mc->is_default = 1; \
@@ -676,6 +676,8 @@ bool css_migration_enabled(void)
#define CCW_COMPAT_2_12 \
HW_COMPAT_2_12
+#if 0 /* Disabled for Red Hat Enterprise Linux */
+
#define CCW_COMPAT_2_11 \
HW_COMPAT_2_11 \
{\
@@ -898,6 +900,48 @@ static void ccw_machine_2_4_class_options(MachineClass *mc)
}
DEFINE_CCW_MACHINE(2_4, "2.4", false);
+#else
+
+/*
+ * like CCW_COMPAT_2_11, but includes HW_COMPAT_RHEL7_5 (derived from
+ * HW_COMPAT_2_11 and HW_COMPAT_2_10) instead of HW_COMPAT_2_11
+ */
+#define CCW_COMPAT_RHEL7_5 \
+ HW_COMPAT_RHEL7_5 \
+ {\
+ .driver = TYPE_SCLP_EVENT_FACILITY,\
+ .property = "allow_all_mask_sizes",\
+ .value = "off",\
+ },
+
+static void ccw_machine_rhel760_instance_options(MachineState *machine)
+{
+}
+
+static void ccw_machine_rhel760_class_options(MachineClass *mc)
+{
+}
+DEFINE_CCW_MACHINE(rhel760, "rhel7.6.0", true);
+
+static void ccw_machine_rhel750_instance_options(MachineState *machine)
+{
+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V2_11 };
+ ccw_machine_rhel760_instance_options(machine);
+
+ /* before 2.12 we emulated the very first z900, and RHEL 7.5 is
+ based on 2.10 */
+ s390_set_qemu_cpu_model(0x2064, 7, 1, qemu_cpu_feat);
+}
+
+static void ccw_machine_rhel750_class_options(MachineClass *mc)
+{
+ ccw_machine_rhel760_class_options(mc);
+ SET_MACHINE_COMPAT(mc, CCW_COMPAT_RHEL7_5);
+}
+DEFINE_CCW_MACHINE(rhel750, "rhel7.5.0", false);
+
+#endif
+
static void ccw_machine_register_types(void)
{
type_register_static(&ccw_machine_info);
--
1.8.3.1

1069
0010-Add-x86_64-machine-types.patch Normal file
View File

File diff suppressed because it is too large Load Diff

498
0011-Enable-make-check.patch Normal file
View File

@ -0,0 +1,498 @@
From f4e3d697cb6a18301b1279c0b07896eb5b228aa9 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 8 Nov 2018 12:03:48 +0100
Subject: Enable make check
Fixing tests after device disabling and machine types changes and enabling
make check run during build.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
redhat/qemu-kvm.spec.template | 2 +-
tests/Makefile.include | 123 +++++++++++++++++++++---------------------
tests/boot-serial-test.c | 6 ++-
tests/cpu-plug-test.c | 3 +-
tests/e1000-test.c | 2 +
tests/endianness-test.c | 2 +
tests/prom-env-test.c | 2 +
tests/qemu-iotests/051 | 12 ++---
tests/qemu-iotests/group | 4 +-
tests/qom-test.c | 2 +-
tests/test-x86-cpuid-compat.c | 2 +
tests/usb-hcd-xhci-test.c | 4 ++
12 files changed, 91 insertions(+), 73 deletions(-)
diff --git a/tests/Makefile.include b/tests/Makefile.include
index a492827..4b78396 100644
--- a/tests/Makefile.include
+++ b/tests/Makefile.include
@@ -184,8 +184,8 @@ gcov-files-generic-y = qdev-monitor.c qmp.c
check-qtest-generic-y += tests/cdrom-test$(EXESUF)
gcov-files-ipack-y += hw/ipack/ipack.c
-check-qtest-ipack-y += tests/ipoctal232-test$(EXESUF)
-gcov-files-ipack-y += hw/char/ipoctal232.c
+#check-qtest-ipack-y += tests/ipoctal232-test$(EXESUF)
+#gcov-files-ipack-y += hw/char/ipoctal232.c
check-qtest-virtioserial-y += tests/virtio-console-test$(EXESUF)
gcov-files-virtioserial-y += hw/char/virtio-console.c
@@ -217,23 +217,23 @@ check-qtest-pci-y += tests/e1000e-test$(EXESUF)
gcov-files-pci-y += hw/net/e1000e.c hw/net/e1000e_core.c
check-qtest-pci-y += tests/rtl8139-test$(EXESUF)
gcov-files-pci-y += hw/net/rtl8139.c
-check-qtest-pci-y += tests/pcnet-test$(EXESUF)
-gcov-files-pci-y += hw/net/pcnet.c
-gcov-files-pci-y += hw/net/pcnet-pci.c
-check-qtest-pci-y += tests/eepro100-test$(EXESUF)
-gcov-files-pci-y += hw/net/eepro100.c
-check-qtest-pci-y += tests/ne2000-test$(EXESUF)
-gcov-files-pci-y += hw/net/ne2000.c
-check-qtest-pci-y += tests/nvme-test$(EXESUF)
-gcov-files-pci-y += hw/block/nvme.c
+#check-qtest-pci-y += tests/pcnet-test$(EXESUF)
+#gcov-files-pci-y += hw/net/pcnet.c
+#gcov-files-pci-y += hw/net/pcnet-pci.c
+#check-qtest-pci-y += tests/eepro100-test$(EXESUF)
+#gcov-files-pci-y += hw/net/eepro100.c
+#check-qtest-pci-y += tests/ne2000-test$(EXESUF)
+#gcov-files-pci-y += hw/net/ne2000.c
+#check-qtest-pci-y += tests/nvme-test$(EXESUF)
+#gcov-files-pci-y += hw/block/nvme.c
check-qtest-pci-y += tests/ac97-test$(EXESUF)
gcov-files-pci-y += hw/audio/ac97.c
-check-qtest-pci-y += tests/es1370-test$(EXESUF)
-gcov-files-pci-y += hw/audio/es1370.c
+#check-qtest-pci-y += tests/es1370-test$(EXESUF)
+#gcov-files-pci-y += hw/audio/es1370.c
check-qtest-pci-y += $(check-qtest-virtio-y)
gcov-files-pci-y += $(gcov-files-virtio-y) hw/virtio/virtio-pci.c
-check-qtest-pci-y += tests/tpci200-test$(EXESUF)
-gcov-files-pci-y += hw/ipack/tpci200.c
+#check-qtest-pci-y += tests/tpci200-test$(EXESUF)
+#gcov-files-pci-y += hw/ipack/tpci200.c
check-qtest-pci-y += $(check-qtest-ipack-y)
gcov-files-pci-y += $(gcov-files-ipack-y)
check-qtest-pci-y += tests/display-vga-test$(EXESUF)
@@ -245,25 +245,25 @@ gcov-files-pci-y += hw/display/virtio-gpu-pci.c
gcov-files-pci-$(CONFIG_VIRTIO_VGA) += hw/display/virtio-vga.c
check-qtest-pci-y += tests/intel-hda-test$(EXESUF)
gcov-files-pci-y += hw/audio/intel-hda.c hw/audio/hda-codec.c
-check-qtest-pci-$(CONFIG_IVSHMEM) += tests/ivshmem-test$(EXESUF)
-gcov-files-pci-y += hw/misc/ivshmem.c
-check-qtest-pci-y += tests/megasas-test$(EXESUF)
-gcov-files-pci-y += hw/scsi/megasas.c
+check-qtest-pci-$(CONFIG_IVSHMEM_DEVICE) += tests/ivshmem-test$(EXESUF)
+gcov-files-pci-$(CONFIG_IVSHMEM_DEVICE) += hw/misc/ivshmem.c
+#check-qtest-pci-y += tests/megasas-test$(EXESUF)
+#gcov-files-pci-y += hw/scsi/megasas.c
check-qtest-i386-y = tests/endianness-test$(EXESUF)
-check-qtest-i386-y += tests/fdc-test$(EXESUF)
-gcov-files-i386-y = hw/block/fdc.c
+#check-qtest-i386-y += tests/fdc-test$(EXESUF)
+#gcov-files-i386-y = hw/block/fdc.c
check-qtest-i386-y += tests/ide-test$(EXESUF)
check-qtest-i386-y += tests/ahci-test$(EXESUF)
check-qtest-i386-y += tests/hd-geo-test$(EXESUF)
gcov-files-i386-y += hw/block/hd-geometry.c
check-qtest-i386-y += tests/boot-order-test$(EXESUF)
-check-qtest-i386-y += tests/bios-tables-test$(EXESUF)
+#check-qtest-i386-y += tests/bios-tables-test$(EXESUF)
check-qtest-i386-y += tests/boot-serial-test$(EXESUF)
check-qtest-i386-$(CONFIG_SLIRP) += tests/pxe-test$(EXESUF)
check-qtest-i386-y += tests/rtc-test$(EXESUF)
-check-qtest-i386-y += tests/ipmi-kcs-test$(EXESUF)
-check-qtest-i386-y += tests/ipmi-bt-test$(EXESUF)
+#check-qtest-i386-y += tests/ipmi-kcs-test$(EXESUF)
+#check-qtest-i386-y += tests/ipmi-bt-test$(EXESUF)
check-qtest-i386-y += tests/i440fx-test$(EXESUF)
check-qtest-i386-y += tests/fw_cfg-test$(EXESUF)
check-qtest-i386-y += tests/drive_del-test$(EXESUF)
@@ -272,8 +272,8 @@ check-qtest-i386-y += tests/tco-test$(EXESUF)
gcov-files-i386-y += hw/watchdog/watchdog.c hw/watchdog/wdt_ib700.c
check-qtest-i386-y += $(check-qtest-pci-y)
gcov-files-i386-y += $(gcov-files-pci-y)
-check-qtest-i386-y += tests/vmxnet3-test$(EXESUF)
-gcov-files-i386-y += hw/net/vmxnet3.c
+#check-qtest-i386-y += tests/vmxnet3-test$(EXESUF)
+#gcov-files-i386-y += hw/net/vmxnet3.c
gcov-files-i386-y += hw/net/net_rx_pkt.c
gcov-files-i386-y += hw/net/net_tx_pkt.c
check-qtest-i386-y += tests/pvpanic-test$(EXESUF)
@@ -282,8 +282,8 @@ check-qtest-i386-y += tests/i82801b11-test$(EXESUF)
gcov-files-i386-y += hw/pci-bridge/i82801b11.c
check-qtest-i386-y += tests/ioh3420-test$(EXESUF)
gcov-files-i386-y += hw/pci-bridge/ioh3420.c
-check-qtest-i386-y += tests/usb-hcd-ohci-test$(EXESUF)
-gcov-files-i386-y += hw/usb/hcd-ohci.c
+#check-qtest-i386-y += tests/usb-hcd-ohci-test$(EXESUF)
+#gcov-files-i386-y += hw/usb/hcd-ohci.c
check-qtest-i386-y += tests/usb-hcd-uhci-test$(EXESUF)
gcov-files-i386-y += hw/usb/hcd-uhci.c
check-qtest-i386-y += tests/usb-hcd-ehci-test$(EXESUF)
@@ -311,7 +311,7 @@ check-qtest-i386-y += tests/migration-test$(EXESUF)
check-qtest-i386-y += tests/test-x86-cpuid-compat$(EXESUF)
check-qtest-i386-y += tests/numa-test$(EXESUF)
check-qtest-x86_64-y += $(check-qtest-i386-y)
-check-qtest-x86_64-y += tests/sdhci-test$(EXESUF)
+#check-qtest-x86_64-y += tests/sdhci-test$(EXESUF)
gcov-files-i386-y += i386-softmmu/hw/timer/mc146818rtc.c
gcov-files-x86_64-y = $(subst i386-softmmu/,x86_64-softmmu/,$(gcov-files-i386-y))
@@ -332,34 +332,35 @@ check-qtest-mips64el-y = tests/endianness-test$(EXESUF)
check-qtest-moxie-y = tests/boot-serial-test$(EXESUF)
check-qtest-ppc-y = tests/endianness-test$(EXESUF)
-check-qtest-ppc-y += tests/boot-order-test$(EXESUF)
+#check-qtest-ppc-y += tests/boot-order-test$(EXESUF)
check-qtest-ppc-y += tests/prom-env-test$(EXESUF)
check-qtest-ppc-y += tests/drive_del-test$(EXESUF)
check-qtest-ppc-y += tests/boot-serial-test$(EXESUF)
-check-qtest-ppc-y += tests/m48t59-test$(EXESUF)
-gcov-files-ppc-y += hw/timer/m48t59.c
+#check-qtest-ppc-y += tests/m48t59-test$(EXESUF)
+#gcov-files-ppc-y += hw/timer/m48t59.c
check-qtest-ppc64-y = $(check-qtest-ppc-y)
gcov-files-ppc64-y = $(subst ppc-softmmu/,ppc64-softmmu/,$(gcov-files-ppc-y))
check-qtest-ppc64-y += tests/spapr-phb-test$(EXESUF)
gcov-files-ppc64-y += ppc64-softmmu/hw/ppc/spapr_pci.c
-check-qtest-ppc64-y += tests/pnv-xscom-test$(EXESUF)
+#check-qtest-ppc64-y += tests/pnv-xscom-test$(EXESUF)
check-qtest-ppc64-y += tests/migration-test$(EXESUF)
check-qtest-ppc64-y += tests/rtas-test$(EXESUF)
check-qtest-ppc64-$(CONFIG_SLIRP) += tests/pxe-test$(EXESUF)
-check-qtest-ppc64-y += tests/usb-hcd-ohci-test$(EXESUF)
-gcov-files-ppc64-y += hw/usb/hcd-ohci.c
-check-qtest-ppc64-y += tests/usb-hcd-uhci-test$(EXESUF)
-gcov-files-ppc64-y += hw/usb/hcd-uhci.c
+#check-qtest-ppc64-y += tests/usb-hcd-ohci-test$(EXESUF)
+#gcov-files-ppc64-y += hw/usb/hcd-ohci.c
+#check-qtest-ppc64-y += tests/usb-hcd-uhci-test$(EXESUF)
+#gcov-files-ppc64-y += hw/usb/hcd-uhci.c
check-qtest-ppc64-y += tests/usb-hcd-xhci-test$(EXESUF)
gcov-files-ppc64-y += hw/usb/hcd-xhci.c
check-qtest-ppc64-y += $(check-qtest-virtio-y)
-check-qtest-ppc64-$(CONFIG_SLIRP) += tests/test-netfilter$(EXESUF)
-check-qtest-ppc64-$(CONFIG_POSIX) += tests/test-filter-mirror$(EXESUF)
-check-qtest-ppc64-$(CONFIG_POSIX) += tests/test-filter-redirector$(EXESUF)
+#check-qtest-ppc64-$(CONFIG_SLIRP) += tests/test-netfilter$(EXESUF)
+#check-qtest-ppc64-$(CONFIG_POSIX) += tests/test-filter-mirror$(EXESUF)
+#check-qtest-ppc64-$(CONFIG_POSIX) += tests/test-filter-redirector$(EXESUF)
check-qtest-ppc64-y += tests/display-vga-test$(EXESUF)
check-qtest-ppc64-y += tests/numa-test$(EXESUF)
-check-qtest-ppc64-$(CONFIG_IVSHMEM) += tests/ivshmem-test$(EXESUF)
+check-qtest-ppc64-$(CONFIG_IVSHMEM_DEVICE) += tests/ivshmem-test$(EXESUF)
+gcov-files-ppc64-$(CONFIG_IVSHMEM_DEVICE) += hw/misc/ivshmem.c
check-qtest-ppc64-y += tests/cpu-plug-test$(EXESUF)
check-qtest-sh4-y = tests/endianness-test$(EXESUF)
@@ -388,7 +389,7 @@ check-qtest-arm-y += tests/boot-serial-test$(EXESUF)
check-qtest-arm-y += tests/sdhci-test$(EXESUF)
check-qtest-aarch64-y = tests/numa-test$(EXESUF)
-check-qtest-aarch64-y += tests/sdhci-test$(EXESUF)
+#check-qtest-aarch64-y += tests/sdhci-test$(EXESUF)
check-qtest-aarch64-y += tests/boot-serial-test$(EXESUF)
check-qtest-microblazeel-y = $(check-qtest-microblaze-y)
@@ -777,15 +778,15 @@ tests/endianness-test$(EXESUF): tests/endianness-test.o
tests/spapr-phb-test$(EXESUF): tests/spapr-phb-test.o $(libqos-obj-y)
tests/prom-env-test$(EXESUF): tests/prom-env-test.o $(libqos-obj-y)
tests/rtas-test$(EXESUF): tests/rtas-test.o $(libqos-spapr-obj-y)
-tests/fdc-test$(EXESUF): tests/fdc-test.o
+#tests/fdc-test$(EXESUF): tests/fdc-test.o
tests/ide-test$(EXESUF): tests/ide-test.o $(libqos-pc-obj-y)
tests/ahci-test$(EXESUF): tests/ahci-test.o $(libqos-pc-obj-y)
-tests/ipmi-kcs-test$(EXESUF): tests/ipmi-kcs-test.o
-tests/ipmi-bt-test$(EXESUF): tests/ipmi-bt-test.o
+#tests/ipmi-kcs-test$(EXESUF): tests/ipmi-kcs-test.o
+#tests/ipmi-bt-test$(EXESUF): tests/ipmi-bt-test.o
tests/hd-geo-test$(EXESUF): tests/hd-geo-test.o
tests/boot-order-test$(EXESUF): tests/boot-order-test.o $(libqos-obj-y)
tests/boot-serial-test$(EXESUF): tests/boot-serial-test.o $(libqos-obj-y)
-tests/bios-tables-test$(EXESUF): tests/bios-tables-test.o \
+#tests/bios-tables-test$(EXESUF): tests/bios-tables-test.o \
tests/boot-sector.o tests/acpi-utils.o $(libqos-obj-y)
tests/pxe-test$(EXESUF): tests/pxe-test.o tests/boot-sector.o $(libqos-obj-y)
tests/tmp105-test$(EXESUF): tests/tmp105-test.o $(libqos-omap-obj-y)
@@ -798,11 +799,11 @@ tests/fw_cfg-test$(EXESUF): tests/fw_cfg-test.o $(libqos-pc-obj-y)
tests/e1000-test$(EXESUF): tests/e1000-test.o
tests/e1000e-test$(EXESUF): tests/e1000e-test.o $(libqos-pc-obj-y)
tests/rtl8139-test$(EXESUF): tests/rtl8139-test.o $(libqos-pc-obj-y)
-tests/pcnet-test$(EXESUF): tests/pcnet-test.o
-tests/pnv-xscom-test$(EXESUF): tests/pnv-xscom-test.o
-tests/eepro100-test$(EXESUF): tests/eepro100-test.o
-tests/vmxnet3-test$(EXESUF): tests/vmxnet3-test.o
-tests/ne2000-test$(EXESUF): tests/ne2000-test.o
+#tests/pcnet-test$(EXESUF): tests/pcnet-test.o
+#tests/pnv-xscom-test$(EXESUF): tests/pnv-xscom-test.o
+#tests/eepro100-test$(EXESUF): tests/eepro100-test.o
+#tests/vmxnet3-test$(EXESUF): tests/vmxnet3-test.o
+#tests/ne2000-test$(EXESUF): tests/ne2000-test.o
tests/wdt_ib700-test$(EXESUF): tests/wdt_ib700-test.o
tests/tco-test$(EXESUF): tests/tco-test.o $(libqos-pc-obj-y)
tests/virtio-balloon-test$(EXESUF): tests/virtio-balloon-test.o $(libqos-virtio-obj-y)
@@ -813,22 +814,22 @@ tests/virtio-scsi-test$(EXESUF): tests/virtio-scsi-test.o $(libqos-virtio-obj-y)
tests/virtio-9p-test$(EXESUF): tests/virtio-9p-test.o $(libqos-virtio-obj-y)
tests/virtio-serial-test$(EXESUF): tests/virtio-serial-test.o $(libqos-virtio-obj-y)
tests/virtio-console-test$(EXESUF): tests/virtio-console-test.o $(libqos-virtio-obj-y)
-tests/tpci200-test$(EXESUF): tests/tpci200-test.o
+#tests/tpci200-test$(EXESUF): tests/tpci200-test.o
tests/display-vga-test$(EXESUF): tests/display-vga-test.o
-tests/ipoctal232-test$(EXESUF): tests/ipoctal232-test.o
+#tests/ipoctal232-test$(EXESUF): tests/ipoctal232-test.o
tests/qom-test$(EXESUF): tests/qom-test.o
tests/test-hmp$(EXESUF): tests/test-hmp.o
tests/machine-none-test$(EXESUF): tests/machine-none-test.o
tests/drive_del-test$(EXESUF): tests/drive_del-test.o $(libqos-virtio-obj-y)
tests/qdev-monitor-test$(EXESUF): tests/qdev-monitor-test.o $(libqos-pc-obj-y)
-tests/nvme-test$(EXESUF): tests/nvme-test.o
+#tests/nvme-test$(EXESUF): tests/nvme-test.o
tests/pvpanic-test$(EXESUF): tests/pvpanic-test.o
tests/i82801b11-test$(EXESUF): tests/i82801b11-test.o
tests/ac97-test$(EXESUF): tests/ac97-test.o
-tests/es1370-test$(EXESUF): tests/es1370-test.o
+#tests/es1370-test$(EXESUF): tests/es1370-test.o
tests/intel-hda-test$(EXESUF): tests/intel-hda-test.o
tests/ioh3420-test$(EXESUF): tests/ioh3420-test.o
-tests/usb-hcd-ohci-test$(EXESUF): tests/usb-hcd-ohci-test.o $(libqos-usb-obj-y)
+#tests/usb-hcd-ohci-test$(EXESUF): tests/usb-hcd-ohci-test.o $(libqos-usb-obj-y)
tests/usb-hcd-uhci-test$(EXESUF): tests/usb-hcd-uhci-test.o $(libqos-usb-obj-y)
tests/usb-hcd-ehci-test$(EXESUF): tests/usb-hcd-ehci-test.o $(libqos-usb-obj-y)
tests/usb-hcd-xhci-test$(EXESUF): tests/usb-hcd-xhci-test.o $(libqos-usb-obj-y)
@@ -841,19 +842,19 @@ tests/qemu-iotests/socket_scm_helper$(EXESUF): tests/qemu-iotests/socket_scm_hel
tests/test-qemu-opts$(EXESUF): tests/test-qemu-opts.o $(test-util-obj-y)
tests/test-keyval$(EXESUF): tests/test-keyval.o $(test-util-obj-y) $(test-qapi-obj-y)
tests/test-write-threshold$(EXESUF): tests/test-write-threshold.o $(test-block-obj-y)
-tests/test-netfilter$(EXESUF): tests/test-netfilter.o $(qtest-obj-y)
-tests/test-filter-mirror$(EXESUF): tests/test-filter-mirror.o $(qtest-obj-y)
-tests/test-filter-redirector$(EXESUF): tests/test-filter-redirector.o $(qtest-obj-y)
+#tests/test-netfilter$(EXESUF): tests/test-netfilter.o $(qtest-obj-y)
+#tests/test-filter-mirror$(EXESUF): tests/test-filter-mirror.o $(qtest-obj-y)
+#tests/test-filter-redirector$(EXESUF): tests/test-filter-redirector.o $(qtest-obj-y)
tests/test-x86-cpuid-compat$(EXESUF): tests/test-x86-cpuid-compat.o $(qtest-obj-y)
tests/ivshmem-test$(EXESUF): tests/ivshmem-test.o contrib/ivshmem-server/ivshmem-server.o $(libqos-pc-obj-y) $(libqos-spapr-obj-y)
-tests/megasas-test$(EXESUF): tests/megasas-test.o $(libqos-spapr-obj-y) $(libqos-pc-obj-y)
+#tests/megasas-test$(EXESUF): tests/megasas-test.o $(libqos-spapr-obj-y) $(libqos-pc-obj-y)
tests/vhost-user-bridge$(EXESUF): tests/vhost-user-bridge.o $(test-util-obj-y) libvhost-user.a
tests/test-uuid$(EXESUF): tests/test-uuid.o $(test-util-obj-y)
tests/test-arm-mptimer$(EXESUF): tests/test-arm-mptimer.o
tests/test-qapi-util$(EXESUF): tests/test-qapi-util.o $(test-util-obj-y)
tests/numa-test$(EXESUF): tests/numa-test.o
tests/vmgenid-test$(EXESUF): tests/vmgenid-test.o tests/boot-sector.o tests/acpi-utils.o
-tests/sdhci-test$(EXESUF): tests/sdhci-test.o $(libqos-pc-obj-y)
+#tests/sdhci-test$(EXESUF): tests/sdhci-test.o $(libqos-pc-obj-y)
tests/cdrom-test$(EXESUF): tests/cdrom-test.o tests/boot-sector.o $(libqos-obj-y)
tests/migration/stress$(EXESUF): tests/migration/stress.o
diff --git a/tests/boot-serial-test.c b/tests/boot-serial-test.c
index 952a2e7..5217a39 100644
--- a/tests/boot-serial-test.c
+++ b/tests/boot-serial-test.c
@@ -80,17 +80,21 @@ static testdef_t tests[] = {
{ "ppc", "g3beige", "", "PowerPC,750" },
{ "ppc", "mac99", "", "PowerPC,G4" },
{ "ppc", "sam460ex", "-m 256", "DRAM: 256 MiB" },
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ "ppc64", "ppce500", "", "U-Boot" },
{ "ppc64", "prep", "-boot e", "Booting from device e" },
{ "ppc64", "40p", "-m 192", "Memory size: 192 MB" },
{ "ppc64", "mac99", "", "PowerPC,970FX" },
+#endif
{ "ppc64", "pseries", "", "Open Firmware" },
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ "ppc64", "powernv", "-cpu POWER8", "OPAL" },
{ "ppc64", "sam460ex", "-device e1000", "8086 100e" },
+#endif
{ "i386", "isapc", "-cpu qemu32 -device sga", "SGABIOS" },
{ "i386", "pc", "-device sga", "SGABIOS" },
{ "i386", "q35", "-device sga", "SGABIOS" },
- { "x86_64", "isapc", "-cpu qemu32 -device sga", "SGABIOS" },
+ { "x86_64", "pc", "-cpu qemu32 -device sga", "SGABIOS" },
{ "x86_64", "q35", "-device sga", "SGABIOS" },
{ "sparc", "LX", "", "TMS390S10" },
{ "sparc", "SS-4", "", "MB86904" },
diff --git a/tests/cpu-plug-test.c b/tests/cpu-plug-test.c
index 5f39ba0..48b8d09 100644
--- a/tests/cpu-plug-test.c
+++ b/tests/cpu-plug-test.c
@@ -192,7 +192,8 @@ static void add_pseries_test_case(const char *mname)
PlugTestData *data;
if (!g_str_has_prefix(mname, "pseries-") ||
- (g_str_has_prefix(mname, "pseries-2.") && atoi(&mname[10]) < 7)) {
+ (g_str_has_prefix(mname, "pseries-2.") && atoi(&mname[10]) < 7) ||
+ strcmp(mname,"pseries-rhel7.2.0") == 0) {
return;
}
data = g_new(PlugTestData, 1);
diff --git a/tests/e1000-test.c b/tests/e1000-test.c
index 0c5fcdc..b830432 100644
--- a/tests/e1000-test.c
+++ b/tests/e1000-test.c
@@ -29,8 +29,10 @@ static void test_device(gconstpointer data)
static const char *models[] = {
"e1000",
"e1000-82540em",
+#if 0 /* Disabled for Red Hat Enterprise Linux */
"e1000-82544gc",
"e1000-82545em",
+#endif
};
int main(int argc, char **argv)
diff --git a/tests/endianness-test.c b/tests/endianness-test.c
index 546e096..440353d 100644
--- a/tests/endianness-test.c
+++ b/tests/endianness-test.c
@@ -37,10 +37,12 @@ static const TestCase test_cases[] = {
{ "ppc", "g3beige", 0xfe000000, .bswap = true, .superio = "i82378" },
{ "ppc", "prep", 0x80000000, .bswap = true },
{ "ppc", "bamboo", 0xe8000000, .bswap = true, .superio = "i82378" },
+#if 0 /* Disabled for RHEL, since ISA is not enabled */
{ "ppc64", "mac99", 0xf2000000, .bswap = true, .superio = "i82378" },
{ "ppc64", "pseries", (1ULL << 45), .bswap = true, .superio = "i82378" },
{ "ppc64", "pseries-2.7", 0x10080000000ULL,
.bswap = true, .superio = "i82378" },
+#endif /* Disabled for RHEL, since ISA is not enabled */
{ "sh4", "r2d", 0xfe240000, .superio = "i82378" },
{ "sh4eb", "r2d", 0xfe240000, .bswap = true, .superio = "i82378" },
{ "sparc64", "sun4u", 0x1fe02000000LL, .bswap = true },
diff --git a/tests/prom-env-test.c b/tests/prom-env-test.c
index 8c867e6..cc9b6ec 100644
--- a/tests/prom-env-test.c
+++ b/tests/prom-env-test.c
@@ -82,7 +82,9 @@ int main(int argc, char *argv[])
if (!strcmp(arch, "ppc")) {
add_tests(ppc_machines);
} else if (!strcmp(arch, "ppc64")) {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
add_tests(ppc_machines);
+#endif
if (g_test_slow()) {
qtest_add_data_func("prom-env/pseries", "pseries", test_machine);
}
diff --git a/tests/qemu-iotests/051 b/tests/qemu-iotests/051
index ee9c820..c5cc0ee 100755
--- a/tests/qemu-iotests/051
+++ b/tests/qemu-iotests/051
@@ -183,11 +183,11 @@ run_qemu -drive if=virtio
case "$QEMU_DEFAULT_MACHINE" in
pc)
run_qemu -drive if=none,id=disk -device ide-cd,drive=disk
- run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-cd,drive=disk
+# run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-cd,drive=disk
run_qemu -drive if=none,id=disk -device ide-drive,drive=disk
run_qemu -drive if=none,id=disk -device ide-hd,drive=disk
- run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-disk,drive=disk
- run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-hd,drive=disk
+# run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-disk,drive=disk
+# run_qemu -drive if=none,id=disk -device lsi53c895a -device scsi-hd,drive=disk
;;
*)
;;
@@ -212,11 +212,11 @@ run_qemu -drive file="$TEST_IMG",if=virtio,readonly=on
case "$QEMU_DEFAULT_MACHINE" in
pc)
run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device ide-cd,drive=disk
- run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-cd,drive=disk
+# run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-cd,drive=disk
run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device ide-drive,drive=disk
run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device ide-hd,drive=disk
- run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-disk,drive=disk
- run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-hd,drive=disk
+# run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-disk,drive=disk
+# run_qemu -drive file="$TEST_IMG",if=none,id=disk,readonly=on -device lsi53c895a -device scsi-hd,drive=disk
;;
*)
;;
diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group
index b973dc8..f1059f6 100644
--- a/tests/qemu-iotests/group
+++ b/tests/qemu-iotests/group
@@ -77,7 +77,7 @@
068 rw auto quick
069 rw auto quick
070 rw auto quick
-071 rw auto quick
+# 071 rw auto quick -- requires whitelisted blkverify
072 rw auto quick
073 rw auto quick
074 rw auto quick
@@ -105,7 +105,7 @@
096 rw auto quick
097 rw auto backing
098 rw auto backing quick
-099 rw auto quick
+# 099 rw auto quick -- requires whitelisted blkverify
# 100 was removed, do not reuse
101 rw auto quick
102 rw auto quick
diff --git a/tests/qom-test.c b/tests/qom-test.c
index e6f712c..ebd15fd 100644
--- a/tests/qom-test.c
+++ b/tests/qom-test.c
@@ -16,7 +16,7 @@
#include "libqtest.h"
static const char *blacklist_x86[] = {
- "xenfv", "xenpv", NULL
+ "xenfv", "xenpv", "isapc", NULL
};
static const struct {
diff --git a/tests/test-x86-cpuid-compat.c b/tests/test-x86-cpuid-compat.c
index 84ce9c7..c1ee197 100644
--- a/tests/test-x86-cpuid-compat.c
+++ b/tests/test-x86-cpuid-compat.c
@@ -306,6 +306,7 @@ int main(int argc, char **argv)
"-cpu 486,xlevel2=0xC0000002,+xstore",
"xlevel2", 0xC0000002);
+#if 0 /* Disabled in Red Hat Enterprise Linux */
/* Check compatibility of old machine-types that didn't
* auto-increase level/xlevel/xlevel2: */
@@ -356,6 +357,7 @@ int main(int argc, char **argv)
add_cpuid_test("x86/cpuid/xlevel-compat/pc-i440fx-2.4/npt-on",
"-machine pc-i440fx-2.4 -cpu SandyBridge,+npt",
"xlevel", 0x80000008);
+#endif
/* Test feature parsing */
add_feature_test("x86/cpuid/features/plus",
diff --git a/tests/usb-hcd-xhci-test.c b/tests/usb-hcd-xhci-test.c
index 5b1b681..85fa150 100644
--- a/tests/usb-hcd-xhci-test.c
+++ b/tests/usb-hcd-xhci-test.c
@@ -21,6 +21,7 @@ static void test_xhci_hotplug(void)
usb_test_hotplug("xhci", 1, NULL);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void test_usb_uas_hotplug(void)
{
qtest_qmp_device_add("usb-uas", "uas", NULL);
@@ -34,6 +35,7 @@ static void test_usb_uas_hotplug(void)
qtest_qmp_device_del("scsihd");
qtest_qmp_device_del("uas");
}
+#endif
static void test_usb_ccid_hotplug(void)
{
@@ -52,7 +54,9 @@ int main(int argc, char **argv)
qtest_add_func("/xhci/pci/init", test_xhci_init);
qtest_add_func("/xhci/pci/hotplug", test_xhci_hotplug);
+#if 0 /* Disabled for Red Hat Enterprise Linux */
qtest_add_func("/xhci/pci/hotplug/usb-uas", test_usb_uas_hotplug);
+#endif
qtest_add_func("/xhci/pci/hotplug/usb-ccid", test_usb_ccid_hotplug);
qtest_start("-device nec-usb-xhci,id=xhci"
--
1.8.3.1

2
0004-Use-kvm-by-default.patch → 0012-Use-kvm-by-default.patch
View File

@ -1,4 +1,4 @@
From 5a441b820faa4e6e9e6fc80cccc813a3c333b6c2 Mon Sep 17 00:00:00 2001
From ce4cd21e28e1511e056877e3cc8dcf6f0b8c7baa Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 18 Dec 2014 06:27:49 +0100
Subject: Use kvm by default

2
0005-vfio-cap-number-of-devices-that-can-be-assigned.patch → 0013-vfio-cap-number-of-devices-that-can-be-assigned.patch
View File

@ -1,4 +1,4 @@
From 0c57186334ab4ef7f04de604a8f13b39ad6578c8 Mon Sep 17 00:00:00 2001
From 43a09e06e76cba94c6ecd448f51912362b42f94d Mon Sep 17 00:00:00 2001
From: Bandan Das <bsd@redhat.com>
Date: Tue, 3 Dec 2013 20:05:13 +0100
Subject: vfio: cap number of devices that can be assigned

2
0006-Add-support-statement-to-help-output.patch → 0014-Add-support-statement-to-help-output.patch
View File

@ -1,4 +1,4 @@
From c2858d09461c6f69553e8b9d69804f243c2d08bb Mon Sep 17 00:00:00 2001
From f8e7911bb97eb942a4eadad1731b7c59c43fd2eb Mon Sep 17 00:00:00 2001
From: Eduardo Habkost <ehabkost@redhat.com>
Date: Wed, 4 Dec 2013 18:53:17 +0100
Subject: Add support statement to -help output

2
0007-globally-limit-the-maximum-number-of-CPUs.patch → 0015-globally-limit-the-maximum-number-of-CPUs.patch
View File

@ -1,4 +1,4 @@
From 36dda20ae7312b1db0b4060bb2420ab18e5f5483 Mon Sep 17 00:00:00 2001
From 8413778453742aeb3ad6b38d5f4440a0dbabca7d Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 21 Jan 2014 10:46:52 +0100
Subject: globally limit the maximum number of CPUs

2
0008-Add-support-for-simpletrace.patch → 0016-Add-support-for-simpletrace.patch
View File

@ -1,4 +1,4 @@
From 84763026a2e71d7b9f7fc9249ba25771724c272d Mon Sep 17 00:00:00 2001
From f262acdee88f36b625fcbd5eb1cd66739428cca3 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 8 Oct 2015 09:50:17 +0200
Subject: Add support for simpletrace

2
0009-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch → 0017-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch
View File

@ -1,4 +1,4 @@
From 7f5450ae0077f13427a54bd2868c1986284839d2 Mon Sep 17 00:00:00 2001
From 33e2c01c1b0b64a76d5193b60378d2329a86626b Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 14 Nov 2014 08:51:50 +0100
Subject: Use qemu-kvm in documentation instead of qemu-system-<arch>

2
0010-usb-xhci-Fix-PCI-capability-order.patch → 0018-usb-xhci-Fix-PCI-capability-order.patch
View File

@ -1,4 +1,4 @@
From 268966c530da2d8e07e2c9034a82acd01335e2c2 Mon Sep 17 00:00:00 2001
From 69912b533a88bda6377292231fb94475a674a90d Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Date: Fri, 5 May 2017 19:06:14 +0200
Subject: usb-xhci: Fix PCI capability order

2
0011-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch → 0019-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch
View File

@ -1,4 +1,4 @@
From 126cb3f3717b266f27dc7c657da833779f9f3b54 Mon Sep 17 00:00:00 2001
From a883dbcc1c55cab189ff4a48cbdd12c4b4246b9c Mon Sep 17 00:00:00 2001
From: Fam Zheng <famz@redhat.com>
Date: Wed, 14 Jun 2017 15:37:01 +0200
Subject: virtio-scsi: Reject scsi-cd if data plane enabled [RHEL only]

2
0012-linux-headers-asm-s390-kvm.h-header-sync.patch → 0020-linux-headers-asm-s390-kvm.h-header-sync.patch
View File

@ -1,4 +1,4 @@
From 811173cac3e80b6235de885b7b2ec4f9be3b4e31 Mon Sep 17 00:00:00 2001
From f3d0b355f946ab87b281ef75ebfb52f7b7592f2a Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 9 Aug 2018 10:15:08 +0000
Subject: linux-headers: asm-s390/kvm.h header sync

2
0013-s390x-Enable-KVM-huge-page-backing-support.patch → 0021-s390x-Enable-KVM-huge-page-backing-support.patch
View File

@ -1,4 +1,4 @@
From fa8eda01f21298e6bc50abb78775390b4bf3f954 Mon Sep 17 00:00:00 2001
From 3b4526245dcb2daad3a6393b6b129f85f9e2c7a2 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 6 Aug 2018 14:18:41 +0100
Subject: s390x: Enable KVM huge page backing support

2
0014-s390x-kvm-add-etoken-facility.patch → 0022-s390x-kvm-add-etoken-facility.patch
View File

@ -1,4 +1,4 @@
From 4b36866031e559bc895e64ecb20417323cb03e3d Mon Sep 17 00:00:00 2001
From 8eacbf0e8e26b2a8aa3de955a57a7a3cb680d922 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 9 Aug 2018 10:15:09 +0000
Subject: s390x/kvm: add etoken facility

2
0015-s390x-cpumodel-default-enable-bpb-and-ppa15-for-z196.patch → 0023-s390x-cpumodel-default-enable-bpb-and-ppa15-for-z196.patch
View File

@ -1,4 +1,4 @@
From 79d0599b21b64f8a8107855e844b347d2cc138d9 Mon Sep 17 00:00:00 2001
From 29df663d045345a8c498dc3966cc59dcf091a50d Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cohuck@redhat.com>
Date: Tue, 7 Aug 2018 09:05:54 +0000
Subject: s390x/cpumodel: default enable bpb and ppa15 for z196 and later

2
0016-i386-Fix-arch_query_cpu_model_expansion-leak.patch → 0024-i386-Fix-arch_query_cpu_model_expansion-leak.patch
View File

@ -1,4 +1,4 @@
From 786fb991b644eddb9f52fd04d377cc7a62685d59 Mon Sep 17 00:00:00 2001
From 43b08a1e4bc47d810212f569cc0fc30eebfd7036 Mon Sep 17 00:00:00 2001
From: Markus Armbruster <armbru@redhat.com>
Date: Fri, 31 Aug 2018 13:59:22 +0100
Subject: i386: Fix arch_query_cpu_model_expansion() leak

2
0017-i386-Disable-TOPOEXT-by-default-on-cpu-host.patch → 0025-i386-Disable-TOPOEXT-by-default-on-cpu-host.patch
View File

@ -1,4 +1,4 @@
From 25abf99ebc7004999e79fa5e5b1370e4dfdaeed2 Mon Sep 17 00:00:00 2001
From 628b10cd4d5cd8fde97dab66f143db78fe03398a Mon Sep 17 00:00:00 2001
From: Eduardo Habkost <ehabkost@redhat.com>
Date: Tue, 21 Aug 2018 19:15:41 +0100
Subject: i386: Disable TOPOEXT by default on "-cpu host"

2
0018-curl-Make-sslverify-off-disable-host-as-well-as-peer.patch → 0026-curl-Make-sslverify-off-disable-host-as-well-as-peer.patch
View File

@ -1,4 +1,4 @@
From 49d4861ffc56cb233dacc1abcb2a5ec608e599ab Mon Sep 17 00:00:00 2001
From 1ed2bb0d831983b68bcdecd057c2c5bfd419c304 Mon Sep 17 00:00:00 2001
From: Jeffrey Cody <jcody@redhat.com>
Date: Wed, 26 Sep 2018 04:08:14 +0100
Subject: curl: Make sslverify=off disable host as well as peer verification.

2
0019-migration-postcopy-Clear-have_listen_thread.patch → 0027-migration-postcopy-Clear-have_listen_thread.patch
View File

@ -1,4 +1,4 @@
From 324493e716a2e5fa60b6b013d5df831b03f2a678 Mon Sep 17 00:00:00 2001
From 096b7abf1d2755ad469e4bcb3dc6302021979814 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Date: Mon, 1 Oct 2018 10:54:48 +0100
Subject: migration/postcopy: Clear have_listen_thread

2
0020-migration-cleanup-in-error-paths-in-loadvm.patch → 0028-migration-cleanup-in-error-paths-in-loadvm.patch
View File

@ -1,4 +1,4 @@
From 005c4cb023ffdcb8888c7453d263cab95d5b1b1c Mon Sep 17 00:00:00 2001
From bff052b89b0c32c179d858bd8eed91e0d9f98db4 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Date: Mon, 1 Oct 2018 10:54:49 +0100
Subject: migration: cleanup in error paths in loadvm

2
0021-jobs-change-start-callback-to-run-callback.patch → 0029-jobs-change-start-callback-to-run-callback.patch
View File

@ -1,4 +1,4 @@
From 287cb50c08d64773470732be8a6a566bcdde4b75 Mon Sep 17 00:00:00 2001
From 2999207ffd4de9f139922b444edba07b051d4a67 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:07 +0100
Subject: jobs: change start callback to run callback

2
0022-jobs-canonize-Error-object.patch → 0030-jobs-canonize-Error-object.patch
View File

@ -1,4 +1,4 @@
From 9dff1ec5bdde5e8bd8745d2e0697cc6e28c87214 Mon Sep 17 00:00:00 2001
From df9702d737eea1720a10d350c24bdcc3f54bcba9 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Wed, 29 Aug 2018 21:57:27 -0400
Subject: jobs: canonize Error object

2
0023-jobs-add-exit-shim.patch → 0031-jobs-add-exit-shim.patch
View File

@ -1,4 +1,4 @@
From 29ae3509885eaa6d24ee82aa4cae47ddeda086db Mon Sep 17 00:00:00 2001
From 17511eb281e005da6e617acd12c81a0a1fa1771d Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:09 +0100
Subject: jobs: add exit shim

2
0024-block-commit-utilize-job_exit-shim.patch → 0032-block-commit-utilize-job_exit-shim.patch
View File

@ -1,4 +1,4 @@
From 2207ab7e71d5d3c3806d60b3f483988a62566292 Mon Sep 17 00:00:00 2001
From 912e8eaa87f8dab40466cf0d45c3290d02e6a9d5 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:10 +0100
Subject: block/commit: utilize job_exit shim

2
0025-block-mirror-utilize-job_exit-shim.patch → 0033-block-mirror-utilize-job_exit-shim.patch
View File

@ -1,4 +1,4 @@
From f96869810df10ac28030a31d8cb1e39825133e94 Mon Sep 17 00:00:00 2001
From 2322917770da98e175e7ae8bf0bb1a624ec3cebc Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Wed, 29 Aug 2018 21:57:30 -0400
Subject: block/mirror: utilize job_exit shim

2
0026-jobs-utilize-job_exit-shim.patch → 0034-jobs-utilize-job_exit-shim.patch
View File

@ -1,4 +1,4 @@
From 5947e8781d9dffb069fcc570402f775f80068e63 Mon Sep 17 00:00:00 2001
From 83d2840eeadd8a55b796eae5454783d42913963c Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:12 +0100
Subject: jobs: utilize job_exit shim

2
0027-block-backup-make-function-variables-consistently-na.patch → 0035-block-backup-make-function-variables-consistently-na.patch
View File

@ -1,4 +1,4 @@
From 3e86b802541a7230eda88a6bd7f17b411deab9fa Mon Sep 17 00:00:00 2001
From b5532575bb8aa748dc066834d7ac150bbb6575a7 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:13 +0100
Subject: block/backup: make function variables consistently named

2
0028-jobs-remove-ret-argument-to-job_completed-privatize-.patch → 0036-jobs-remove-ret-argument-to-job_completed-privatize-.patch
View File

@ -1,4 +1,4 @@
From 3141614c15fbcf6aee7af19069380aa6d186656b Mon Sep 17 00:00:00 2001
From 7fe6d53387852907871d82997fbccc2cf774bdb4 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:14 +0100
Subject: jobs: remove ret argument to job_completed; privatize it

2
0029-jobs-remove-job_defer_to_main_loop.patch → 0037-jobs-remove-job_defer_to_main_loop.patch
View File

@ -1,4 +1,4 @@
From 73694b41a7e96fb364bdfd6fbad89c69dc2d1f73 Mon Sep 17 00:00:00 2001
From 1827993a08cc8c86cc40ca9ccb7ef668261b2bc4 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:15 +0100
Subject: jobs: remove job_defer_to_main_loop

2
0030-block-commit-add-block-job-creation-flags.patch → 0038-block-commit-add-block-job-creation-flags.patch
View File

@ -1,4 +1,4 @@
From 8141d5f8ab70551c59fae63373a9562c99c8e00d Mon Sep 17 00:00:00 2001
From 6c8da2ba018d7546a15c3917f52ad1cc2b5b133c Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:16 +0100
Subject: block/commit: add block job creation flags

2
0031-block-mirror-add-block-job-creation-flags.patch → 0039-block-mirror-add-block-job-creation-flags.patch
View File

@ -1,4 +1,4 @@
From 8ac0fb4e4202e6321d57f1be01f4ca6e51a98687 Mon Sep 17 00:00:00 2001
From d4f6cfe194df3236bf53b1093e0a7f98f0a5da0e Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:17 +0100
Subject: block/mirror: add block job creation flags

2
0032-block-stream-add-block-job-creation-flags.patch → 0040-block-stream-add-block-job-creation-flags.patch
View File

@ -1,4 +1,4 @@
From 64569465b360642820193586116aa51ed0b356bd Mon Sep 17 00:00:00 2001
From 4fd98648eb0df8157c1238a1cee36373278d44a5 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:18 +0100
Subject: block/stream: add block job creation flags

2
0033-block-commit-refactor-commit-to-use-job-callbacks.patch → 0041-block-commit-refactor-commit-to-use-job-callbacks.patch
View File

@ -1,4 +1,4 @@
From b0ac95edde586e808a1118c4b04c1608de8b5b6c Mon Sep 17 00:00:00 2001
From b0b7d48f97dd97efacf93e5529d7597bd2280095 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:19 +0100
Subject: block/commit: refactor commit to use job callbacks

2
0034-block-mirror-don-t-install-backing-chain-on-abort.patch → 0042-block-mirror-don-t-install-backing-chain-on-abort.patch
View File

@ -1,4 +1,4 @@
From 7f155f96e9db0be97501f90e482a29d51779f887 Mon Sep 17 00:00:00 2001
From e849bf276e59b282f3288b42abe9d6dff51dc678 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:20 +0100
Subject: block/mirror: don't install backing chain on abort

2
0035-block-mirror-conservative-mirror_exit-refactor.patch → 0043-block-mirror-conservative-mirror_exit-refactor.patch
View File

@ -1,4 +1,4 @@
From 8b394ff523e607060c80c6b647dbb89a2f73571d Mon Sep 17 00:00:00 2001
From 430c298d6bf9a7c8b90ad30bc2cd445e5cd6dd50 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Thu, 6 Sep 2018 09:02:15 -0400
Subject: block/mirror: conservative mirror_exit refactor

2
0036-block-stream-refactor-stream-to-use-job-callbacks.patch → 0044-block-stream-refactor-stream-to-use-job-callbacks.patch
View File

@ -1,4 +1,4 @@
From 533c77ee076c0050b4c4deb26fda54c085a994ce Mon Sep 17 00:00:00 2001
From 57ede8577bbecac73a2945ca5278662dfc019dca Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:22 +0100
Subject: block/stream: refactor stream to use job callbacks

2
0037-tests-blockjob-replace-Blockjob-with-Job.patch → 0045-tests-blockjob-replace-Blockjob-with-Job.patch
View File

@ -1,4 +1,4 @@
From ac945e63cca25c453d472834c64aa3a4192729f9 Mon Sep 17 00:00:00 2001
From 3817b0c67fb4636bacd9c4ebdef39f51b18e05c1 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:23 +0100
Subject: tests/blockjob: replace Blockjob with Job

2
0038-tests-test-blockjob-remove-exit-callback.patch → 0046-tests-test-blockjob-remove-exit-callback.patch
View File

@ -1,4 +1,4 @@
From 62fd56870fb6296f795c9fc7f5965d83a72dabac Mon Sep 17 00:00:00 2001
From f641d3f6946af31724c578aa6f09ba883bb5fab3 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:24 +0100
Subject: tests/test-blockjob: remove exit callback

2
0039-tests-test-blockjob-txn-move-.exit-to-.clean.patch → 0047-tests-test-blockjob-txn-move-.exit-to-.clean.patch
View File

@ -1,4 +1,4 @@
From 6247c4b10e3fb6c677947a503ddad961cb71faff Mon Sep 17 00:00:00 2001
From 43b1e07411d06cd676f3f55e14e0ac1082a679d0 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:25 +0100
Subject: tests/test-blockjob-txn: move .exit to .clean

2
0040-jobs-remove-.exit-callback.patch → 0048-jobs-remove-.exit-callback.patch
View File

@ -1,4 +1,4 @@
From c2c10f4fac6757d292f8b3d9ac7723a718e596aa Mon Sep 17 00:00:00 2001
From ea31341d12bc2080f7a1b606dcf578376d6a4637 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:26 +0100
Subject: jobs: remove .exit callback

2
0041-qapi-block-commit-expose-new-job-properties.patch → 0049-qapi-block-commit-expose-new-job-properties.patch
View File

@ -1,4 +1,4 @@
From ce81bd3fa7316bcdee5e121e6ea71c7b2e1e81e1 Mon Sep 17 00:00:00 2001
From 756c3ccf83d5612ca2b326a8fed8fdf1f7958adb Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:27 +0100
Subject: qapi/block-commit: expose new job properties

2
0042-qapi-block-mirror-expose-new-job-properties.patch → 0050-qapi-block-mirror-expose-new-job-properties.patch
View File

@ -1,4 +1,4 @@
From 318445193efc33c06e63e021a988814d49658a0f Mon Sep 17 00:00:00 2001
From 254a2b41a647cf39abaa5d94f17aef62f035d30f Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Thu, 6 Sep 2018 09:02:22 -0400
Subject: qapi/block-mirror: expose new job properties

2
0043-qapi-block-stream-expose-new-job-properties.patch → 0051-qapi-block-stream-expose-new-job-properties.patch
View File

@ -1,4 +1,4 @@
From 67fa4ccaffcd7e2698d30597f51093903aef4a5d Mon Sep 17 00:00:00 2001
From 50990953696a8803f6b2b7ad71901c58c375eb8c Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:29 +0100
Subject: qapi/block-stream: expose new job properties

2
0044-block-backup-qapi-documentation-fixup.patch → 0052-block-backup-qapi-documentation-fixup.patch
View File

@ -1,4 +1,4 @@
From c104ce571b585040ca4d0c77419d2ca06c2087b8 Mon Sep 17 00:00:00 2001
From 6ecfc87059e78892c868227319a91adea909e09e Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:30 +0100
Subject: block/backup: qapi documentation fixup

2
0045-blockdev-document-transactional-shortcomings.patch → 0053-blockdev-document-transactional-shortcomings.patch
View File

@ -1,4 +1,4 @@
From 53dc1dce0b91a7ebb1c32d10a7482461c01326d6 Mon Sep 17 00:00:00 2001
From 00a437d87c6bd8ec956b25fc0dffe8397ce475b8 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 25 Sep 2018 22:34:31 +0100
Subject: blockdev: document transactional shortcomings

67
0054-seccomp-use-SIGSYS-signal-instead-of-killing-the-thr.patch Normal file
View File

@ -0,0 +1,67 @@
From 5b9ccef27363b61223b31312062cde1210216985 Mon Sep 17 00:00:00 2001
From: Eduardo Otubo <otubo@redhat.com>
Date: Fri, 28 Sep 2018 07:56:36 +0100
Subject: seccomp: use SIGSYS signal instead of killing the thread
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eduardo Otubo <otubo@redhat.com>
Message-id: <20180928075639.16746-3-otubo@redhat.com>
Patchwork-id: 82314
O-Subject: [RHEL-8 qemu-kvm PATCH 2/5] seccomp: use SIGSYS signal instead of killing the thread
Bugzilla: 1618356
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Marc-André Lureau <marcandre.lureau@redhat.com>
commit 6f2231e9b0931e1998d9ed0c509adf7aedc02db2
Author: Marc-André Lureau <marcandre.lureau@redhat.com>
Date: Wed Aug 22 19:02:47 2018 +0200
seccomp: use SIGSYS signal instead of killing the thread
The seccomp action SCMP_ACT_KILL results in immediate termination of
the thread that made the bad system call. However, qemu being
multi-threaded, it keeps running. There is no easy way for parent
process / management layer (libvirt) to know about that situation.
Instead, the default SIGSYS handler when invoked with SCMP_ACT_TRAP
will terminate the program and core dump.
This may not be the most secure solution, but probably better than
just killing the offending thread. SCMP_ACT_KILL_PROCESS has been
added in Linux 4.14 to improve the situation, which I propose to use
by default if available in the next patch.
Related to:
https://bugzilla.redhat.com/show_bug.cgi?id=1594456
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Acked-by: Eduardo Otubo <otubo@redhat.com>
Signed-off-by: Eduardo Otubo <otubo@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
qemu-seccomp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/qemu-seccomp.c b/qemu-seccomp.c
index 9cd8eb9..b117a92 100644
--- a/qemu-seccomp.c
+++ b/qemu-seccomp.c
@@ -125,7 +125,7 @@ static int seccomp_start(uint32_t seccomp_opts)
continue;
}
- rc = seccomp_rule_add_array(ctx, SCMP_ACT_KILL, blacklist[i].num,
+ rc = seccomp_rule_add_array(ctx, SCMP_ACT_TRAP, blacklist[i].num,
blacklist[i].narg, blacklist[i].arg_cmp);
if (rc < 0) {
goto seccomp_return;
--
1.8.3.1

110
0055-seccomp-prefer-SCMP_ACT_KILL_PROCESS-if-available.patch Normal file
View File

@ -0,0 +1,110 @@
From 80574fd1c226ca5c8555b3bb37bc3fe121bbf69f Mon Sep 17 00:00:00 2001
From: Eduardo Otubo <otubo@redhat.com>
Date: Fri, 28 Sep 2018 07:56:37 +0100
Subject: seccomp: prefer SCMP_ACT_KILL_PROCESS if available
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eduardo Otubo <otubo@redhat.com>
Message-id: <20180928075639.16746-4-otubo@redhat.com>
Patchwork-id: 82315
O-Subject: [RHEL-8 qemu-kvm PATCH 3/5] seccomp: prefer SCMP_ACT_KILL_PROCESS if available
Bugzilla: 1618356
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Marc-André Lureau <marcandre.lureau@redhat.com>
commit bda08a5764d470f101fa38635d30b41179a313e1
Author: Marc-André Lureau <marcandre.lureau@redhat.com>
Date: Wed Aug 22 19:02:48 2018 +0200
seccomp: prefer SCMP_ACT_KILL_PROCESS if available
The upcoming libseccomp release should have SCMP_ACT_KILL_PROCESS
action (https://github.com/seccomp/libseccomp/issues/96).
SCMP_ACT_KILL_PROCESS is preferable to immediately terminate the
offending process, rather than having the SIGSYS handler running.
Use SECCOMP_GET_ACTION_AVAIL to check availability of kernel support,
as libseccomp will fallback on SCMP_ACT_KILL otherwise, and we still
prefer SCMP_ACT_TRAP.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Acked-by: Eduardo Otubo <otubo@redhat.com>
Signed-off-by: Eduardo Otubo <otubo@rehdat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
qemu-seccomp.c | 31 ++++++++++++++++++++++++++++++-
1 file changed, 30 insertions(+), 1 deletion(-)
diff --git a/qemu-seccomp.c b/qemu-seccomp.c
index b117a92..f0c833f 100644
--- a/qemu-seccomp.c
+++ b/qemu-seccomp.c
@@ -20,6 +20,7 @@
#include <sys/prctl.h>
#include <seccomp.h>
#include "sysemu/seccomp.h"
+#include <linux/seccomp.h>
/* For some architectures (notably ARM) cacheflush is not supported until
* libseccomp 2.2.3, but configure enforces that we are using a more recent
@@ -107,12 +108,40 @@ static const struct QemuSeccompSyscall blacklist[] = {
{ SCMP_SYS(sched_get_priority_min), QEMU_SECCOMP_SET_RESOURCECTL },
};
+static inline __attribute__((unused)) int
+qemu_seccomp(unsigned int operation, unsigned int flags, void *args)
+{
+#ifdef __NR_seccomp
+ return syscall(__NR_seccomp, operation, flags, args);
+#else
+ errno = ENOSYS;
+ return -1;
+#endif
+}
+
+static uint32_t qemu_seccomp_get_kill_action(void)
+{
+#if defined(SECCOMP_GET_ACTION_AVAIL) && defined(SCMP_ACT_KILL_PROCESS) && \
+ defined(SECCOMP_RET_KILL_PROCESS)
+ {
+ uint32_t action = SECCOMP_RET_KILL_PROCESS;
+
+ if (qemu_seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &action) == 0) {
+ return SCMP_ACT_KILL_PROCESS;
+ }
+ }
+#endif
+
+ return SCMP_ACT_TRAP;
+}
+
static int seccomp_start(uint32_t seccomp_opts)
{
int rc = 0;
unsigned int i = 0;
scmp_filter_ctx ctx;
+ uint32_t action = qemu_seccomp_get_kill_action();
ctx = seccomp_init(SCMP_ACT_ALLOW);
if (ctx == NULL) {
@@ -125,7 +154,7 @@ static int seccomp_start(uint32_t seccomp_opts)
continue;
}
- rc = seccomp_rule_add_array(ctx, SCMP_ACT_TRAP, blacklist[i].num,
+ rc = seccomp_rule_add_array(ctx, action, blacklist[i].num,
blacklist[i].narg, blacklist[i].arg_cmp);
if (rc < 0) {
goto seccomp_return;
--
1.8.3.1

77
0056-seccomp-set-the-seccomp-filter-to-all-threads.patch Normal file
View File

@ -0,0 +1,77 @@
From ef8bae877ca544af956f8314cdd702d1c62a9b15 Mon Sep 17 00:00:00 2001
From: Eduardo Otubo <otubo@redhat.com>
Date: Fri, 28 Sep 2018 07:56:39 +0100
Subject: seccomp: set the seccomp filter to all threads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eduardo Otubo <otubo@redhat.com>
Message-id: <20180928075639.16746-6-otubo@redhat.com>
Patchwork-id: 82316
O-Subject: [RHEL-8 qemu-kvm PATCH 5/5] seccomp: set the seccomp filter to all threads
Bugzilla: 1618356
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Marc-André Lureau <marcandre.lureau@redhat.com>
commit 70dfabeaa79ba4d7a3b699abe1a047c8012db114
Author: Marc-André Lureau <marcandre.lureau@redhat.com>
Date: Wed Aug 22 19:02:50 2018 +0200
seccomp: set the seccomp filter to all threads
When using "-seccomp on", the seccomp policy is only applied to the
main thread, the vcpu worker thread and other worker threads created
after seccomp policy is applied; the seccomp policy is not applied to
e.g. the RCU thread because it is created before the seccomp policy is
applied and SECCOMP_FILTER_FLAG_TSYNC isn't used.
This can be verified with
for task in /proc/`pidof qemu`/task/*; do cat $task/status | grep Secc ; done
Seccomp: 2
Seccomp: 0
Seccomp: 0
Seccomp: 2
Seccomp: 2
Seccomp: 2
Starting with libseccomp 2.2.0 and kernel >= 3.17, we can use
seccomp_attr_set(ctx, > SCMP_FLTATR_CTL_TSYNC, 1) to update the policy
on all threads.
libseccomp requirement was bumped to 2.2.0 in previous patch.
libseccomp should fail to set the filter if it can't honour
SCMP_FLTATR_CTL_TSYNC (untested), and thus -sandbox will now fail on
kernel < 3.17.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Acked-by: Eduardo Otubo <otubo@redhat.com>
Signed-off-by: Eduardo Otubo <otubo@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
qemu-seccomp.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/qemu-seccomp.c b/qemu-seccomp.c
index f0c833f..4729eb1 100644
--- a/qemu-seccomp.c
+++ b/qemu-seccomp.c
@@ -149,6 +149,11 @@ static int seccomp_start(uint32_t seccomp_opts)
goto seccomp_return;
}
+ rc = seccomp_attr_set(ctx, SCMP_FLTATR_CTL_TSYNC, 1);
+ if (rc != 0) {
+ goto seccomp_return;
+ }
+
for (i = 0; i < ARRAY_SIZE(blacklist); i++) {
if (!(seccomp_opts & blacklist[i].set)) {
continue;
--
1.8.3.1

185
0057-memory-cleanup-side-effects-of-memory_region_init_fo.patch Normal file
View File

@ -0,0 +1,185 @@
From da9c980b19783915f8675894b88da631f27dd34d Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Fri, 5 Oct 2018 12:59:47 +0100
Subject: memory: cleanup side effects of memory_region_init_foo() on failure
RH-Author: Igor Mammedov <imammedo@redhat.com>
Message-id: <1538744387-84898-1-git-send-email-imammedo@redhat.com>
Patchwork-id: 82391
O-Subject: [RHEL-8 qemu-kvm PATCH] memory: cleanup side effects of memory_region_init_foo() on failure
Bugzilla: 1600365
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Pankaj Gupta <pagupta@redhat.com>
RH-Acked-by: Laszlo Ersek <lersek@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1600365
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=18658506
if MemoryRegion intialization fails it's left in semi-initialized state,
where it's size is not 0 and attached as child to owner object.
And this leds to crash in following use-case:
(monitor) object_add memory-backend-file,id=mem1,size=99999G,mem-path=/tmp/foo,discard-data=yes
memory.c:2083: memory_region_get_ram_ptr: Assertion `mr->ram_block' failed
Aborted (core dumped)
it happens due to assumption that memory region is intialized when
memory_region_size() != 0
and therefore it's ok to access it in
file_backend_unparent()
if (memory_region_size() != 0)
memory_region_get_ram_ptr()
which happens when object_add fails and unparents failed backend making
file_backend_unparent() access invalid memory region.
Fix it by making sure that memory_region_init_foo() APIs cleanup externally
visible side effects on failure (like set size to 0 and unparenting object)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <1536064777-42312-1-git-send-email-imammedo@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 1cd3d492624da399d66c4c3e6a5eabb8f96bb0a2)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
Conflicts:
memory.c
due missing (cbfc01710 "memory, exec: switch file ram allocation functions to 'flags' parameters")
not related to the patch signature mismatch of
qemu_ram_alloc_from_file()/qemu_ram_alloc_from_fd()
---
memory.c | 48 ++++++++++++++++++++++++++++++++++++++++++------
1 file changed, 42 insertions(+), 6 deletions(-)
diff --git a/memory.c b/memory.c
index e9cd446..88c75d8 100644
--- a/memory.c
+++ b/memory.c
@@ -1518,12 +1518,18 @@ void memory_region_init_ram_shared_nomigrate(MemoryRegion *mr,
bool share,
Error **errp)
{
+ Error *err = NULL;
memory_region_init(mr, owner, name, size);
mr->ram = true;
mr->terminates = true;
mr->destructor = memory_region_destructor_ram;
- mr->ram_block = qemu_ram_alloc(size, share, mr, errp);
+ mr->ram_block = qemu_ram_alloc(size, share, mr, &err);
mr->dirty_log_mask = tcg_enabled() ? (1 << DIRTY_MEMORY_CODE) : 0;
+ if (err) {
+ mr->size = int128_zero();
+ object_unparent(OBJECT(mr));
+ error_propagate(errp, err);
+ }
}
void memory_region_init_resizeable_ram(MemoryRegion *mr,
@@ -1536,13 +1542,19 @@ void memory_region_init_resizeable_ram(MemoryRegion *mr,
void *host),
Error **errp)
{
+ Error *err = NULL;
memory_region_init(mr, owner, name, size);
mr->ram = true;
mr->terminates = true;
mr->destructor = memory_region_destructor_ram;
mr->ram_block = qemu_ram_alloc_resizeable(size, max_size, resized,
- mr, errp);
+ mr, &err);
mr->dirty_log_mask = tcg_enabled() ? (1 << DIRTY_MEMORY_CODE) : 0;
+ if (err) {
+ mr->size = int128_zero();
+ object_unparent(OBJECT(mr));
+ error_propagate(errp, err);
+ }
}
#ifdef __linux__
@@ -1555,13 +1567,19 @@ void memory_region_init_ram_from_file(MemoryRegion *mr,
const char *path,
Error **errp)
{
+ Error *err = NULL;
memory_region_init(mr, owner, name, size);
mr->ram = true;
mr->terminates = true;
mr->destructor = memory_region_destructor_ram;
mr->align = align;
- mr->ram_block = qemu_ram_alloc_from_file(size, mr, share, path, errp);
+ mr->ram_block = qemu_ram_alloc_from_file(size, mr, share, path, &err);
mr->dirty_log_mask = tcg_enabled() ? (1 << DIRTY_MEMORY_CODE) : 0;
+ if (err) {
+ mr->size = int128_zero();
+ object_unparent(OBJECT(mr));
+ error_propagate(errp, err);
+ }
}
void memory_region_init_ram_from_fd(MemoryRegion *mr,
@@ -1572,12 +1590,18 @@ void memory_region_init_ram_from_fd(MemoryRegion *mr,
int fd,
Error **errp)
{
+ Error *err = NULL;
memory_region_init(mr, owner, name, size);
mr->ram = true;
mr->terminates = true;
mr->destructor = memory_region_destructor_ram;
- mr->ram_block = qemu_ram_alloc_from_fd(size, mr, share, fd, errp);
+ mr->ram_block = qemu_ram_alloc_from_fd(size, mr, share, fd, &err);
mr->dirty_log_mask = tcg_enabled() ? (1 << DIRTY_MEMORY_CODE) : 0;
+ if (err) {
+ mr->size = int128_zero();
+ object_unparent(OBJECT(mr));
+ error_propagate(errp, err);
+ }
}
#endif
@@ -1628,13 +1652,19 @@ void memory_region_init_rom_nomigrate(MemoryRegion *mr,
uint64_t size,
Error **errp)
{
+ Error *err = NULL;
memory_region_init(mr, owner, name, size);
mr->ram = true;
mr->readonly = true;
mr->terminates = true;
mr->destructor = memory_region_destructor_ram;
- mr->ram_block = qemu_ram_alloc(size, false, mr, errp);
+ mr->ram_block = qemu_ram_alloc(size, false, mr, &err);
mr->dirty_log_mask = tcg_enabled() ? (1 << DIRTY_MEMORY_CODE) : 0;
+ if (err) {
+ mr->size = int128_zero();
+ object_unparent(OBJECT(mr));
+ error_propagate(errp, err);
+ }
}
void memory_region_init_rom_device_nomigrate(MemoryRegion *mr,
@@ -1645,6 +1675,7 @@ void memory_region_init_rom_device_nomigrate(MemoryRegion *mr,
uint64_t size,
Error **errp)
{
+ Error *err = NULL;
assert(ops);
memory_region_init(mr, owner, name, size);
mr->ops = ops;
@@ -1652,7 +1683,12 @@ void memory_region_init_rom_device_nomigrate(MemoryRegion *mr,
mr->terminates = true;
mr->rom_device = true;
mr->destructor = memory_region_destructor_ram;
- mr->ram_block = qemu_ram_alloc(size, false, mr, errp);
+ mr->ram_block = qemu_ram_alloc(size, false, mr, &err);
+ if (err) {
+ mr->size = int128_zero();
+ object_unparent(OBJECT(mr));
+ error_propagate(errp, err);
+ }
}
void memory_region_init_iommu(void *_iommu_mr,
--
1.8.3.1

87
0058-mirror-Fail-gracefully-for-source-target.patch Normal file
View File

@ -0,0 +1,87 @@
From a96ed7a8374891516e626b797321d4be69cb071d Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 13:19:57 +0100
Subject: mirror: Fail gracefully for source == target
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010131957.23198-2-kwolf@redhat.com>
Patchwork-id: 82564
O-Subject: [RHEL-8 qemu-kvm PATCH 1/1] mirror: Fail gracefully for source == target
Bugzilla: 1637963
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Fam Zheng <famz@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
blockdev-mirror with the same node for source and target segfaults
today: A node is in its own backing chain, so mirror_start_job() decides
that this is an active commit. When adding the intermediate nodes with
block_job_add_bdrv(), it starts the iteration through the subchain with
the backing file of source, though, so it never reaches target and
instead runs into NULL at the base.
While we could fix that by starting with source itself, there is no
point in allowing mirroring a node into itself and I wouldn't be
surprised if this caused more problems later.
So just check for this scenario and error out.
Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit 86fae10c64d642256cf019e6829929fa0d259c7a)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/mirror.c | 5 +++++
tests/qemu-iotests/041 | 6 ++++++
tests/qemu-iotests/041.out | 4 ++--
3 files changed, 13 insertions(+), 2 deletions(-)
diff --git a/block/mirror.c b/block/mirror.c
index 7efba77..b61f99b 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -1516,6 +1516,11 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
buf_size = DEFAULT_MIRROR_BUF_SIZE;
}
+ if (bs == target) {
+ error_setg(errp, "Can't mirror node into itself");
+ return;
+ }
+
/* In the case of active commit, add dummy driver to provide consistent
* reads on the top, while disabling it in the intermediate nodes, and make
* the backing chain writable. */
diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041
index c20ac7d..9336ab6 100755
--- a/tests/qemu-iotests/041
+++ b/tests/qemu-iotests/041
@@ -234,6 +234,12 @@ class TestSingleBlockdev(TestSingleDrive):
result = self.vm.qmp("blockdev-add", **args)
self.assert_qmp(result, 'return', {})
+ def test_mirror_to_self(self):
+ result = self.vm.qmp(self.qmp_cmd, job_id='job0',
+ device=self.qmp_target, sync='full',
+ target=self.qmp_target)
+ self.assert_qmp(result, 'error/class', 'GenericError')
+
test_large_cluster = None
test_image_not_found = None
test_small_buffer2 = None
diff --git a/tests/qemu-iotests/041.out b/tests/qemu-iotests/041.out
index c28b392..e071d0b 100644
--- a/tests/qemu-iotests/041.out
+++ b/tests/qemu-iotests/041.out
@@ -1,5 +1,5 @@
-.....................................................................................
+........................................................................................
----------------------------------------------------------------------
-Ran 85 tests
+Ran 88 tests
OK
--
1.8.3.1

141
0059-commit-Add-top-node-base-node-options.patch Normal file
View File

@ -0,0 +1,141 @@
From 0086e14eef7fc78bc1254ee888bd7d720d6ee5b9 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 13:50:54 +0100
Subject: commit: Add top-node/base-node options
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010135055.3874-2-kwolf@redhat.com>
Patchwork-id: 82569
O-Subject: [RHEL-8 qemu-kvm PATCH 1/2] commit: Add top-node/base-node options
Bugzilla: 1637970
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Fam Zheng <famz@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
The block-commit QMP command required specifying the top and base nodes
of the commit jobs using the file name of that node. While this works
in simple cases (local files with absolute paths), the file names
generated for more complicated setups can be hard to predict.
The block-commit command has more problems than just this, so we want to
replace it altogether in the long run, but libvirt needs a reliable way
to address nodes now. So we don't want to wait for a new, cleaner
command, but just add the minimal thing needed right now.
This adds two new options top-node and base-node to the command, which
allow specifying node names instead. They are mutually exclusive with
the old options.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 3c605f4074ebeb97970eb660fb56a9cb06525923)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
blockdev.c | 32 ++++++++++++++++++++++++++++++--
qapi/block-core.json | 24 ++++++++++++++++++------
2 files changed, 48 insertions(+), 8 deletions(-)
diff --git a/blockdev.c b/blockdev.c
index d97202a..df256e6 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -3324,7 +3324,9 @@ out:
}
void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
+ bool has_base_node, const char *base_node,
bool has_base, const char *base,
+ bool has_top_node, const char *top_node,
bool has_top, const char *top,
bool has_backing_file, const char *backing_file,
bool has_speed, int64_t speed,
@@ -3385,7 +3387,20 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
/* default top_bs is the active layer */
top_bs = bs;
- if (has_top && top) {
+ if (has_top_node && has_top) {
+ error_setg(errp, "'top-node' and 'top' are mutually exclusive");
+ goto out;
+ } else if (has_top_node) {
+ top_bs = bdrv_lookup_bs(NULL, top_node, errp);
+ if (top_bs == NULL) {
+ goto out;
+ }
+ if (!bdrv_chain_contains(bs, top_bs)) {
+ error_setg(errp, "'%s' is not in this backing file chain",
+ top_node);
+ goto out;
+ }
+ } else if (has_top && top) {
if (strcmp(bs->filename, top) != 0) {
top_bs = bdrv_find_backing_image(bs, top);
}
@@ -3398,7 +3413,20 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
assert(bdrv_get_aio_context(top_bs) == aio_context);
- if (has_base && base) {
+ if (has_base_node && has_base) {
+ error_setg(errp, "'base-node' and 'base' are mutually exclusive");
+ goto out;
+ } else if (has_base_node) {
+ base_bs = bdrv_lookup_bs(NULL, base_node, errp);
+ if (base_bs == NULL) {
+ goto out;
+ }
+ if (!bdrv_chain_contains(top_bs, base_bs)) {
+ error_setg(errp, "'%s' is not in this backing file chain",
+ base_node);
+ goto out;
+ }
+ } else if (has_base && base) {
base_bs = bdrv_find_backing_image(top_bs, base);
} else {
base_bs = bdrv_find_base(top_bs);
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 2953991..6f38dc0 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -1457,12 +1457,23 @@
#
# @device: the device name or node-name of a root node
#
-# @base: The file name of the backing image to write data into.
-# If not specified, this is the deepest backing image.
+# @base-node: The node name of the backing image to write data into.
+# If not specified, this is the deepest backing image.
+# (since: 3.1)
#
-# @top: The file name of the backing image within the image chain,
-# which contains the topmost data to be committed down. If
-# not specified, this is the active layer.
+# @base: Same as @base-node, except that it is a file name rather than a node
+# name. This must be the exact filename string that was used to open the
+# node; other strings, even if addressing the same file, are not
+# accepted (deprecated, use @base-node instead)
+#
+# @top-node: The node name of the backing image within the image chain
+# which contains the topmost data to be committed down. If
+# not specified, this is the active layer. (since: 3.1)
+#
+# @top: Same as @top-node, except that it is a file name rather than a node
+# name. This must be the exact filename string that was used to open the
+# node; other strings, even if addressing the same file, are not
+# accepted (deprecated, use @base-node instead)
#
# @backing-file: The backing file string to write into the overlay
# image of 'top'. If 'top' is the active layer,
@@ -1531,7 +1542,8 @@
#
##
{ 'command': 'block-commit',
- 'data': { '*job-id': 'str', 'device': 'str', '*base': 'str', '*top': 'str',
+ 'data': { '*job-id': 'str', 'device': 'str', '*base-node': 'str',
+ '*base': 'str', '*top-node': 'str', '*top': 'str',
'*backing-file': 'str', '*speed': 'int',
'*filter-node-name': 'str',
'*auto-finalize': 'bool', '*auto-dismiss': 'bool' } }
--
1.8.3.1

127
0060-qemu-iotests-Test-commit-with-top-node-base-node.patch Normal file
View File

@ -0,0 +1,127 @@
From bb9687c8dadef42d11f3606e68e956a7c60b2487 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 13:50:55 +0100
Subject: qemu-iotests: Test commit with top-node/base-node
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010135055.3874-3-kwolf@redhat.com>
Patchwork-id: 82568
O-Subject: [RHEL-8 qemu-kvm PATCH 2/2] qemu-iotests: Test commit with top-node/base-node
Bugzilla: 1637970
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Fam Zheng <famz@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
This adds some tests for block-commit with the new options top-node and
base-node (taking node names) instead of top and base (taking file
names).
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit d57177a48fc604e5427921bf20b22ee0e6d578b3)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
tests/qemu-iotests/040 | 52 ++++++++++++++++++++++++++++++++++++++++++++--
tests/qemu-iotests/040.out | 4 ++--
2 files changed, 52 insertions(+), 4 deletions(-)
diff --git a/tests/qemu-iotests/040 b/tests/qemu-iotests/040
index 1beb5e6..1cb1cee 100755
--- a/tests/qemu-iotests/040
+++ b/tests/qemu-iotests/040
@@ -57,9 +57,12 @@ class ImageCommitTestCase(iotests.QMPTestCase):
self.assert_no_active_block_jobs()
self.vm.shutdown()
- def run_commit_test(self, top, base, need_ready=False):
+ def run_commit_test(self, top, base, need_ready=False, node_names=False):
self.assert_no_active_block_jobs()
- result = self.vm.qmp('block-commit', device='drive0', top=top, base=base)
+ if node_names:
+ result = self.vm.qmp('block-commit', device='drive0', top_node=top, base_node=base)
+ else:
+ result = self.vm.qmp('block-commit', device='drive0', top=top, base=base)
self.assert_qmp(result, 'return', {})
self.wait_for_complete(need_ready)
@@ -101,6 +104,11 @@ class TestSingleDrive(ImageCommitTestCase):
self.assertEqual(-1, qemu_io('-f', 'raw', '-c', 'read -P 0xab 0 524288', backing_img).find("verification failed"))
self.assertEqual(-1, qemu_io('-f', 'raw', '-c', 'read -P 0xef 524288 524288', backing_img).find("verification failed"))
+ def test_commit_node(self):
+ self.run_commit_test("mid", "base", node_names=True)
+ self.assertEqual(-1, qemu_io('-f', 'raw', '-c', 'read -P 0xab 0 524288', backing_img).find("verification failed"))
+ self.assertEqual(-1, qemu_io('-f', 'raw', '-c', 'read -P 0xef 524288 524288', backing_img).find("verification failed"))
+
def test_device_not_found(self):
result = self.vm.qmp('block-commit', device='nonexistent', top='%s' % mid_img)
self.assert_qmp(result, 'error/class', 'DeviceNotFound')
@@ -123,6 +131,30 @@ class TestSingleDrive(ImageCommitTestCase):
self.assert_qmp(result, 'error/class', 'GenericError')
self.assert_qmp(result, 'error/desc', 'Base \'badfile\' not found')
+ def test_top_node_invalid(self):
+ self.assert_no_active_block_jobs()
+ result = self.vm.qmp('block-commit', device='drive0', top_node='badfile', base_node='base')
+ self.assert_qmp(result, 'error/class', 'GenericError')
+ self.assert_qmp(result, 'error/desc', "Cannot find device= nor node_name=badfile")
+
+ def test_base_node_invalid(self):
+ self.assert_no_active_block_jobs()
+ result = self.vm.qmp('block-commit', device='drive0', top_node='mid', base_node='badfile')
+ self.assert_qmp(result, 'error/class', 'GenericError')
+ self.assert_qmp(result, 'error/desc', "Cannot find device= nor node_name=badfile")
+
+ def test_top_path_and_node(self):
+ self.assert_no_active_block_jobs()
+ result = self.vm.qmp('block-commit', device='drive0', top_node='mid', base_node='base', top='%s' % mid_img)
+ self.assert_qmp(result, 'error/class', 'GenericError')
+ self.assert_qmp(result, 'error/desc', "'top-node' and 'top' are mutually exclusive")
+
+ def test_base_path_and_node(self):
+ self.assert_no_active_block_jobs()
+ result = self.vm.qmp('block-commit', device='drive0', top_node='mid', base_node='base', base='%s' % backing_img)
+ self.assert_qmp(result, 'error/class', 'GenericError')
+ self.assert_qmp(result, 'error/desc', "'base-node' and 'base' are mutually exclusive")
+
def test_top_is_active(self):
self.run_commit_test(test_img, backing_img, need_ready=True)
self.assertEqual(-1, qemu_io('-f', 'raw', '-c', 'read -P 0xab 0 524288', backing_img).find("verification failed"))
@@ -139,6 +171,22 @@ class TestSingleDrive(ImageCommitTestCase):
self.assert_qmp(result, 'error/class', 'GenericError')
self.assert_qmp(result, 'error/desc', 'Base \'%s\' not found' % mid_img)
+ def test_top_and_base_node_reversed(self):
+ self.assert_no_active_block_jobs()
+ result = self.vm.qmp('block-commit', device='drive0', top_node='base', base_node='top')
+ self.assert_qmp(result, 'error/class', 'GenericError')
+ self.assert_qmp(result, 'error/desc', "'top' is not in this backing file chain")
+
+ def test_top_node_in_wrong_chain(self):
+ self.assert_no_active_block_jobs()
+
+ result = self.vm.qmp('blockdev-add', driver='null-co', node_name='null')
+ self.assert_qmp(result, 'return', {})
+
+ result = self.vm.qmp('block-commit', device='drive0', top_node='null', base_node='base')
+ self.assert_qmp(result, 'error/class', 'GenericError')
+ self.assert_qmp(result, 'error/desc', "'null' is not in this backing file chain")
+
# When the job is running on a BB that is automatically deleted on hot
# unplug, the job is cancelled when the device disappears
def test_hot_unplug(self):
diff --git a/tests/qemu-iotests/040.out b/tests/qemu-iotests/040.out
index e20a75c..802ffaa 100644
--- a/tests/qemu-iotests/040.out
+++ b/tests/qemu-iotests/040.out
@@ -1,5 +1,5 @@
-.............................
+...........................................
----------------------------------------------------------------------
-Ran 29 tests
+Ran 43 tests
OK
--
1.8.3.1

59
0061-block-for-jobs-do-not-clear-user_paused-until-after-.patch Normal file
View File

@ -0,0 +1,59 @@
From 0908cd5291828eca03bbba206f133a37b87c8b41 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Wed, 10 Oct 2018 20:50:58 +0100
Subject: block: for jobs, do not clear user_paused until after the resume
RH-Author: John Snow <jsnow@redhat.com>
Message-id: <20181010205100.17689-2-jsnow@redhat.com>
Patchwork-id: 82631
O-Subject: [RHEL8/rhel qemu-kvm PATCH 1/3] block: for jobs, do not clear user_paused until after the resume
Bugzilla: 1635583
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
From: Jeff Cody <jcody@redhat.com>
The function job_cancel_async() will always cause an assert for blockjob
user resume. We set job->user_paused to false, and then call
job->driver->user_resume(). In the case of blockjobs, this is the
block_job_user_resume() function.
In that function, we assert that job.user_paused is set to true.
Unfortunately, right before calling this function, it has explicitly
been set to false.
The fix is pretty simple: set job->user_paused to false only after the
job user_resume() function has been called.
Reviewed-by: John Snow <jsnow@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: bb183b77d8f2dd6bd67b8da559a90ac1e74b2052.1534868459.git.jcody@redhat.com
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit e321c0597c7590499bacab239d7f86e257f96bcd)
Signed-off-by: John Snow <jsnow@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
job.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/job.c b/job.c
index 87c9aa4..bb322de 100644
--- a/job.c
+++ b/job.c
@@ -705,10 +705,10 @@ static void job_cancel_async(Job *job, bool force)
{
if (job->user_paused) {
/* Do not call job_enter here, the caller will handle it. */
- job->user_paused = false;
if (job->driver->user_resume) {
job->driver->user_resume(job);
}
+ job->user_paused = false;
assert(job->pause_count > 0);
job->pause_count--;
}
--
1.8.3.1

173
0062-block-iotest-to-catch-abort-on-forced-blockjob-cance.patch Normal file
View File

@ -0,0 +1,173 @@
From d26430360b5996c99c0e1dd95b4dbb48bd894944 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Wed, 10 Oct 2018 20:51:00 +0100
Subject: block: iotest to catch abort on forced blockjob cancel
RH-Author: John Snow <jsnow@redhat.com>
Message-id: <20181010205100.17689-4-jsnow@redhat.com>
Patchwork-id: 82632
O-Subject: [RHEL8/rhel qemu-kvm PATCH 3/3] block: iotest to catch abort on forced blockjob cancel
Bugzilla: 1635583
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
From: Jeff Cody <jcody@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: df317f617fbe5affcf699cb8560e7b0c2e028a64.1534868459.git.jcody@redhat.com
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit 26bf474ba92c76e61bea51726e22da6dfd185296)
Signed-off-by: John Snow <jsnow@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
tests/qemu-iotests/229 | 95 ++++++++++++++++++++++++++++++++++++++++++++++
tests/qemu-iotests/229.out | 23 +++++++++++
tests/qemu-iotests/group | 1 +
3 files changed, 119 insertions(+)
create mode 100755 tests/qemu-iotests/229
create mode 100644 tests/qemu-iotests/229.out
diff --git a/tests/qemu-iotests/229 b/tests/qemu-iotests/229
new file mode 100755
index 0000000..ff851ec
--- /dev/null
+++ b/tests/qemu-iotests/229
@@ -0,0 +1,95 @@
+#!/bin/bash
+#
+# Test for force canceling a running blockjob that is paused in
+# an error state.
+#
+# Copyright (C) 2018 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=jcody@redhat.com
+
+seq="$(basename $0)"
+echo "QA output created by $seq"
+
+here="$PWD"
+status=1 # failure is the default!
+
+_cleanup()
+{
+ _cleanup_qemu
+ _cleanup_test_img
+ rm -f "$TEST_IMG" "$DEST_IMG"
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+. ./common.qemu
+
+# Needs backing file and backing format support
+_supported_fmt qcow2 qed
+_supported_proto file
+_supported_os Linux
+
+
+DEST_IMG="$TEST_DIR/d.$IMGFMT"
+TEST_IMG="$TEST_DIR/b.$IMGFMT"
+
+_make_test_img 2M
+
+# destination for mirror will be too small, causing error
+TEST_IMG=$DEST_IMG _make_test_img 1M
+
+$QEMU_IO -c 'write 0 2M' "$TEST_IMG" | _filter_qemu_io
+
+_launch_qemu -drive id=testdisk,file="$TEST_IMG",format="$IMGFMT"
+
+_send_qemu_cmd $QEMU_HANDLE \
+ "{'execute': 'qmp_capabilities'}" \
+ 'return'
+
+echo
+echo '=== Starting drive-mirror, causing error & stop ==='
+echo
+
+_send_qemu_cmd $QEMU_HANDLE \
+ "{'execute': 'drive-mirror',
+ 'arguments': {'device': 'testdisk',
+ 'mode': 'absolute-paths',
+ 'format': '$IMGFMT',
+ 'target': '$DEST_IMG',
+ 'sync': 'full',
+ 'mode': 'existing',
+ 'on-source-error': 'stop',
+ 'on-target-error': 'stop' }}" \
+ "JOB_STATUS_CHANGE.*pause"
+
+echo
+echo '=== Force cancel job paused in error state ==='
+echo
+
+success_or_failure="y" _send_qemu_cmd $QEMU_HANDLE \
+ "{'execute': 'block-job-cancel',
+ 'arguments': { 'device': 'testdisk',
+ 'force': true}}" \
+ "BLOCK_JOB_CANCELLED" "Assertion"
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0
diff --git a/tests/qemu-iotests/229.out b/tests/qemu-iotests/229.out
new file mode 100644
index 0000000..4c41128
--- /dev/null
+++ b/tests/qemu-iotests/229.out
@@ -0,0 +1,23 @@
+QA output created by 229
+Formatting 'TEST_DIR/b.IMGFMT', fmt=IMGFMT size=2097152
+Formatting 'TEST_DIR/d.IMGFMT', fmt=IMGFMT size=1048576
+wrote 2097152/2097152 bytes at offset 0
+2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+{"return": {}}
+
+=== Starting drive-mirror, causing error & stop ===
+
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "testdisk"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "testdisk"}}
+{"return": {}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_ERROR", "data": {"device": "testdisk", "operation": "write", "action": "stop"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "paused", "id": "testdisk"}}
+
+=== Force cancel job paused in error state ===
+
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "testdisk"}}
+{"return": {}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_ERROR", "data": {"device": "testdisk", "operation": "write", "action": "stop"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "testdisk"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "testdisk", "len": 2097152, "offset": 1048576, "speed": 0, "type": "mirror"}}
+*** done
diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group
index f1059f6..23ab4d3 100644
--- a/tests/qemu-iotests/group
+++ b/tests/qemu-iotests/group
@@ -225,3 +225,4 @@
225 rw auto quick
226 auto quick
227 auto quick
+229 auto quick
--
1.8.3.1

117
0063-Revert-hw-acpi-build-build-SRAT-memory-affinity-stru.patch Normal file
View File

@ -0,0 +1,117 @@
From c0bedad9bd133c14096eeeae49877fbb9eb179c3 Mon Sep 17 00:00:00 2001
From: Igor Mammedov <imammedo@redhat.com>
Date: Thu, 4 Oct 2018 10:31:31 +0100
Subject: Revert "hw/acpi-build: build SRAT memory affinity structures for DIMM
devices"
RH-Author: Igor Mammedov <imammedo@redhat.com>
Message-id: <1538649091-70517-1-git-send-email-imammedo@redhat.com>
Patchwork-id: 82373
O-Subject: [RHEL8/virt-8.0.0 qemu-kvm PATCH] Revert "hw/acpi-build: build SRAT memory affinity structures for DIMM devices"
Bugzilla: 1609235
RH-Acked-by: Laszlo Ersek <lersek@redhat.com>
RH-Acked-by: Michael S. Tsirkin <mst@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
Since upstream commits
(0efd7e108 "pc: acpi: fix memory hotplug regression by reducing stub SRAT entry size")
(dbb6da8ba7 "pc: acpi: revert back to 1 SRAT entry for hotpluggable area")
hasn't been backported to RHEL8, it's sufficient to revert commit
(848a1cc1e8 "hw/acpi-build: build SRAT memory affinity structures for DIMM devices")
for the result to match the current upstream state and fix the bug.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
Rebase notes (3.0.0):
- Replace hotplug_memory with device_memory in PCMachineState
---
hw/i386/acpi-build.c | 65 ++++------------------------------------------------
1 file changed, 4 insertions(+), 61 deletions(-)
diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index be9bdb5..f95516c 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -2254,64 +2254,6 @@ build_tpm2(GArray *table_data, BIOSLinker *linker, GArray *tcpalog)
#define HOLE_640K_START (640 * KiB)
#define HOLE_640K_END (1 * MiB)
-static void build_srat_hotpluggable_memory(GArray *table_data, uint64_t base,
- uint64_t len, int default_node)
-{
- MemoryDeviceInfoList *info_list = qmp_memory_device_list();
- MemoryDeviceInfoList *info;
- MemoryDeviceInfo *mi;
- PCDIMMDeviceInfo *di;
- uint64_t end = base + len, cur, size;
- bool is_nvdimm;
- AcpiSratMemoryAffinity *numamem;
- MemoryAffinityFlags flags;
-
- for (cur = base, info = info_list;
- cur < end;
- cur += size, info = info->next) {
- numamem = acpi_data_push(table_data, sizeof *numamem);
-
- if (!info) {
- /*
- * Entry is required for Windows to enable memory hotplug in OS
- * and for Linux to enable SWIOTLB when booted with less than
- * 4G of RAM. Windows works better if the entry sets proximity
- * to the highest NUMA node in the machine at the end of the
- * reserved space.
- * Memory devices may override proximity set by this entry,
- * providing _PXM method if necessary.
- */
- build_srat_memory(numamem, end - 1, 1, default_node,
- MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED);
- break;
- }
-
- mi = info->value;
- is_nvdimm = (mi->type == MEMORY_DEVICE_INFO_KIND_NVDIMM);
- di = !is_nvdimm ? mi->u.dimm.data : mi->u.nvdimm.data;
-
- if (cur < di->addr) {
- build_srat_memory(numamem, cur, di->addr - cur, default_node,
- MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED);
- numamem = acpi_data_push(table_data, sizeof *numamem);
- }
-
- size = di->size;
-
- flags = MEM_AFFINITY_ENABLED;
- if (di->hotpluggable) {
- flags |= MEM_AFFINITY_HOTPLUGGABLE;
- }
- if (is_nvdimm) {
- flags |= MEM_AFFINITY_NON_VOLATILE;
- }
-
- build_srat_memory(numamem, di->addr, size, di->node, flags);
- }
-
- qapi_free_MemoryDeviceInfoList(info_list);
-}
-
static void
build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
{
@@ -2418,9 +2360,10 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
}
if (hotplugabble_address_space_size) {
- build_srat_hotpluggable_memory(table_data, machine->device_memory->base,
- hotplugabble_address_space_size,
- pcms->numa_nodes - 1);
+ numamem = acpi_data_push(table_data, sizeof *numamem);
+ build_srat_memory(numamem, machine->device_memory->base,
+ hotplugabble_address_space_size, pcms->numa_nodes - 1,
+ MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED);
}
build_header(linker, table_data,
--
1.8.3.1

48
0064-aio-posix-Don-t-count-ctx-notifier-as-progress-when-.patch Normal file
View File

@ -0,0 +1,48 @@
From c476cf6c76298803fe896eb7c597085af3b73c12 Mon Sep 17 00:00:00 2001
From: Fam Zheng <famz@redhat.com>
Date: Tue, 9 Oct 2018 08:16:47 +0100
Subject: aio-posix: Don't count ctx->notifier as progress when polling
RH-Author: Fam Zheng <famz@redhat.com>
Message-id: <20181009081651.15463-2-famz@redhat.com>
Patchwork-id: 82454
O-Subject: [RHEL8/rhel qemu-kvm PATCH 1/5] aio-posix: Don't count ctx->notifier as progress when polling
Bugzilla: 1623085
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Danilo de Paula <ddepaula@redhat.com>
BZ: 1623085
The same logic exists in fd polling. This change is especially important
to avoid busy loop once we limit aio_notify_accept() to blocking
aio_poll().
Cc: qemu-stable@nongnu.org
Signed-off-by: Fam Zheng <famz@redhat.com>
Message-Id: <20180809132259.18402-2-famz@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit 70232b5253a3c4e03ed1ac47ef9246a8ac66c6fa)
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
util/aio-posix.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/util/aio-posix.c b/util/aio-posix.c
index 118bf57..b5c7f46 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -494,7 +494,8 @@ static bool run_poll_handlers_once(AioContext *ctx)
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
if (!node->deleted && node->io_poll &&
aio_node_check(ctx, node->is_external) &&
- node->io_poll(node->opaque)) {
+ node->io_poll(node->opaque) &&
+ node->opaque != &ctx->notifier) {
progress = true;
}
--
1.8.3.1

124
0065-aio-Do-aio_notify_accept-only-during-blocking-aio_po.patch Normal file
View File

@ -0,0 +1,124 @@
From 1580d01151ceea428dc9a25dd3d83990a594e286 Mon Sep 17 00:00:00 2001
From: Fam Zheng <famz@redhat.com>
Date: Tue, 9 Oct 2018 08:16:48 +0100
Subject: aio: Do aio_notify_accept only during blocking aio_poll
RH-Author: Fam Zheng <famz@redhat.com>
Message-id: <20181009081651.15463-3-famz@redhat.com>
Patchwork-id: 82450
O-Subject: [RHEL8/rhel qemu-kvm PATCH 2/5] aio: Do aio_notify_accept only during blocking aio_poll
Bugzilla: 1623085
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Danilo de Paula <ddepaula@redhat.com>
BZ: 1623085
An aio_notify() pairs with an aio_notify_accept(). The former should
happen in the main thread or a vCPU thread, and the latter should be
done in the IOThread.
There is one rare case that the main thread or vCPU thread may "steal"
the aio_notify() event just raised by itself, in bdrv_set_aio_context()
[1]. The sequence is like this:
main thread IO Thread
===============================================================
bdrv_drained_begin()
aio_disable_external(ctx)
aio_poll(ctx, true)
ctx->notify_me += 2
...
bdrv_drained_end()
...
aio_notify()
...
bdrv_set_aio_context()
aio_poll(ctx, false)
[1] aio_notify_accept(ctx)
ppoll() /* Hang! */
[1] is problematic. It will clear the ctx->notifier event so that
the blocked ppoll() will not return.
(For the curious, this bug was noticed when booting a number of VMs
simultaneously in RHV. One or two of the VMs will hit this race
condition, making the VIRTIO device unresponsive to I/O commands. When
it hangs, Seabios is busy waiting for a read request to complete (read
MBR), right after initializing the virtio-blk-pci device, using 100%
guest CPU. See also https://bugzilla.redhat.com/show_bug.cgi?id=1562750
for the original bug analysis.)
aio_notify() only injects an event when ctx->notify_me is set,
correspondingly aio_notify_accept() is only useful when ctx->notify_me
_was_ set. Move the call to it into the "blocking" branch. This will
effectively skip [1] and fix the hang.
Furthermore, blocking aio_poll is only allowed on home thread
(in_aio_context_home_thread), because otherwise two blocking
aio_poll()'s can steal each other's ctx->notifier event and cause
hanging just like described above.
Cc: qemu-stable@nongnu.org
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
Message-Id: <20180809132259.18402-3-famz@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit b37548fcd1b8ac2e88e185a395bef851f3fc4e65)
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
util/aio-posix.c | 4 ++--
util/aio-win32.c | 3 ++-
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/util/aio-posix.c b/util/aio-posix.c
index b5c7f46..b5c609b 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -591,6 +591,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
* so disable the optimization now.
*/
if (blocking) {
+ assert(in_aio_context_home_thread(ctx));
atomic_add(&ctx->notify_me, 2);
}
@@ -633,6 +634,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
if (blocking) {
atomic_sub(&ctx->notify_me, 2);
+ aio_notify_accept(ctx);
}
/* Adjust polling time */
@@ -676,8 +678,6 @@ bool aio_poll(AioContext *ctx, bool blocking)
}
}
- aio_notify_accept(ctx);
-
/* if we have any readable fds, dispatch event */
if (ret > 0) {
for (i = 0; i < npfd; i++) {
diff --git a/util/aio-win32.c b/util/aio-win32.c
index e676a8d..c58957c 100644
--- a/util/aio-win32.c
+++ b/util/aio-win32.c
@@ -373,11 +373,12 @@ bool aio_poll(AioContext *ctx, bool blocking)
ret = WaitForMultipleObjects(count, events, FALSE, timeout);
if (blocking) {
assert(first);
+ assert(in_aio_context_home_thread(ctx));
atomic_sub(&ctx->notify_me, 2);
+ aio_notify_accept(ctx);
}
if (first) {
- aio_notify_accept(ctx);
progress |= aio_bh_poll(ctx);
first = false;
}
--
1.8.3.1

122
0066-aio-posix-fix-concurrent-access-to-poll_disable_cnt.patch Normal file
View File

@ -0,0 +1,122 @@
From 07bbb6779b2a628b3e83b5474be550009aae034d Mon Sep 17 00:00:00 2001
From: Fam Zheng <famz@redhat.com>
Date: Tue, 9 Oct 2018 08:16:49 +0100
Subject: aio-posix: fix concurrent access to poll_disable_cnt
RH-Author: Fam Zheng <famz@redhat.com>
Message-id: <20181009081651.15463-4-famz@redhat.com>
Patchwork-id: 82452
O-Subject: [RHEL8/rhel qemu-kvm PATCH 3/5] aio-posix: fix concurrent access to poll_disable_cnt
Bugzilla: 1632622
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Danilo de Paula <ddepaula@redhat.com>
From: Paolo Bonzini <pbonzini@redhat.com>
BZ: 1632622
It is valid for an aio_set_fd_handler to happen concurrently with
aio_poll. In that case, poll_disable_cnt can change under the heels
of aio_poll, and the assertion on poll_disable_cnt can fail in
run_poll_handlers.
Therefore, this patch simply checks the counter on every polling
iteration. There are no particular needs for ordering, since the
polling loop is terminated anyway by aio_notify at the end of
aio_set_fd_handler.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20180912171040.1732-2-pbonzini@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit d7be5dd19c0df7f76e1b42f0c2cbbabefa1974cb)
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
util/aio-posix.c | 26 +++++++++++++++-----------
1 file changed, 15 insertions(+), 11 deletions(-)
diff --git a/util/aio-posix.c b/util/aio-posix.c
index b5c609b..9189033 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -211,6 +211,7 @@ void aio_set_fd_handler(AioContext *ctx,
AioHandler *node;
bool is_new = false;
bool deleted = false;
+ int poll_disable_change;
qemu_lockcnt_lock(&ctx->list_lock);
@@ -244,11 +245,9 @@ void aio_set_fd_handler(AioContext *ctx,
QLIST_REMOVE(node, node);
deleted = true;
}
-
- if (!node->io_poll) {
- ctx->poll_disable_cnt--;
- }
+ poll_disable_change = -!node->io_poll;
} else {
+ poll_disable_change = !io_poll - (node && !node->io_poll);
if (node == NULL) {
/* Alloc and insert if it's not already there */
node = g_new0(AioHandler, 1);
@@ -257,10 +256,6 @@ void aio_set_fd_handler(AioContext *ctx,
g_source_add_poll(&ctx->source, &node->pfd);
is_new = true;
-
- ctx->poll_disable_cnt += !io_poll;
- } else {
- ctx->poll_disable_cnt += !io_poll - !node->io_poll;
}
/* Update handler with latest information */
@@ -274,6 +269,15 @@ void aio_set_fd_handler(AioContext *ctx,
node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);
}
+ /* No need to order poll_disable_cnt writes against other updates;
+ * the counter is only used to avoid wasting time and latency on
+ * iterated polling when the system call will be ultimately necessary.
+ * Changing handlers is a rare event, and a little wasted polling until
+ * the aio_notify below is not an issue.
+ */
+ atomic_set(&ctx->poll_disable_cnt,
+ atomic_read(&ctx->poll_disable_cnt) + poll_disable_change);
+
aio_epoll_update(ctx, node, is_new);
qemu_lockcnt_unlock(&ctx->list_lock);
aio_notify(ctx);
@@ -525,7 +529,6 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns)
assert(ctx->notify_me);
assert(qemu_lockcnt_count(&ctx->list_lock) > 0);
- assert(ctx->poll_disable_cnt == 0);
trace_run_poll_handlers_begin(ctx, max_ns);
@@ -533,7 +536,8 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns)
do {
progress = run_poll_handlers_once(ctx);
- } while (!progress && qemu_clock_get_ns(QEMU_CLOCK_REALTIME) < end_time);
+ } while (!progress && qemu_clock_get_ns(QEMU_CLOCK_REALTIME) < end_time
+ && !atomic_read(&ctx->poll_disable_cnt));
trace_run_poll_handlers_end(ctx, progress);
@@ -552,7 +556,7 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns)
*/
static bool try_poll_mode(AioContext *ctx, bool blocking)
{
- if (blocking && ctx->poll_max_ns && ctx->poll_disable_cnt == 0) {
+ if (blocking && ctx->poll_max_ns && !atomic_read(&ctx->poll_disable_cnt)) {
/* See qemu_soonest_timeout() uint64_t hack */
int64_t max_ns = MIN((uint64_t)aio_compute_timeout(ctx),
(uint64_t)ctx->poll_ns);
--
1.8.3.1

186
0067-aio-posix-compute-timeout-before-polling.patch Normal file
View File

@ -0,0 +1,186 @@
From 44bb29739a1cfa471447d6c5880e7527399b146f Mon Sep 17 00:00:00 2001
From: Fam Zheng <famz@redhat.com>
Date: Tue, 9 Oct 2018 08:16:50 +0100
Subject: aio-posix: compute timeout before polling
RH-Author: Fam Zheng <famz@redhat.com>
Message-id: <20181009081651.15463-5-famz@redhat.com>
Patchwork-id: 82453
O-Subject: [RHEL8/rhel qemu-kvm PATCH 4/5] aio-posix: compute timeout before polling
Bugzilla: 1632622
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Danilo de Paula <ddepaula@redhat.com>
From: Paolo Bonzini <pbonzini@redhat.com>
BZ: 1632622
This is a preparation for the next patch, and also a very small
optimization. Compute the timeout only once, before invoking
try_poll_mode, and adjust it in run_poll_handlers. The adjustment
is the polling time when polling fails, or zero (non-blocking) if
polling succeeds.
Fixes: 70232b5253a3c4e03ed1ac47ef9246a8ac66c6fa
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20180912171040.1732-3-pbonzini@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit e30cffa04d52e35996569f1cfac111be19576bde)
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
util/aio-posix.c | 59 ++++++++++++++++++++++++++++++++-----------------------
util/trace-events | 4 ++--
2 files changed, 36 insertions(+), 27 deletions(-)
diff --git a/util/aio-posix.c b/util/aio-posix.c
index 9189033..bb862e1 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -490,7 +490,7 @@ static void add_pollfd(AioHandler *node)
npfd++;
}
-static bool run_poll_handlers_once(AioContext *ctx)
+static bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout)
{
bool progress = false;
AioHandler *node;
@@ -500,6 +500,7 @@ static bool run_poll_handlers_once(AioContext *ctx)
aio_node_check(ctx, node->is_external) &&
node->io_poll(node->opaque) &&
node->opaque != &ctx->notifier) {
+ *timeout = 0;
progress = true;
}
@@ -522,31 +523,38 @@ static bool run_poll_handlers_once(AioContext *ctx)
*
* Returns: true if progress was made, false otherwise
*/
-static bool run_poll_handlers(AioContext *ctx, int64_t max_ns)
+static bool run_poll_handlers(AioContext *ctx, int64_t max_ns, int64_t *timeout)
{
bool progress;
- int64_t end_time;
+ int64_t start_time, elapsed_time;
assert(ctx->notify_me);
assert(qemu_lockcnt_count(&ctx->list_lock) > 0);
- trace_run_poll_handlers_begin(ctx, max_ns);
-
- end_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + max_ns;
+ trace_run_poll_handlers_begin(ctx, max_ns, *timeout);
+ start_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
do {
- progress = run_poll_handlers_once(ctx);
- } while (!progress && qemu_clock_get_ns(QEMU_CLOCK_REALTIME) < end_time
+ progress = run_poll_handlers_once(ctx, timeout);
+ elapsed_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start_time;
+ } while (!progress && elapsed_time < max_ns
&& !atomic_read(&ctx->poll_disable_cnt));
- trace_run_poll_handlers_end(ctx, progress);
+ /* If time has passed with no successful polling, adjust *timeout to
+ * keep the same ending time.
+ */
+ if (*timeout != -1) {
+ *timeout -= MIN(*timeout, elapsed_time);
+ }
+ trace_run_poll_handlers_end(ctx, progress, *timeout);
return progress;
}
/* try_poll_mode:
* @ctx: the AioContext
- * @blocking: busy polling is only attempted when blocking is true
+ * @timeout: timeout for blocking wait, computed by the caller and updated if
+ * polling succeeds.
*
* ctx->notify_me must be non-zero so this function can detect aio_notify().
*
@@ -554,19 +562,16 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns)
*
* Returns: true if progress was made, false otherwise
*/
-static bool try_poll_mode(AioContext *ctx, bool blocking)
+static bool try_poll_mode(AioContext *ctx, int64_t *timeout)
{
- if (blocking && ctx->poll_max_ns && !atomic_read(&ctx->poll_disable_cnt)) {
- /* See qemu_soonest_timeout() uint64_t hack */
- int64_t max_ns = MIN((uint64_t)aio_compute_timeout(ctx),
- (uint64_t)ctx->poll_ns);
+ /* See qemu_soonest_timeout() uint64_t hack */
+ int64_t max_ns = MIN((uint64_t)*timeout, (uint64_t)ctx->poll_ns);
- if (max_ns) {
- poll_set_started(ctx, true);
+ if (max_ns && !atomic_read(&ctx->poll_disable_cnt)) {
+ poll_set_started(ctx, true);
- if (run_poll_handlers(ctx, max_ns)) {
- return true;
- }
+ if (run_poll_handlers(ctx, max_ns, timeout)) {
+ return true;
}
}
@@ -575,7 +580,7 @@ static bool try_poll_mode(AioContext *ctx, bool blocking)
/* Even if we don't run busy polling, try polling once in case it can make
* progress and the caller will be able to avoid ppoll(2)/epoll_wait(2).
*/
- return run_poll_handlers_once(ctx);
+ return run_poll_handlers_once(ctx, timeout);
}
bool aio_poll(AioContext *ctx, bool blocking)
@@ -605,8 +610,14 @@ bool aio_poll(AioContext *ctx, bool blocking)
start = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
}
- progress = try_poll_mode(ctx, blocking);
- if (!progress) {
+ timeout = blocking ? aio_compute_timeout(ctx) : 0;
+ progress = try_poll_mode(ctx, &timeout);
+ assert(!(timeout && progress));
+
+ /* If polling is allowed, non-blocking aio_poll does not need the
+ * system call---a single round of run_poll_handlers_once suffices.
+ */
+ if (timeout || atomic_read(&ctx->poll_disable_cnt)) {
assert(npfd == 0);
/* fill pollfds */
@@ -620,8 +631,6 @@ bool aio_poll(AioContext *ctx, bool blocking)
}
}
- timeout = blocking ? aio_compute_timeout(ctx) : 0;
-
/* wait until next event */
if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) {
AioHandler epoll_handler;
diff --git a/util/trace-events b/util/trace-events
index 4822434..79569b7 100644
--- a/util/trace-events
+++ b/util/trace-events
@@ -1,8 +1,8 @@
# See docs/devel/tracing.txt for syntax documentation.
# util/aio-posix.c
-run_poll_handlers_begin(void *ctx, int64_t max_ns) "ctx %p max_ns %"PRId64
-run_poll_handlers_end(void *ctx, bool progress) "ctx %p progress %d"
+run_poll_handlers_begin(void *ctx, int64_t max_ns, int64_t timeout) "ctx %p max_ns %"PRId64 " timeout %"PRId64
+run_poll_handlers_end(void *ctx, bool progress, int64_t timeout) "ctx %p progress %d new timeout %"PRId64
poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64
poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64
--
1.8.3.1

64
0068-aio-posix-do-skip-system-call-if-ctx-notifier-pollin.patch Normal file
View File

@ -0,0 +1,64 @@
From ea1db6ad3fcbcda2068d3aeb21c384d42004aaaf Mon Sep 17 00:00:00 2001
From: Fam Zheng <famz@redhat.com>
Date: Tue, 9 Oct 2018 08:16:51 +0100
Subject: aio-posix: do skip system call if ctx->notifier polling succeeds
RH-Author: Fam Zheng <famz@redhat.com>
Message-id: <20181009081651.15463-6-famz@redhat.com>
Patchwork-id: 82449
O-Subject: [RHEL8/rhel qemu-kvm PATCH 5/5] aio-posix: do skip system call if ctx->notifier polling succeeds
Bugzilla: 1632622
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Danilo de Paula <ddepaula@redhat.com>
From: Paolo Bonzini <pbonzini@redhat.com>
BZ: 1632622
Commit 70232b5253 ("aio-posix: Don't count ctx->notifier as progress when
2018-08-15), by not reporting progress, causes aio_poll to execute the
system call when polling succeeds because of ctx->notifier. This introduces
latency before the call to aio_bh_poll() and negates the advantages of
polling, unfortunately.
The fix builds on the previous patch, separating the effect of polling on
the timeout from the progress reported to aio_poll(). ctx->notifier
does zero the timeout, causing the caller to skip the system call,
but it does not report progress, so that the bug fix of commit 70232b5253
still stands.
Fixes: 70232b5253a3c4e03ed1ac47ef9246a8ac66c6fa
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20180912171040.1732-4-pbonzini@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit cfeb35d6774b2e936046aa9923217818bd160299)
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
util/aio-posix.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/util/aio-posix.c b/util/aio-posix.c
index bb862e1..a959ff6 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -498,10 +498,11 @@ static bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout)
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
if (!node->deleted && node->io_poll &&
aio_node_check(ctx, node->is_external) &&
- node->io_poll(node->opaque) &&
- node->opaque != &ctx->notifier) {
+ node->io_poll(node->opaque)) {
*timeout = 0;
- progress = true;
+ if (node->opaque != &ctx->notifier) {
+ progress = true;
+ }
}
/* Caller handles freeing deleted nodes. Don't do it here. */
--
1.8.3.1

202
0069-linux-headers-update.patch Normal file
View File

@ -0,0 +1,202 @@
From 7e13447e23269939c3d1267a957187a60fef36e9 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 15 Oct 2018 10:19:26 +0100
Subject: linux-headers: update
RH-Author: Thomas Huth <thuth@redhat.com>
Message-id: <1539598771-16223-2-git-send-email-thuth@redhat.com>
Patchwork-id: 82696
O-Subject: [RHEL-8 qemu-kvm PATCH 1/6] linux-headers: update
Bugzilla: 1508142
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Jens Freimann <jfreimann@redhat.com>
From: Cornelia Huck <cohuck@redhat.com>
Update to kvm/next commit dd5bd0a65ff6 ("Merge tag 'kvm-s390-next-4.20-1'
of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD")
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
(cherry picked from commit 8f3cd250a897213d39e621e3d824507b48158d42)
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
Conflicts:
linux-headers/linux/kvm.h
linux-headers/linux/vhost.h
(simple contextual conflicts due to some missing patches in downstream)
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
include/standard-headers/linux/input.h | 9 +++++----
linux-headers/asm-arm/kvm.h | 13 +++++++++++++
linux-headers/asm-arm64/kvm.h | 13 +++++++++++++
linux-headers/asm-s390/kvm.h | 2 ++
linux-headers/asm-x86/kvm.h | 1 +
linux-headers/linux/kvm.h | 3 +++
linux-headers/linux/vfio.h | 2 ++
linux-headers/linux/vhost.h | 8 ++++++++
8 files changed, 47 insertions(+), 4 deletions(-)
diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h
index 6d6128c..c0ad9fc 100644
--- a/include/standard-headers/linux/input.h
+++ b/include/standard-headers/linux/input.h
@@ -267,10 +267,11 @@ struct input_mask {
/*
* MT_TOOL types
*/
-#define MT_TOOL_FINGER 0
-#define MT_TOOL_PEN 1
-#define MT_TOOL_PALM 2
-#define MT_TOOL_MAX 2
+#define MT_TOOL_FINGER 0x00
+#define MT_TOOL_PEN 0x01
+#define MT_TOOL_PALM 0x02
+#define MT_TOOL_DIAL 0x0a
+#define MT_TOOL_MAX 0x0f
/*
* Values describing the status of a force-feedback effect
diff --git a/linux-headers/asm-arm/kvm.h b/linux-headers/asm-arm/kvm.h
index 72aa226..e1f8b74 100644
--- a/linux-headers/asm-arm/kvm.h
+++ b/linux-headers/asm-arm/kvm.h
@@ -27,6 +27,7 @@
#define __KVM_HAVE_GUEST_DEBUG
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_READONLY_MEM
+#define __KVM_HAVE_VCPU_EVENTS
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -125,6 +126,18 @@ struct kvm_sync_regs {
struct kvm_arch_memory_slot {
};
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+ struct {
+ __u8 serror_pending;
+ __u8 serror_has_esr;
+ /* Align it to 8 bytes */
+ __u8 pad[6];
+ __u64 serror_esr;
+ } exception;
+ __u32 reserved[12];
+};
+
/* If you need to interpret the index values, here is the key: */
#define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000
#define KVM_REG_ARM_COPROC_SHIFT 16
diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h
index 99cb9ad..e6a98c1 100644
--- a/linux-headers/asm-arm64/kvm.h
+++ b/linux-headers/asm-arm64/kvm.h
@@ -39,6 +39,7 @@
#define __KVM_HAVE_GUEST_DEBUG
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_READONLY_MEM
+#define __KVM_HAVE_VCPU_EVENTS
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -154,6 +155,18 @@ struct kvm_sync_regs {
struct kvm_arch_memory_slot {
};
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+ struct {
+ __u8 serror_pending;
+ __u8 serror_has_esr;
+ /* Align it to 8 bytes */
+ __u8 pad[6];
+ __u64 serror_esr;
+ } exception;
+ __u32 reserved[12];
+};
+
/* If you need to interpret the index values, here is the key: */
#define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000
#define KVM_REG_ARM_COPROC_SHIFT 16
diff --git a/linux-headers/asm-s390/kvm.h b/linux-headers/asm-s390/kvm.h
index 1ab9901..0265482 100644
--- a/linux-headers/asm-s390/kvm.h
+++ b/linux-headers/asm-s390/kvm.h
@@ -160,6 +160,8 @@ struct kvm_s390_vm_cpu_subfunc {
#define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW 1
#define KVM_S390_VM_CRYPTO_DISABLE_AES_KW 2
#define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW 3
+#define KVM_S390_VM_CRYPTO_ENABLE_APIE 4
+#define KVM_S390_VM_CRYPTO_DISABLE_APIE 5
/* kvm attributes for migration mode */
#define KVM_S390_VM_MIGRATION_STOP 0
diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h
index c535c2f..9bba973 100644
--- a/linux-headers/asm-x86/kvm.h
+++ b/linux-headers/asm-x86/kvm.h
@@ -377,5 +377,6 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
#endif /* _ASM_X86_KVM_H */
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index 2aae948..c4a5542 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -950,6 +950,9 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_HYPERV_EVENTFD 154
#define KVM_CAP_HYPERV_TLBFLUSH 155
#define KVM_CAP_S390_HPAGE_1M 156
+#define KVM_CAP_NESTED_STATE 157
+#define KVM_CAP_ARM_INJECT_SERROR_ESR 158
+#define KVM_CAP_MSR_PLATFORM_INFO 159
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index 3615a26..ceb6453 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -200,6 +200,7 @@ struct vfio_device_info {
#define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2) /* vfio-platform device */
#define VFIO_DEVICE_FLAGS_AMBA (1 << 3) /* vfio-amba device */
#define VFIO_DEVICE_FLAGS_CCW (1 << 4) /* vfio-ccw device */
+#define VFIO_DEVICE_FLAGS_AP (1 << 5) /* vfio-ap device */
__u32 num_regions; /* Max region index + 1 */
__u32 num_irqs; /* Max IRQ index + 1 */
};
@@ -215,6 +216,7 @@ struct vfio_device_info {
#define VFIO_DEVICE_API_PLATFORM_STRING "vfio-platform"
#define VFIO_DEVICE_API_AMBA_STRING "vfio-amba"
#define VFIO_DEVICE_API_CCW_STRING "vfio-ccw"
+#define VFIO_DEVICE_API_AP_STRING "vfio-ap"
/**
* VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h
index e336395..3421624 100644
--- a/linux-headers/linux/vhost.h
+++ b/linux-headers/linux/vhost.h
@@ -160,6 +160,14 @@ struct vhost_memory {
#define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24, \
struct vhost_vring_state)
+/* Set or get vhost backend capability */
+
+/* Use message type V2 */
+#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
+
+#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
+#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
+
/* VHOST_NET specific defines */
/* Attach virtio net ring to a raw socket, or tap device.
--
1.8.3.1

148
0070-s390x-cpumodel-Set-up-CPU-model-for-AP-device-suppor.patch Normal file
View File

@ -0,0 +1,148 @@
From 9ceba72eb99b073a86b0aa529154de3e06330720 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 15 Oct 2018 10:19:27 +0100
Subject: s390x/cpumodel: Set up CPU model for AP device support
RH-Author: Thomas Huth <thuth@redhat.com>
Message-id: <1539598771-16223-3-git-send-email-thuth@redhat.com>
Patchwork-id: 82694
O-Subject: [RHEL-8 qemu-kvm PATCH 2/6] s390x/cpumodel: Set up CPU model for AP device support
Bugzilla: 1508142
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Jens Freimann <jfreimann@redhat.com>
From: Tony Krowiak <akrowiak@linux.ibm.com>
A new CPU model feature and two new CPU model facilities are
introduced to support AP devices for a KVM guest.
CPU model features:
1. The S390_FEAT_AP CPU model feature indicates whether AP
instructions are available to the guest. This feature will
be enabled only if the AP instructions are available on the
linux host as determined by the availability of the
KVM_S390_VM_CRYPTO_ENABLE_APIE VM attribute which is exposed
by KVM only if the AP instructions are available on the
host.
This feature must be turned on from userspace to execute AP
instructions on the KVM guest. The QEMU command line to turn
this feature on looks something like this:
qemu-system-s390x ... -cpu xxx,ap=on ...
This feature will be supported for zEC12 and newer CPU models.
The feature will not be supported for older models because
there are few older systems on which to test and the older
crypto cards will be going out of service in the relatively
near future.
CPU model facilities:
1. The S390_FEAT_AP_QUERY_CONFIG_INFO feature indicates whether the
AP Query Configuration Information (QCI) facility is available
to the guest as determined by whether the facility is available
on the host. This feature will be exposed by KVM only if the
QCI facility is installed on the host.
2. The S390_FEAT_AP_FACILITY_TEST feature indicates whether the AP
Facility Test (APFT) facility is available to the guest as
determined by whether the facility is available on the host.
This feature will be exposed by KVM only if APFT is installed
on the host.
Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Tested-by: Pierre Morel <pmorel@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Message-Id: <20181010170309.12045-3-akrowiak@linux.ibm.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
(cherry picked from commit c5cd17afddda89376712b315a41ede96b034e4c2)
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
target/s390x/cpu_features.c | 3 +++
target/s390x/cpu_features_def.h | 3 +++
target/s390x/cpu_models.c | 2 ++
target/s390x/gen-features.c | 3 +++
4 files changed, 11 insertions(+)
diff --git a/target/s390x/cpu_features.c b/target/s390x/cpu_features.c
index e05e6aa..0fbee27 100644
--- a/target/s390x/cpu_features.c
+++ b/target/s390x/cpu_features.c
@@ -40,8 +40,10 @@ static const S390FeatDef s390_features[] = {
FEAT_INIT("srs", S390_FEAT_TYPE_STFL, 9, "Sense-running-status facility"),
FEAT_INIT("csske", S390_FEAT_TYPE_STFL, 10, "Conditional-SSKE facility"),
FEAT_INIT("ctop", S390_FEAT_TYPE_STFL, 11, "Configuration-topology facility"),
+ FEAT_INIT("apqci", S390_FEAT_TYPE_STFL, 12, "Query AP Configuration Information facility"),
FEAT_INIT("ipter", S390_FEAT_TYPE_STFL, 13, "IPTE-range facility"),
FEAT_INIT("nonqks", S390_FEAT_TYPE_STFL, 14, "Nonquiescing key-setting facility"),
+ FEAT_INIT("apft", S390_FEAT_TYPE_STFL, 15, "AP Facilities Test facility"),
FEAT_INIT("etf2", S390_FEAT_TYPE_STFL, 16, "Extended-translation facility 2"),
FEAT_INIT("msa-base", S390_FEAT_TYPE_STFL, 17, "Message-security-assist facility (excluding subfunctions)"),
FEAT_INIT("ldisp", S390_FEAT_TYPE_STFL, 18, "Long-displacement facility"),
@@ -130,6 +132,7 @@ static const S390FeatDef s390_features[] = {
FEAT_INIT_MISC("dateh2", "DAT-enhancement facility 2"),
FEAT_INIT_MISC("cmm", "Collaborative-memory-management facility"),
+ FEAT_INIT_MISC("ap", "AP instructions installed"),
FEAT_INIT("plo-cl", S390_FEAT_TYPE_PLO, 0, "PLO Compare and load (32 bit in general registers)"),
FEAT_INIT("plo-clg", S390_FEAT_TYPE_PLO, 1, "PLO Compare and load (64 bit in parameter list)"),
diff --git a/target/s390x/cpu_features_def.h b/target/s390x/cpu_features_def.h
index ac2c947..5fc7e7b 100644
--- a/target/s390x/cpu_features_def.h
+++ b/target/s390x/cpu_features_def.h
@@ -27,8 +27,10 @@ typedef enum {
S390_FEAT_SENSE_RUNNING_STATUS,
S390_FEAT_CONDITIONAL_SSKE,
S390_FEAT_CONFIGURATION_TOPOLOGY,
+ S390_FEAT_AP_QUERY_CONFIG_INFO,
S390_FEAT_IPTE_RANGE,
S390_FEAT_NONQ_KEY_SETTING,
+ S390_FEAT_AP_FACILITIES_TEST,
S390_FEAT_EXTENDED_TRANSLATION_2,
S390_FEAT_MSA,
S390_FEAT_LONG_DISPLACEMENT,
@@ -119,6 +121,7 @@ typedef enum {
/* Misc */
S390_FEAT_DAT_ENH_2,
S390_FEAT_CMM,
+ S390_FEAT_AP,
/* PLO */
S390_FEAT_PLO_CL,
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index 9c469ff..a8722cd 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -782,6 +782,8 @@ static void check_consistency(const S390CPUModel *model)
{ S390_FEAT_PRNO_TRNG_QRTCR, S390_FEAT_MSA_EXT_5 },
{ S390_FEAT_PRNO_TRNG, S390_FEAT_MSA_EXT_5 },
{ S390_FEAT_SIE_KSS, S390_FEAT_SIE_F2 },
+ { S390_FEAT_AP_QUERY_CONFIG_INFO, S390_FEAT_AP },
+ { S390_FEAT_AP_FACILITIES_TEST, S390_FEAT_AP },
};
int i;
diff --git a/target/s390x/gen-features.c b/target/s390x/gen-features.c
index 5af042c..7302269 100644
--- a/target/s390x/gen-features.c
+++ b/target/s390x/gen-features.c
@@ -447,6 +447,9 @@ static uint16_t full_GEN12_GA1[] = {
S390_FEAT_ADAPTER_INT_SUPPRESSION,
S390_FEAT_EDAT_2,
S390_FEAT_SIDE_EFFECT_ACCESS_ESOP2,
+ S390_FEAT_AP_QUERY_CONFIG_INFO,
+ S390_FEAT_AP_FACILITIES_TEST,
+ S390_FEAT_AP,
};
static uint16_t full_GEN12_GA2[] = {
--
1.8.3.1

89
0071-s390x-kvm-enable-AP-instruction-interpretation-for-g.patch Normal file
View File

@ -0,0 +1,89 @@
From ef6a15cefa04a4f29d0d800d17caa9a37c40b05c Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 15 Oct 2018 10:19:28 +0100
Subject: s390x/kvm: enable AP instruction interpretation for guest
RH-Author: Thomas Huth <thuth@redhat.com>
Message-id: <1539598771-16223-4-git-send-email-thuth@redhat.com>
Patchwork-id: 82697
O-Subject: [RHEL-8 qemu-kvm PATCH 3/6] s390x/kvm: enable AP instruction interpretation for guest
Bugzilla: 1508142
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Jens Freimann <jfreimann@redhat.com>
From: Tony Krowiak <akrowiak@linux.ibm.com>
Let's use the KVM_SET_DEVICE_ATTR ioctl to enable hardware
interpretation of AP instructions executed on the guest.
If the S390_FEAT_AP feature is switched on for the guest,
AP instructions must be interpreted by default; otherwise,
they will be intercepted.
This attribute setting may be overridden by a device. For example,
a device may want to provide AP instructions to the guest (i.e.,
S390_FEAT_AP turned on), but it may want to emulate them. In this
case, the AP instructions executed on the guest must be
intercepted; so when the device is realized, it must disable
interpretation.
Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Tested-by: Pierre Morel <pmorel@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Halil Pasic <pasic@linux.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Message-Id: <20181010170309.12045-4-akrowiak@linux.ibm.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
(cherry picked from commit 1d7db85b61cb9888b8ed8c8923343b468405b7a0)
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
target/s390x/kvm.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/target/s390x/kvm.c b/target/s390x/kvm.c
index 71d90f2..d25e2e2 100644
--- a/target/s390x/kvm.c
+++ b/target/s390x/kvm.c
@@ -2290,11 +2290,26 @@ void kvm_s390_get_host_cpu_model(S390CPUModel *model, Error **errp)
error_setg(errp, "KVM: host CPU model could not be identified");
return;
}
+ /* for now, we can only provide the AP feature with HW support */
+ if (kvm_vm_check_attr(kvm_state, KVM_S390_VM_CRYPTO,
+ KVM_S390_VM_CRYPTO_ENABLE_APIE)) {
+ set_bit(S390_FEAT_AP, model->features);
+ }
/* strip of features that are not part of the maximum model */
bitmap_and(model->features, model->features, model->def->full_feat,
S390_FEAT_MAX);
}
+static void kvm_s390_configure_apie(bool interpret)
+{
+ uint64_t attr = interpret ? KVM_S390_VM_CRYPTO_ENABLE_APIE :
+ KVM_S390_VM_CRYPTO_DISABLE_APIE;
+
+ if (kvm_vm_check_attr(kvm_state, KVM_S390_VM_CRYPTO, attr)) {
+ kvm_s390_set_attr(attr);
+ }
+}
+
void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
{
struct kvm_s390_vm_cpu_processor prop = {
@@ -2352,6 +2367,10 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
if (test_bit(S390_FEAT_CMM, model->features)) {
kvm_s390_enable_cmma();
}
+
+ if (test_bit(S390_FEAT_AP, model->features)) {
+ kvm_s390_configure_apie(true);
+ }
}
void kvm_s390_restart_interrupt(S390CPU *cpu)
--
1.8.3.1

281
0072-s390x-ap-base-Adjunct-Processor-AP-object-model.patch Normal file
View File

@ -0,0 +1,281 @@
From a57558fc97a82853d0c5e1e190297f7677598d5a Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 15 Oct 2018 10:19:29 +0100
Subject: s390x/ap: base Adjunct Processor (AP) object model
RH-Author: Thomas Huth <thuth@redhat.com>
Message-id: <1539598771-16223-5-git-send-email-thuth@redhat.com>
Patchwork-id: 82695
O-Subject: [RHEL-8 qemu-kvm PATCH 4/6] s390x/ap: base Adjunct Processor (AP) object model
Bugzilla: 1508142
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Jens Freimann <jfreimann@redhat.com>
From: Tony Krowiak <akrowiak@linux.ibm.com>
Introduces the base object model for virtualizing AP devices.
Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Tested-by: Pierre Morel <pmorel@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Message-Id: <20181010170309.12045-5-akrowiak@linux.ibm.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
(cherry picked from commit a51b31535a8ec13997de29b357f7cc1dcd8a7f9c)
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
MAINTAINERS | 12 +++++++
hw/s390x/Makefile.objs | 2 ++
hw/s390x/ap-bridge.c | 78 ++++++++++++++++++++++++++++++++++++++++++++
hw/s390x/ap-device.c | 38 +++++++++++++++++++++
hw/s390x/s390-virtio-ccw.c | 4 +++
include/hw/s390x/ap-bridge.h | 19 +++++++++++
include/hw/s390x/ap-device.h | 22 +++++++++++++
7 files changed, 175 insertions(+)
create mode 100644 hw/s390x/ap-bridge.c
create mode 100644 hw/s390x/ap-device.c
create mode 100644 include/hw/s390x/ap-bridge.h
create mode 100644 include/hw/s390x/ap-device.h
diff --git a/MAINTAINERS b/MAINTAINERS
index 666e936..d5b3c18 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1184,6 +1184,18 @@ F: include/hw/s390x/s390-ccw.h
T: git git://github.com/cohuck/qemu.git s390-next
L: qemu-s390x@nongnu.org
+vfio-ap
+M: Christian Borntraeger <borntraeger@de.ibm.com>
+M: Tony Krowiak <akrowiak@linux.ibm.com>
+M: Halil Pasic <pasic@linux.ibm.com>
+M: Pierre Morel <pmorel@linux.ibm.com>
+S: Supported
+F: hw/s390x/ap-device.c
+F: hw/s390x/ap-bridge.c
+F: include/hw/s390x/ap-device.h
+F: include/hw/s390x/ap-bridge.h
+L: qemu-s390x@nongnu.org
+
vhost
M: Michael S. Tsirkin <mst@redhat.com>
S: Supported
diff --git a/hw/s390x/Makefile.objs b/hw/s390x/Makefile.objs
index 93282f7..add89b1 100644
--- a/hw/s390x/Makefile.objs
+++ b/hw/s390x/Makefile.objs
@@ -20,3 +20,5 @@ obj-$(CONFIG_TCG) += tod-qemu.o
obj-$(CONFIG_KVM) += s390-skeys-kvm.o
obj-$(CONFIG_KVM) += s390-stattrib-kvm.o
obj-y += s390-ccw.o
+obj-y += ap-device.o
+obj-y += ap-bridge.o
diff --git a/hw/s390x/ap-bridge.c b/hw/s390x/ap-bridge.c
new file mode 100644
index 0000000..3795d30
--- /dev/null
+++ b/hw/s390x/ap-bridge.c
@@ -0,0 +1,78 @@
+/*
+ * ap bridge
+ *
+ * Copyright 2018 IBM Corp.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or (at
+ * your option) any later version. See the COPYING file in the top-level
+ * directory.
+ */
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "hw/sysbus.h"
+#include "qemu/bitops.h"
+#include "hw/s390x/ap-bridge.h"
+#include "cpu.h"
+
+static char *ap_bus_get_dev_path(DeviceState *dev)
+{
+ /* at most one */
+ return g_strdup_printf("/1");
+}
+
+static void ap_bus_class_init(ObjectClass *oc, void *data)
+{
+ BusClass *k = BUS_CLASS(oc);
+
+ k->get_dev_path = ap_bus_get_dev_path;
+ /* More than one ap device does not make sense */
+ k->max_dev = 1;
+}
+
+static const TypeInfo ap_bus_info = {
+ .name = TYPE_AP_BUS,
+ .parent = TYPE_BUS,
+ .instance_size = 0,
+ .class_init = ap_bus_class_init,
+};
+
+void s390_init_ap(void)
+{
+ DeviceState *dev;
+
+ /* If no AP instructions then no need for AP bridge */
+ if (!s390_has_feat(S390_FEAT_AP)) {
+ return;
+ }
+
+ /* Create bridge device */
+ dev = qdev_create(NULL, TYPE_AP_BRIDGE);
+ object_property_add_child(qdev_get_machine(), TYPE_AP_BRIDGE,
+ OBJECT(dev), NULL);
+ qdev_init_nofail(dev);
+
+ /* Create bus on bridge device */
+ qbus_create(TYPE_AP_BUS, dev, TYPE_AP_BUS);
+ }
+
+static void ap_bridge_class_init(ObjectClass *oc, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(oc);
+
+ set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
+}
+
+static const TypeInfo ap_bridge_info = {
+ .name = TYPE_AP_BRIDGE,
+ .parent = TYPE_SYS_BUS_DEVICE,
+ .instance_size = 0,
+ .class_init = ap_bridge_class_init,
+};
+
+static void ap_register(void)
+{
+ type_register_static(&ap_bridge_info);
+ type_register_static(&ap_bus_info);
+}
+
+type_init(ap_register)
diff --git a/hw/s390x/ap-device.c b/hw/s390x/ap-device.c
new file mode 100644
index 0000000..f5ac8db
--- /dev/null
+++ b/hw/s390x/ap-device.c
@@ -0,0 +1,38 @@
+/*
+ * Adjunct Processor (AP) matrix device
+ *
+ * Copyright 2018 IBM Corp.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or (at
+ * your option) any later version. See the COPYING file in the top-level
+ * directory.
+ */
+#include "qemu/osdep.h"
+#include "qemu/module.h"
+#include "qapi/error.h"
+#include "hw/qdev.h"
+#include "hw/s390x/ap-device.h"
+
+static void ap_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ dc->desc = "AP device class";
+ dc->hotpluggable = false;
+}
+
+static const TypeInfo ap_device_info = {
+ .name = AP_DEVICE_TYPE,
+ .parent = TYPE_DEVICE,
+ .instance_size = sizeof(APDevice),
+ .class_size = sizeof(DeviceClass),
+ .class_init = ap_class_init,
+ .abstract = true,
+};
+
+static void ap_device_register(void)
+{
+ type_register_static(&ap_device_info);
+}
+
+type_init(ap_device_register)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index cdf4558..a4b8b62 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -32,6 +32,7 @@
#include "ipl.h"
#include "hw/s390x/s390-virtio-ccw.h"
#include "hw/s390x/css-bridge.h"
+#include "hw/s390x/ap-bridge.h"
#include "migration/register.h"
#include "cpu_models.h"
#include "hw/nmi.h"
@@ -263,6 +264,9 @@ static void ccw_init(MachineState *machine)
/* init the SIGP facility */
s390_init_sigp();
+ /* create AP bridge and bus(es) */
+ s390_init_ap();
+
/* get a BUS */
css_bus = virtual_css_bus_init();
s390_init_ipl_dev(machine->kernel_filename, machine->kernel_cmdline,
diff --git a/include/hw/s390x/ap-bridge.h b/include/hw/s390x/ap-bridge.h
new file mode 100644
index 0000000..470e439
--- /dev/null
+++ b/include/hw/s390x/ap-bridge.h
@@ -0,0 +1,19 @@
+/*
+ * ap bridge
+ *
+ * Copyright 2018 IBM Corp.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or (at
+ * your option) any later version. See the COPYING file in the top-level
+ * directory.
+ */
+
+#ifndef HW_S390X_AP_BRIDGE_H
+#define HW_S390X_AP_BRIDGE_H
+
+#define TYPE_AP_BRIDGE "ap-bridge"
+#define TYPE_AP_BUS "ap-bus"
+
+void s390_init_ap(void);
+
+#endif
diff --git a/include/hw/s390x/ap-device.h b/include/hw/s390x/ap-device.h
new file mode 100644
index 0000000..765e908
--- /dev/null
+++ b/include/hw/s390x/ap-device.h
@@ -0,0 +1,22 @@
+/*
+ * Adjunct Processor (AP) matrix device interfaces
+ *
+ * Copyright 2018 IBM Corp.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or (at
+ * your option) any later version. See the COPYING file in the top-level
+ * directory.
+ */
+#ifndef HW_S390X_AP_DEVICE_H
+#define HW_S390X_AP_DEVICE_H
+
+#define AP_DEVICE_TYPE "ap-device"
+
+typedef struct APDevice {
+ DeviceState parent_obj;
+} APDevice;
+
+#define AP_DEVICE(obj) \
+ OBJECT_CHECK(APDevice, (obj), AP_DEVICE_TYPE)
+
+#endif /* HW_S390X_AP_DEVICE_H */
--
1.8.3.1

305
0073-s390x-vfio-ap-Introduce-VFIO-AP-device.patch Normal file
View File

@ -0,0 +1,305 @@
From 9f3a3325bb6859b1d3b46818a7d5b75c5d609f32 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 15 Oct 2018 10:19:30 +0100
Subject: s390x/vfio: ap: Introduce VFIO AP device
RH-Author: Thomas Huth <thuth@redhat.com>
Message-id: <1539598771-16223-6-git-send-email-thuth@redhat.com>
Patchwork-id: 82700
O-Subject: [RHEL-8 qemu-kvm PATCH 5/6] s390x/vfio: ap: Introduce VFIO AP device
Bugzilla: 1508142
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Jens Freimann <jfreimann@redhat.com>
From: Tony Krowiak <akrowiak@linux.ibm.com>
Introduces a VFIO based AP device. The device is defined via
the QEMU command line by specifying:
-device vfio-ap,sysfsdev=<path-to-mediated-matrix-device>
There may be only one vfio-ap device configured for a guest.
The mediated matrix device is created by the VFIO AP device
driver by writing a UUID to a sysfs attribute file (see
docs/vfio-ap.txt). The mediated matrix device will be named
after the UUID. Symbolic links to the $uuid are created in
many places, so the path to the mediated matrix device $uuid
can be specified in any of the following ways:
/sys/devices/vfio_ap/matrix/$uuid
/sys/devices/vfio_ap/matrix/mdev_supported_types/vfio_ap-passthrough/devices/$uuid
/sys/bus/mdev/devices/$uuid
/sys/bus/mdev/drivers/vfio_mdev/$uuid
When the vfio-ap device is realized, it acquires and opens the
VFIO iommu group to which the mediated matrix device is
bound. This causes a VFIO group notification event to be
signaled. The vfio_ap device driver's group notification
handler will get called at which time the device driver
will configure the the AP devices to which the guest will
be granted access.
Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Tested-by: Pierre Morel <pmorel@linux.ibm.com>
Acked-by: Halil Pasic <pasic@linux.ibm.com>
Tested-by: Pierre Morel <pmorel@linux.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Message-Id: <20181010170309.12045-6-akrowiak@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
[CH: added missing g_free and device category]
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
(cherry picked from commit 2fe2942cd6ddad8ddd40fe5d16d67599c28959d7)
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
MAINTAINERS | 2 +
default-configs/s390x-softmmu.mak | 1 +
hw/vfio/Makefile.objs | 1 +
hw/vfio/ap.c | 181 ++++++++++++++++++++++++++++++++++++++
include/hw/vfio/vfio-common.h | 1 +
5 files changed, 186 insertions(+)
create mode 100644 hw/vfio/ap.c
diff --git a/MAINTAINERS b/MAINTAINERS
index d5b3c18..f2fa1b8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -88,6 +88,7 @@ F: hw/char/terminal3270.c
F: hw/intc/s390_flic.c
F: hw/intc/s390_flic_kvm.c
F: hw/s390x/
+F: hw/vfio/ap.c
F: hw/vfio/ccw.c
F: hw/watchdog/wdt_diag288.c
F: include/hw/s390x/
@@ -1194,6 +1195,7 @@ F: hw/s390x/ap-device.c
F: hw/s390x/ap-bridge.c
F: include/hw/s390x/ap-device.h
F: include/hw/s390x/ap-bridge.h
+F: hw/vfio/ap.c
L: qemu-s390x@nongnu.org
vhost
diff --git a/default-configs/s390x-softmmu.mak b/default-configs/s390x-softmmu.mak
index 8b2db3e..49a59fc 100644
--- a/default-configs/s390x-softmmu.mak
+++ b/default-configs/s390x-softmmu.mak
@@ -8,3 +8,4 @@ CONFIG_S390_FLIC_KVM=$(CONFIG_KVM)
# Disabled for Red Hat Enterprise Linux:
# CONFIG_VFIO_CCW=$(CONFIG_LINUX)
CONFIG_WDT_DIAG288=y
+CONFIG_VFIO_AP=$(CONFIG_LINUX)
diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs
index d38205b..53b4cbe 100644
--- a/hw/vfio/Makefile.objs
+++ b/hw/vfio/Makefile.objs
@@ -5,4 +5,5 @@ obj-$(CONFIG_VFIO_CCW) += ccw.o
obj-$(CONFIG_VFIO_XGMAC) += calxeda-xgmac.o
obj-$(CONFIG_VFIO_AMD_XGBE) += amd-xgbe.o
obj-$(CONFIG_SOFTMMU) += spapr.o
+obj-$(CONFIG_VFIO_AP) += ap.o
endif
diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c
new file mode 100644
index 0000000..3962bb7
--- /dev/null
+++ b/hw/vfio/ap.c
@@ -0,0 +1,181 @@
+/*
+ * VFIO based AP matrix device assignment
+ *
+ * Copyright 2018 IBM Corp.
+ * Author(s): Tony Krowiak <akrowiak@linux.ibm.com>
+ * Halil Pasic <pasic@linux.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or (at
+ * your option) any later version. See the COPYING file in the top-level
+ * directory.
+ */
+
+#include <linux/vfio.h>
+#include <sys/ioctl.h>
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "hw/sysbus.h"
+#include "hw/vfio/vfio.h"
+#include "hw/vfio/vfio-common.h"
+#include "hw/s390x/ap-device.h"
+#include "qemu/error-report.h"
+#include "qemu/queue.h"
+#include "qemu/option.h"
+#include "qemu/config-file.h"
+#include "cpu.h"
+#include "kvm_s390x.h"
+#include "sysemu/sysemu.h"
+#include "hw/s390x/ap-bridge.h"
+#include "exec/address-spaces.h"
+
+#define VFIO_AP_DEVICE_TYPE "vfio-ap"
+
+typedef struct VFIOAPDevice {
+ APDevice apdev;
+ VFIODevice vdev;
+} VFIOAPDevice;
+
+#define VFIO_AP_DEVICE(obj) \
+ OBJECT_CHECK(VFIOAPDevice, (obj), VFIO_AP_DEVICE_TYPE)
+
+static void vfio_ap_compute_needs_reset(VFIODevice *vdev)
+{
+ vdev->needs_reset = false;
+}
+
+/*
+ * We don't need vfio_hot_reset_multi and vfio_eoi operations for
+ * vfio-ap device now.
+ */
+struct VFIODeviceOps vfio_ap_ops = {
+ .vfio_compute_needs_reset = vfio_ap_compute_needs_reset,
+};
+
+static void vfio_ap_put_device(VFIOAPDevice *vapdev)
+{
+ g_free(vapdev->vdev.name);
+ vfio_put_base_device(&vapdev->vdev);
+}
+
+static VFIOGroup *vfio_ap_get_group(VFIOAPDevice *vapdev, Error **errp)
+{
+ GError *gerror = NULL;
+ char *symlink, *group_path;
+ int groupid;
+
+ symlink = g_strdup_printf("%s/iommu_group", vapdev->vdev.sysfsdev);
+ group_path = g_file_read_link(symlink, &gerror);
+ g_free(symlink);
+
+ if (!group_path) {
+ error_setg(errp, "%s: no iommu_group found for %s: %s",
+ VFIO_AP_DEVICE_TYPE, vapdev->vdev.sysfsdev, gerror->message);
+ return NULL;
+ }
+
+ if (sscanf(basename(group_path), "%d", &groupid) != 1) {
+ error_setg(errp, "vfio: failed to read %s", group_path);
+ g_free(group_path);
+ return NULL;
+ }
+
+ g_free(group_path);
+
+ return vfio_get_group(groupid, &address_space_memory, errp);
+}
+
+static void vfio_ap_realize(DeviceState *dev, Error **errp)
+{
+ int ret;
+ char *mdevid;
+ Error *local_err = NULL;
+ VFIOGroup *vfio_group;
+ APDevice *apdev = AP_DEVICE(dev);
+ VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev);
+
+ vfio_group = vfio_ap_get_group(vapdev, &local_err);
+ if (!vfio_group) {
+ goto out_err;
+ }
+
+ vapdev->vdev.ops = &vfio_ap_ops;
+ vapdev->vdev.type = VFIO_DEVICE_TYPE_AP;
+ mdevid = basename(vapdev->vdev.sysfsdev);
+ vapdev->vdev.name = g_strdup_printf("%s", mdevid);
+ vapdev->vdev.dev = dev;
+
+ ret = vfio_get_device(vfio_group, mdevid, &vapdev->vdev, &local_err);
+ if (ret) {
+ goto out_get_dev_err;
+ }
+
+ return;
+
+out_get_dev_err:
+ vfio_ap_put_device(vapdev);
+ vfio_put_group(vfio_group);
+out_err:
+ error_propagate(errp, local_err);
+}
+
+static void vfio_ap_unrealize(DeviceState *dev, Error **errp)
+{
+ APDevice *apdev = AP_DEVICE(dev);
+ VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev);
+ VFIOGroup *group = vapdev->vdev.group;
+
+ vfio_ap_put_device(vapdev);
+ vfio_put_group(group);
+}
+
+static Property vfio_ap_properties[] = {
+ DEFINE_PROP_STRING("sysfsdev", VFIOAPDevice, vdev.sysfsdev),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vfio_ap_reset(DeviceState *dev)
+{
+ int ret;
+ APDevice *apdev = AP_DEVICE(dev);
+ VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev);
+
+ ret = ioctl(vapdev->vdev.fd, VFIO_DEVICE_RESET);
+ if (ret) {
+ error_report("%s: failed to reset %s device: %s", __func__,
+ vapdev->vdev.name, strerror(ret));
+ }
+}
+
+static const VMStateDescription vfio_ap_vmstate = {
+ .name = VFIO_AP_DEVICE_TYPE,
+ .unmigratable = 1,
+};
+
+static void vfio_ap_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ dc->props = vfio_ap_properties;
+ dc->vmsd = &vfio_ap_vmstate;
+ dc->desc = "VFIO-based AP device assignment";
+ set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+ dc->realize = vfio_ap_realize;
+ dc->unrealize = vfio_ap_unrealize;
+ dc->hotpluggable = false;
+ dc->reset = vfio_ap_reset;
+ dc->bus_type = TYPE_AP_BUS;
+}
+
+static const TypeInfo vfio_ap_info = {
+ .name = VFIO_AP_DEVICE_TYPE,
+ .parent = AP_DEVICE_TYPE,
+ .instance_size = sizeof(VFIOAPDevice),
+ .class_init = vfio_ap_class_init,
+};
+
+static void vfio_ap_type_init(void)
+{
+ type_register_static(&vfio_ap_info);
+}
+
+type_init(vfio_ap_type_init)
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index a903692..1389da4 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -37,6 +37,7 @@ enum {
VFIO_DEVICE_TYPE_PCI = 0,
VFIO_DEVICE_TYPE_PLATFORM = 1,
VFIO_DEVICE_TYPE_CCW = 2,
+ VFIO_DEVICE_TYPE_AP = 3,
};
typedef struct VFIOMmap {
--
1.8.3.1

889
0074-s390-doc-detailed-specifications-for-AP-virtualizati.patch Normal file
View File

@ -0,0 +1,889 @@
From 8f59c31a8b0c4cde4bc92126d7102c1be9da97d4 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 15 Oct 2018 10:19:31 +0100
Subject: s390: doc: detailed specifications for AP virtualization
RH-Author: Thomas Huth <thuth@redhat.com>
Message-id: <1539598771-16223-7-git-send-email-thuth@redhat.com>
Patchwork-id: 82699
O-Subject: [RHEL-8 qemu-kvm PATCH 6/6] s390: doc: detailed specifications for AP virtualization
Bugzilla: 1508142
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Jens Freimann <jfreimann@redhat.com>
From: Tony Krowiak <akrowiak@linux.ibm.com>
This patch provides documentation describing the AP architecture and
design concepts behind the virtualization of AP devices. It also
includes an example of how to configure AP devices for exclusive
use of KVM guests.
Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Pierre Morel <pmorel@linux.ibm.com>
Tested-by: Pierre Morel <pmorel@linux.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Message-Id: <20181010170309.12045-7-akrowiak@linux.ibm.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
(cherry picked from commit 694a8d703bfe06226a0574f5ec4af17a2b7060ef)
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
MAINTAINERS | 2 +
docs/vfio-ap.txt | 825 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 827 insertions(+)
create mode 100644 docs/vfio-ap.txt
diff --git a/MAINTAINERS b/MAINTAINERS
index f2fa1b8..fdbfc04 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -96,6 +96,7 @@ F: include/hw/watchdog/wdt_diag288.h
F: pc-bios/s390-ccw/
F: pc-bios/s390-ccw.img
F: target/s390x/
+F: docs/vfio-ap.txt
K: ^Subject:.*(?i)s390x?
T: git git://github.com/cohuck/qemu.git s390-next
L: qemu-s390x@nongnu.org
@@ -1196,6 +1197,7 @@ F: hw/s390x/ap-bridge.c
F: include/hw/s390x/ap-device.h
F: include/hw/s390x/ap-bridge.h
F: hw/vfio/ap.c
+F: docs/vfio-ap.txt
L: qemu-s390x@nongnu.org
vhost
diff --git a/docs/vfio-ap.txt b/docs/vfio-ap.txt
new file mode 100644
index 0000000..1233968
--- /dev/null
+++ b/docs/vfio-ap.txt
@@ -0,0 +1,825 @@
+Adjunct Processor (AP) Device
+=============================
+
+Contents:
+=========
+* Introduction
+* AP Architectural Overview
+* Start Interpretive Execution (SIE) Instruction
+* AP Matrix Configuration on Linux Host
+* Starting a Linux Guest Configured with an AP Matrix
+* Example: Configure AP Matrices for Three Linux Guests
+
+Introduction:
+============
+The IBM Adjunct Processor (AP) Cryptographic Facility is comprised
+of three AP instructions and from 1 to 256 PCIe cryptographic adapter cards.
+These AP devices provide cryptographic functions to all CPUs assigned to a
+linux system running in an IBM Z system LPAR.
+
+On s390x, AP adapter cards are exposed via the AP bus. This document
+describes how those cards may be made available to KVM guests using the
+VFIO mediated device framework.
+
+AP Architectural Overview:
+=========================
+In order understand the terminology used in the rest of this document, let's
+start with some definitions:
+
+* AP adapter
+
+ An AP adapter is an IBM Z adapter card that can perform cryptographic
+ functions. There can be from 0 to 256 adapters assigned to an LPAR depending
+ on the machine model. Adapters assigned to the LPAR in which a linux host is
+ running will be available to the linux host. Each adapter is identified by a
+ number from 0 to 255; however, the maximum adapter number allowed is
+ determined by machine model. When installed, an AP adapter is accessed by
+ AP instructions executed by any CPU.
+
+* AP domain
+
+ An adapter is partitioned into domains. Each domain can be thought of as
+ a set of hardware registers for processing AP instructions. An adapter can
+ hold up to 256 domains; however, the maximum domain number allowed is
+ determined by machine model. Each domain is identified by a number from 0 to
+ 255. Domains can be further classified into two types:
+
+ * Usage domains are domains that can be accessed directly to process AP
+ commands
+
+ * Control domains are domains that are accessed indirectly by AP
+ commands sent to a usage domain to control or change the domain; for
+ example, to set a secure private key for the domain.
+
+* AP Queue
+
+ An AP queue is the means by which an AP command-request message is sent to an
+ AP usage domain inside a specific AP. An AP queue is identified by a tuple
+ comprised of an AP adapter ID (APID) and an AP queue index (APQI). The
+ APQI corresponds to a given usage domain number within the adapter. This tuple
+ forms an AP Queue Number (APQN) uniquely identifying an AP queue. AP
+ instructions include a field containing the APQN to identify the AP queue to
+ which the AP command-request message is to be sent for processing.
+
+* AP Instructions:
+
+ There are three AP instructions:
+
+ * NQAP: to enqueue an AP command-request message to a queue
+ * DQAP: to dequeue an AP command-reply message from a queue
+ * PQAP: to administer the queues
+
+ AP instructions identify the domain that is targeted to process the AP
+ command; this must be one of the usage domains. An AP command may modify a
+ domain that is not one of the usage domains, but the modified domain
+ must be one of the control domains.
+
+Start Interpretive Execution (SIE) Instruction
+==============================================
+A KVM guest is started by executing the Start Interpretive Execution (SIE)
+instruction. The SIE state description is a control block that contains the
+state information for a KVM guest and is supplied as input to the SIE
+instruction. The SIE state description contains a satellite control block called
+the Crypto Control Block (CRYCB). The CRYCB contains three fields to identify
+the adapters, usage domains and control domains assigned to the KVM guest:
+
+* The AP Mask (APM) field is a bit mask that identifies the AP adapters assigned
+ to the KVM guest. Each bit in the mask, from left to right, corresponds to
+ an APID from 0-255. If a bit is set, the corresponding adapter is valid for
+ use by the KVM guest.
+
+* The AP Queue Mask (AQM) field is a bit mask identifying the AP usage domains
+ assigned to the KVM guest. Each bit in the mask, from left to right,
+ corresponds to an AP queue index (APQI) from 0-255. If a bit is set, the
+ corresponding queue is valid for use by the KVM guest.
+
+* The AP Domain Mask field is a bit mask that identifies the AP control domains
+ assigned to the KVM guest. The ADM bit mask controls which domains can be
+ changed by an AP command-request message sent to a usage domain from the
+ guest. Each bit in the mask, from left to right, corresponds to a domain from
+ 0-255. If a bit is set, the corresponding domain can be modified by an AP
+ command-request message sent to a usage domain.
+
+If you recall from the description of an AP Queue, AP instructions include
+an APQN to identify the AP adapter and AP queue to which an AP command-request
+message is to be sent (NQAP and PQAP instructions), or from which a
+command-reply message is to be received (DQAP instruction). The validity of an
+APQN is defined by the matrix calculated from the APM and AQM; it is the
+cross product of all assigned adapter numbers (APM) with all assigned queue
+indexes (AQM). For example, if adapters 1 and 2 and usage domains 5 and 6 are
+assigned to a guest, the APQNs (1,5), (1,6), (2,5) and (2,6) will be valid for
+the guest.
+
+The APQNs can provide secure key functionality - i.e., a private key is stored
+on the adapter card for each of its domains - so each APQN must be assigned to
+at most one guest or the linux host.
+
+ Example 1: Valid configuration:
+ ------------------------------
+ Guest1: adapters 1,2 domains 5,6
+ Guest2: adapter 1,2 domain 7
+
+ This is valid because both guests have a unique set of APQNs: Guest1 has
+ APQNs (1,5), (1,6), (2,5) and (2,6); Guest2 has APQNs (1,7) and (2,7).
+
+ Example 2: Valid configuration:
+ ------------------------------
+ Guest1: adapters 1,2 domains 5,6
+ Guest2: adapters 3,4 domains 5,6
+
+ This is also valid because both guests have a unique set of APQNs:
+ Guest1 has APQNs (1,5), (1,6), (2,5), (2,6);
+ Guest2 has APQNs (3,5), (3,6), (4,5), (4,6)
+
+ Example 3: Invalid configuration:
+ --------------------------------
+ Guest1: adapters 1,2 domains 5,6
+ Guest2: adapter 1 domains 6,7
+
+ This is an invalid configuration because both guests have access to
+ APQN (1,6).
+
+AP Matrix Configuration on Linux Host:
+=====================================
+A linux system is a guest of the LPAR in which it is running and has access to
+the AP resources configured for the LPAR. The LPAR's AP matrix is
+configured via its Activation Profile which can be edited on the HMC. When the
+linux system is started, the AP bus will detect the AP devices assigned to the
+LPAR and create the following in sysfs:
+
+/sys/bus/ap
+... [devices]
+...... xx.yyyy
+...... ...
+...... cardxx
+...... ...
+
+Where:
+ cardxx is AP adapter number xx (in hex)
+....xx.yyyy is an APQN with xx specifying the APID and yyyy specifying the
+ APQI
+
+For example, if AP adapters 5 and 6 and domains 4, 71 (0x47), 171 (0xab) and
+255 (0xff) are configured for the LPAR, the sysfs representation on the linux
+host system would look like this:
+
+/sys/bus/ap
+... [devices]
+...... 05.0004
+...... 05.0047
+...... 05.00ab
+...... 05.00ff
+...... 06.0004
+...... 06.0047
+...... 06.00ab
+...... 06.00ff
+...... card05
+...... card06
+
+A set of default device drivers are also created to control each type of AP
+device that can be assigned to the LPAR on which a linux host is running:
+
+/sys/bus/ap
+... [drivers]
+...... [cex2acard] for Crypto Express 2/3 accelerator cards
+...... [cex2aqueue] for AP queues served by Crypto Express 2/3
+ accelerator cards
+...... [cex4card] for Crypto Express 4/5/6 accelerator and coprocessor
+ cards
+...... [cex4queue] for AP queues served by Crypto Express 4/5/6
+ accelerator and coprocessor cards
+...... [pcixcccard] for Crypto Express 2/3 coprocessor cards
+...... [pcixccqueue] for AP queues served by Crypto Express 2/3
+ coprocessor cards
+
+Binding AP devices to device drivers
+------------------------------------
+There are two sysfs files that specify bitmasks marking a subset of the APQN
+range as 'usable by the default AP queue device drivers' or 'not usable by the
+default device drivers' and thus available for use by the alternate device
+driver(s). The sysfs locations of the masks are:
+
+ /sys/bus/ap/apmask
+ /sys/bus/ap/aqmask
+
+ The 'apmask' is a 256-bit mask that identifies a set of AP adapter IDs
+ (APID). Each bit in the mask, from left to right (i.e., from most significant
+ to least significant bit in big endian order), corresponds to an APID from
+ 0-255. If a bit is set, the APID is marked as usable only by the default AP
+ queue device drivers; otherwise, the APID is usable by the vfio_ap
+ device driver.
+
+ The 'aqmask' is a 256-bit mask that identifies a set of AP queue indexes
+ (APQI). Each bit in the mask, from left to right (i.e., from most significant
+ to least significant bit in big endian order), corresponds to an APQI from
+ 0-255. If a bit is set, the APQI is marked as usable only by the default AP
+ queue device drivers; otherwise, the APQI is usable by the vfio_ap device
+ driver.
+
+ Take, for example, the following mask:
+
+ 0x7dffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
+
+ It indicates:
+
+ 1, 2, 3, 4, 5, and 7-255 belong to the default drivers' pool, and 0 and 6
+ belong to the vfio_ap device driver's pool.
+
+ The APQN of each AP queue device assigned to the linux host is checked by the
+ AP bus against the set of APQNs derived from the cross product of APIDs
+ and APQIs marked as usable only by the default AP queue device drivers. If a
+ match is detected, only the default AP queue device drivers will be probed;
+ otherwise, the vfio_ap device driver will be probed.
+
+ By default, the two masks are set to reserve all APQNs for use by the default
+ AP queue device drivers. There are two ways the default masks can be changed:
+
+ 1. The sysfs mask files can be edited by echoing a string into the
+ respective sysfs mask file in one of two formats:
+
+ * An absolute hex string starting with 0x - like "0x12345678" - sets
+ the mask. If the given string is shorter than the mask, it is padded
+ with 0s on the right; for example, specifying a mask value of 0x41 is
+ the same as specifying:
+
+ 0x4100000000000000000000000000000000000000000000000000000000000000
+
+ Keep in mind that the mask reads from left to right (i.e., most
+ significant to least significant bit in big endian order), so the mask
+ above identifies device numbers 1 and 7 (01000001).
+
+ If the string is longer than the mask, the operation is terminated with
+ an error (EINVAL).
+
+ * Individual bits in the mask can be switched on and off by specifying
+ each bit number to be switched in a comma separated list. Each bit
+ number string must be prepended with a ('+') or minus ('-') to indicate
+ the corresponding bit is to be switched on ('+') or off ('-'). Some
+ valid values are:
+
+ "+0" switches bit 0 on
+ "-13" switches bit 13 off
+ "+0x41" switches bit 65 on
+ "-0xff" switches bit 255 off
+
+ The following example:
+ +0,-6,+0x47,-0xf0
+
+ Switches bits 0 and 71 (0x47) on
+ Switches bits 6 and 240 (0xf0) off
+
+ Note that the bits not specified in the list remain as they were before
+ the operation.
+
+ 2. The masks can also be changed at boot time via parameters on the kernel
+ command line like this:
+
+ ap.apmask=0xffff ap.aqmask=0x40
+
+ This would create the following masks:
+
+ apmask:
+ 0xffff000000000000000000000000000000000000000000000000000000000000
+
+ aqmask:
+ 0x4000000000000000000000000000000000000000000000000000000000000000
+
+ Resulting in these two pools:
+
+ default drivers pool: adapter 0-15, domain 1
+ alternate drivers pool: adapter 16-255, domains 0, 2-255
+
+Configuring an AP matrix for a linux guest.
+------------------------------------------
+The sysfs interfaces for configuring an AP matrix for a guest are built on the
+VFIO mediated device framework. To configure an AP matrix for a guest, a
+mediated matrix device must first be created for the /sys/devices/vfio_ap/matrix
+device. When the vfio_ap device driver is loaded, it registers with the VFIO
+mediated device framework. When the driver registers, the sysfs interfaces for
+creating mediated matrix devices is created:
+
+/sys/devices
+... [vfio_ap]
+......[matrix]
+......... [mdev_supported_types]
+............ [vfio_ap-passthrough]
+............... create
+............... [devices]
+
+A mediated AP matrix device is created by writing a UUID to the attribute file
+named 'create', for example:
+
+ uuidgen > create
+
+ or
+
+ echo $uuid > create
+
+When a mediated AP matrix device is created, a sysfs directory named after
+the UUID is created in the 'devices' subdirectory:
+
+/sys/devices
+... [vfio_ap]
+......[matrix]
+......... [mdev_supported_types]
+............ [vfio_ap-passthrough]
+............... create
+............... [devices]
+.................. [$uuid]
+
+There will also be three sets of attribute files created in the mediated
+matrix device's sysfs directory to configure an AP matrix for the
+KVM guest:
+
+/sys/devices
+... [vfio_ap]
+......[matrix]
+......... [mdev_supported_types]
+............ [vfio_ap-passthrough]
+............... create
+............... [devices]
+.................. [$uuid]
+..................... assign_adapter
+..................... assign_control_domain
+..................... assign_domain
+..................... matrix
+..................... unassign_adapter
+..................... unassign_control_domain
+..................... unassign_domain
+
+assign_adapter
+ To assign an AP adapter to the mediated matrix device, its APID is written
+ to the 'assign_adapter' file. This may be done multiple times to assign more
+ than one adapter. The APID may be specified using conventional semantics
+ as a decimal, hexadecimal, or octal number. For example, to assign adapters
+ 4, 5 and 16 to a mediated matrix device in decimal, hexadecimal and octal
+ respectively:
+
+ echo 4 > assign_adapter
+ echo 0x5 > assign_adapter
+ echo 020 > assign_adapter
+
+ In order to successfully assign an adapter:
+
+ * The adapter number specified must represent a value from 0 up to the
+ maximum adapter number allowed by the machine model. If an adapter number
+ higher than the maximum is specified, the operation will terminate with
+ an error (ENODEV).
+
+ * All APQNs that can be derived from the adapter ID being assigned and the
+ IDs of the previously assigned domains must be bound to the vfio_ap device
+ driver. If no domains have yet been assigned, then there must be at least
+ one APQN with the specified APID bound to the vfio_ap driver. If no such
+ APQNs are bound to the driver, the operation will terminate with an
+ error (EADDRNOTAVAIL).
+
+ No APQN that can be derived from the adapter ID and the IDs of the
+ previously assigned domains can be assigned to another mediated matrix
+ device. If an APQN is assigned to another mediated matrix device, the
+ operation will terminate with an error (EADDRINUSE).
+
+unassign_adapter
+ To unassign an AP adapter, its APID is written to the 'unassign_adapter'
+ file. This may also be done multiple times to unassign more than one adapter.
+
+assign_domain
+ To assign a usage domain, the domain number is written into the
+ 'assign_domain' file. This may be done multiple times to assign more than one
+ usage domain. The domain number is specified using conventional semantics as
+ a decimal, hexadecimal, or octal number. For example, to assign usage domains
+ 4, 8, and 71 to a mediated matrix device in decimal, hexadecimal and octal
+ respectively:
+
+ echo 4 > assign_domain
+ echo 0x8 > assign_domain
+ echo 0107 > assign_domain
+
+ In order to successfully assign a domain:
+
+ * The domain number specified must represent a value from 0 up to the
+ maximum domain number allowed by the machine model. If a domain number
+ higher than the maximum is specified, the operation will terminate with
+ an error (ENODEV).
+
+ * All APQNs that can be derived from the domain ID being assigned and the IDs
+ of the previously assigned adapters must be bound to the vfio_ap device
+ driver. If no domains have yet been assigned, then there must be at least
+ one APQN with the specified APQI bound to the vfio_ap driver. If no such
+ APQNs are bound to the driver, the operation will terminate with an
+ error (EADDRNOTAVAIL).
+
+ No APQN that can be derived from the domain ID being assigned and the IDs
+ of the previously assigned adapters can be assigned to another mediated
+ matrix device. If an APQN is assigned to another mediated matrix device,
+ the operation will terminate with an error (EADDRINUSE).
+
+unassign_domain
+ To unassign a usage domain, the domain number is written into the
+ 'unassign_domain' file. This may be done multiple times to unassign more than
+ one usage domain.
+
+assign_control_domain
+ To assign a control domain, the domain number is written into the
+ 'assign_control_domain' file. This may be done multiple times to
+ assign more than one control domain. The domain number may be specified using
+ conventional semantics as a decimal, hexadecimal, or octal number. For
+ example, to assign control domains 4, 8, and 71 to a mediated matrix device
+ in decimal, hexadecimal and octal respectively:
+
+ echo 4 > assign_domain
+ echo 0x8 > assign_domain
+ echo 0107 > assign_domain
+
+ In order to successfully assign a control domain, the domain number
+ specified must represent a value from 0 up to the maximum domain number
+ allowed by the machine model. If a control domain number higher than the
+ maximum is specified, the operation will terminate with an error (ENODEV).
+
+unassign_control_domain
+ To unassign a control domain, the domain number is written into the
+ 'unassign_domain' file. This may be done multiple times to unassign more than
+ one control domain.
+
+Notes: Hot plug/unplug is not currently supported for mediated AP matrix
+devices, so no changes to the AP matrix will be allowed while a guest using
+the mediated matrix device is running. Attempts to assign an adapter,
+domain or control domain will be rejected and an error (EBUSY) returned.
+
+Starting a Linux Guest Configured with an AP Matrix:
+===================================================
+To provide a mediated matrix device for use by a guest, the following option
+must be specified on the QEMU command line:
+
+ -device vfio_ap,sysfsdev=$path-to-mdev
+
+The sysfsdev parameter specifies the path to the mediated matrix device.
+There are a number of ways to specify this path:
+
+/sys/devices/vfio_ap/matrix/$uuid
+/sys/bus/mdev/devices/$uuid
+/sys/bus/mdev/drivers/vfio_mdev/$uuid
+/sys/devices/vfio_ap/matrix/mdev_supported_types/vfio_ap-passthrough/devices/$uuid
+
+When the linux guest is started, the guest will open the mediated
+matrix device's file descriptor to get information about the mediated matrix
+device. The vfio_ap device driver will update the APM, AQM, and ADM fields in
+the guest's CRYCB with the adapter, usage domain and control domains assigned
+via the mediated matrix device's sysfs attribute files. Programs running on the
+linux guest will then:
+
+1. Have direct access to the APQNs derived from the cross product of the AP
+ adapter numbers (APID) and queue indexes (APQI) specified in the APM and AQM
+ fields of the guests's CRYCB respectively. These APQNs identify the AP queues
+ that are valid for use by the guest; meaning, AP commands can be sent by the
+ guest to any of these queues for processing.
+
+2. Have authorization to process AP commands to change a control domain
+ identified in the ADM field of the guest's CRYCB. The AP command must be sent
+ to a valid APQN (see 1 above).
+
+CPU model features:
+
+Three CPU model features are available for controlling guest access to AP
+facilities:
+
+1. AP facilities feature
+
+ The AP facilities feature indicates that AP facilities are installed on the
+ guest. This feature will be exposed for use only if the AP facilities
+ are installed on the host system. The feature is s390-specific and is
+ represented as a parameter of the -cpu option on the QEMU command line:
+
+ qemu-system-s390x -cpu $model,ap=on|off
+
+ Where:
+
+ $model is the CPU model defined for the guest (defaults to the model of
+ the host system if not specified).
+
+ ap=on|off indicates whether AP facilities are installed (on) or not
+ (off). The default for CPU models zEC12 or newer
+ is ap=on. AP facilities must be installed on the guest if a
+ vfio-ap device (-device vfio-ap,sysfsdev=$path) is configured
+ for the guest, or the guest will fail to start.
+
+2. Query Configuration Information (QCI) facility
+
+ The QCI facility is used by the AP bus running on the guest to query the
+ configuration of the AP facilities. This facility will be available
+ only if the QCI facility is installed on the host system. The feature is
+ s390-specific and is represented as a parameter of the -cpu option on the
+ QEMU command line:
+
+ qemu-system-s390x -cpu $model,apqci=on|off
+
+ Where:
+
+ $model is the CPU model defined for the guest
+
+ apqci=on|off indicates whether the QCI facility is installed (on) or
+ not (off). The default for CPU models zEC12 or newer
+ is apqci=on; for older models, QCI will not be installed.
+
+ If QCI is installed (apqci=on) but AP facilities are not
+ (ap=off), an error message will be logged, but the guest
+ will be allowed to start. It makes no sense to have QCI
+ installed if the AP facilities are not; this is considered
+ an invalid configuration.
+
+ If the QCI facility is not installed, APQNs with an APQI
+ greater than 15 will not be detected by the AP bus
+ running on the guest.
+
+3. Adjunct Process Facility Test (APFT) facility
+
+ The APFT facility is used by the AP bus running on the guest to test the
+ AP facilities available for a given AP queue. This facility will be available
+ only if the APFT facility is installed on the host system. The feature is
+ s390-specific and is represented as a parameter of the -cpu option on the
+ QEMU command line:
+
+ qemu-system-s390x -cpu $model,apft=on|off
+
+ Where:
+
+ $model is the CPU model defined for the guest (defaults to the model of
+ the host system if not specified).
+
+ apft=on|off indicates whether the APFT facility is installed (on) or
+ not (off). The default for CPU models zEC12 and
+ newer is apft=on for older models, APFT will not be
+ installed.
+
+ If APFT is installed (apft=on) but AP facilities are not
+ (ap=off), an error message will be logged, but the guest
+ will be allowed to start. It makes no sense to have APFT
+ installed if the AP facilities are not; this is considered
+ an invalid configuration.
+
+ It also makes no sense to turn APFT off because the AP bus
+ running on the guest will not detect CEX4 and newer devices
+ without it. Since only CEX4 and newer devices are supported
+ for guest usage, no AP devices can be made accessible to a
+ guest started without APFT installed.
+
+Example: Configure AP Matrixes for Three Linux Guests:
+=====================================================
+Let's now provide an example to illustrate how KVM guests may be given
+access to AP facilities. For this example, we will show how to configure
+three guests such that executing the lszcrypt command on the guests would
+look like this:
+
+Guest1
+------
+CARD.DOMAIN TYPE MODE
+------------------------------
+05 CEX5C CCA-Coproc
+05.0004 CEX5C CCA-Coproc
+05.00ab CEX5C CCA-Coproc
+06 CEX5A Accelerator
+06.0004 CEX5A Accelerator
+06.00ab CEX5C CCA-Coproc
+
+Guest2
+------
+CARD.DOMAIN TYPE MODE
+------------------------------
+05 CEX5A Accelerator
+05.0047 CEX5A Accelerator
+05.00ff CEX5A Accelerator (5,4), (5,171), (6,4), (6,171),
+
+Guest3
+------
+CARD.DOMAIN TYPE MODE
+------------------------------
+06 CEX5A Accelerator
+06.0047 CEX5A Accelerator
+06.00ff CEX5A Accelerator
+
+These are the steps:
+
+1. Install the vfio_ap module on the linux host. The dependency chain for the
+ vfio_ap module is:
+ * iommu
+ * s390
+ * zcrypt
+ * vfio
+ * vfio_mdev
+ * vfio_mdev_device
+ * KVM
+
+ To build the vfio_ap module, the kernel build must be configured with the
+ following Kconfig elements selected:
+ * IOMMU_SUPPORT
+ * S390
+ * ZCRYPT
+ * S390_AP_IOMMU
+ * VFIO
+ * VFIO_MDEV
+ * VFIO_MDEV_DEVICE
+ * KVM
+
+ If using make menuconfig select the following to build the vfio_ap module:
+ -> Device Drivers
+ -> IOMMU Hardware Support
+ select S390 AP IOMMU Support
+ -> VFIO Non-Privileged userspace driver framework
+ -> Mediated device driver frramework
+ -> VFIO driver for Mediated devices
+ -> I/O subsystem
+ -> VFIO support for AP devices
+
+2. Secure the AP queues to be used by the three guests so that the host can not
+ access them. To secure the AP queues 05.0004, 05.0047, 05.00ab, 05.00ff,
+ 06.0004, 06.0047, 06.00ab, and 06.00ff for use by the vfio_ap device driver,
+ the corresponding APQNs must be removed from the default queue drivers pool
+ as follows:
+
+ echo -5,-6 > /sys/bus/ap/apmask
+
+ echo -4,-0x47,-0xab,-0xff > /sys/bus/ap/aqmask
+
+ This will result in AP queues 05.0004, 05.0047, 05.00ab, 05.00ff, 06.0004,
+ 06.0047, 06.00ab, and 06.00ff getting bound to the vfio_ap device driver. The
+ sysfs directory for the vfio_ap device driver will now contain symbolic links
+ to the AP queue devices bound to it:
+
+ /sys/bus/ap
+ ... [drivers]
+ ...... [vfio_ap]
+ ......... [05.0004]
+ ......... [05.0047]
+ ......... [05.00ab]
+ ......... [05.00ff]
+ ......... [06.0004]
+ ......... [06.0047]
+ ......... [06.00ab]
+ ......... [06.00ff]
+
+ Keep in mind that only type 10 and newer adapters (i.e., CEX4 and later)
+ can be bound to the vfio_ap device driver. The reason for this is to
+ simplify the implementation by not needlessly complicating the design by
+ supporting older devices that will go out of service in the relatively near
+ future, and for which there are few older systems on which to test.
+
+ The administrator, therefore, must take care to secure only AP queues that
+ can be bound to the vfio_ap device driver. The device type for a given AP
+ queue device can be read from the parent card's sysfs directory. For example,
+ to see the hardware type of the queue 05.0004:
+
+ cat /sys/bus/ap/devices/card05/hwtype
+
+ The hwtype must be 10 or higher (CEX4 or newer) in order to be bound to the
+ vfio_ap device driver.
+
+3. Create the mediated devices needed to configure the AP matrixes for the
+ three guests and to provide an interface to the vfio_ap driver for
+ use by the guests:
+
+ /sys/devices/vfio_ap/matrix/
+ --- [mdev_supported_types]
+ ------ [vfio_ap-passthrough] (passthrough mediated matrix device type)
+ --------- create
+ --------- [devices]
+
+ To create the mediated devices for the three guests:
+
+ uuidgen > create
+ uuidgen > create
+ uuidgen > create
+
+ or
+
+ echo $uuid1 > create
+ echo $uuid2 > create
+ echo $uuid3 > create
+
+ This will create three mediated devices in the [devices] subdirectory named
+ after the UUID used to create the mediated device. We'll call them $uuid1,
+ $uuid2 and $uuid3 and this is the sysfs directory structure after creation:
+
+ /sys/devices/vfio_ap/matrix/
+ --- [mdev_supported_types]
+ ------ [vfio_ap-passthrough]
+ --------- [devices]
+ ------------ [$uuid1]
+ --------------- assign_adapter
+ --------------- assign_control_domain
+ --------------- assign_domain
+ --------------- matrix
+ --------------- unassign_adapter
+ --------------- unassign_control_domain
+ --------------- unassign_domain
+
+ ------------ [$uuid2]
+ --------------- assign_adapter
+ --------------- assign_control_domain
+ --------------- assign_domain
+ --------------- matrix
+ --------------- unassign_adapter
+ ----------------unassign_control_domain
+ ----------------unassign_domain
+
+ ------------ [$uuid3]
+ --------------- assign_adapter
+ --------------- assign_control_domain
+ --------------- assign_domain
+ --------------- matrix
+ --------------- unassign_adapter
+ ----------------unassign_control_domain
+ ----------------unassign_domain
+
+4. The administrator now needs to configure the matrixes for the mediated
+ devices $uuid1 (for Guest1), $uuid2 (for Guest2) and $uuid3 (for Guest3).
+
+ This is how the matrix is configured for Guest1:
+
+ echo 5 > assign_adapter
+ echo 6 > assign_adapter
+ echo 4 > assign_domain
+ echo 0xab > assign_domain
+
+ Control domains can similarly be assigned using the assign_control_domain
+ sysfs file.
+
+ If a mistake is made configuring an adapter, domain or control domain,
+ you can use the unassign_xxx interfaces to unassign the adapter, domain or
+ control domain.
+
+ To display the matrix configuration for Guest1:
+
+ cat matrix
+
+ The output will display the APQNs in the format xx.yyyy, where xx is
+ the adapter number and yyyy is the domain number. The output for Guest1
+ will look like this:
+
+ 05.0004
+ 05.00ab
+ 06.0004
+ 06.00ab
+
+ This is how the matrix is configured for Guest2:
+
+ echo 5 > assign_adapter
+ echo 0x47 > assign_domain
+ echo 0xff > assign_domain
+
+ This is how the matrix is configured for Guest3:
+
+ echo 6 > assign_adapter
+ echo 0x47 > assign_domain
+ echo 0xff > assign_domain
+
+5. Start Guest1:
+
+ /usr/bin/qemu-system-s390x ... -cpu host,ap=on,apqci=on,apft=on \
+ -device vfio-ap,sysfsdev=/sys/devices/vfio_ap/matrix/$uuid1 ...
+
+7. Start Guest2:
+
+ /usr/bin/qemu-system-s390x ... -cpu host,ap=on,apqci=on,apft=on \
+ -device vfio-ap,sysfsdev=/sys/devices/vfio_ap/matrix/$uuid2 ...
+
+7. Start Guest3:
+
+ /usr/bin/qemu-system-s390x ... -cpu host,ap=on,apqci=on,apft=on \
+ -device vfio-ap,sysfsdev=/sys/devices/vfio_ap/matrix/$uuid3 ...
+
+When the guest is shut down, the mediated matrix devices may be removed.
+
+Using our example again, to remove the mediated matrix device $uuid1:
+
+ /sys/devices/vfio_ap/matrix/
+ --- [mdev_supported_types]
+ ------ [vfio_ap-passthrough]
+ --------- [devices]
+ ------------ [$uuid1]
+ --------------- remove
+
+
+ echo 1 > remove
+
+ This will remove all of the mdev matrix device's sysfs structures including
+ the mdev device itself. To recreate and reconfigure the mdev matrix device,
+ all of the steps starting with step 3 will have to be performed again. Note
+ that the remove will fail if a guest using the mdev is still running.
+
+ It is not necessary to remove an mdev matrix device, but one may want to
+ remove it if no guest will use it during the remaining lifetime of the linux
+ host. If the mdev matrix device is removed, one may want to also reconfigure
+ the pool of adapters and queues reserved for use by the default drivers.
+
+Limitations
+===========
+* The KVM/kernel interfaces do not provide a way to prevent restoring an APQN
+ to the default drivers pool of a queue that is still assigned to a mediated
+ device in use by a guest. It is incumbent upon the administrator to
+ ensure there is no mediated device in use by a guest to which the APQN is
+ assigned lest the host be given access to the private data of the AP queue
+ device, such as a private key configured specifically for the guest.
+
+* Dynamically modifying the AP matrix for a running guest (which would amount to
+ hot(un)plug of AP devices for the guest) is currently not supported
+
+* Live guest migration is not supported for guests using AP devices.
--
1.8.3.1

89
0075-vnc-call-sasl_server_init-only-when-required.patch Normal file
View File

@ -0,0 +1,89 @@
From dbf0257cf3587d5580765cbd2040f370820fb5e3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?= <marcandre.lureau@redhat.com>
Date: Tue, 2 Oct 2018 12:34:03 +0100
Subject: vnc: call sasl_server_init() only when required
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Marc-André Lureau <marcandre.lureau@redhat.com>
Message-id: <20181002123403.20747-2-marcandre.lureau@redhat.com>
Patchwork-id: 82356
O-Subject: [RHEL8/rhel qemu-kvm PATCH 1/1] vnc: call sasl_server_init() only when required
Bugzilla: 1609327
RH-Acked-by: Daniel P. Berrange <berrange@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Danilo de Paula <ddepaula@redhat.com>
VNC server is calling sasl_server_init() during startup of QEMU, even
if SASL auth has not been enabled.
This may create undesirable warnings like "Could not find keytab file:
/etc/qemu/krb5.tab" when the user didn't configure SASL on host and
started VNC server.
Instead, only initialize SASL when needed. Note that HMP/QMP "change
vnc" calls vnc_display_open() again, which will initialize SASL if
needed.
Fix assignment in if condition, while touching this code.
Related to:
https://bugzilla.redhat.com/show_bug.cgi?id=1609327
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: 20180907063634.359-1-marcandre.lureau@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit b5dc0d7d565048fcf2767060261d8385805aced1)
BZ: https://bugzilla.redhat.com/show_bug.cgi?id=1609327
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=18601393
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
Conflicts:
ui/vnc.c
Due to "qemu"->"qemu-kvm" rename.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
---
ui/vnc.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/ui/vnc.c b/ui/vnc.c
index 050c421..b3fe7d7 100644
--- a/ui/vnc.c
+++ b/ui/vnc.c
@@ -3878,9 +3878,6 @@ void vnc_display_open(const char *id, Error **errp)
bool reverse = false;
const char *credid;
bool sasl = false;
-#ifdef CONFIG_VNC_SASL
- int saslErr;
-#endif
int acl = 0;
int lock_key_sync = 1;
int key_delay_ms;
@@ -4054,10 +4051,14 @@ void vnc_display_open(const char *id, Error **errp)
trace_vnc_auth_init(vd, 1, vd->ws_auth, vd->ws_subauth);
#ifdef CONFIG_VNC_SASL
- if ((saslErr = sasl_server_init(NULL, "qemu-kvm")) != SASL_OK) {
- error_setg(errp, "Failed to initialize SASL auth: %s",
- sasl_errstring(saslErr, NULL, NULL));
- goto fail;
+ if (sasl) {
+ int saslErr = sasl_server_init(NULL, "qemu-kvm");
+
+ if (saslErr != SASL_OK) {
+ error_setg(errp, "Failed to initialize SASL auth: %s",
+ sasl_errstring(saslErr, NULL, NULL));
+ goto fail;
+ }
}
#endif
vd->lock_key_sync = lock_key_sync;
--
1.8.3.1

52
0076-nbd-server-fix-NBD_CMD_CACHE.patch Normal file
View File

@ -0,0 +1,52 @@
From c10de200e291af4a6a5cb41ac10e1ae7a2b9c5b2 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Wed, 10 Oct 2018 18:19:23 +0100
Subject: nbd/server: fix NBD_CMD_CACHE
RH-Author: John Snow <jsnow@redhat.com>
Message-id: <20181010181924.30470-2-jsnow@redhat.com>
Patchwork-id: 82576
O-Subject: [RHEL8/rhel qemu-kvm PATCH 1/2] nbd/server: fix NBD_CMD_CACHE
Bugzilla: 1636142
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Danilo de Paula <ddepaula@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
We should not go to structured-read branch on CACHE command, fix that.
Bug introduced in bc37b06a5cde24 "nbd/server: introduce NBD_CMD_CACHE"
with the whole feature and affects 3.0.0 release.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
CC: qemu-stable@nongnu.org
Message-Id: <20181003144738.70670-1-vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
[eblake: commit message typo fix]
Signed-off-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit 2f454defc23e1be78f2a96bad2877ce7829f61b4)
Signed-off-by: John Snow <jsnow@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
nbd/server.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/nbd/server.c b/nbd/server.c
index ea5fe0e..1ce3f44 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -2135,7 +2135,8 @@ static coroutine_fn int nbd_do_cmd_read(NBDClient *client, NBDRequest *request,
}
if (client->structured_reply && !(request->flags & NBD_CMD_FLAG_DF) &&
- request->len) {
+ request->len && request->type != NBD_CMD_CACHE)
+ {
return nbd_co_send_sparse_read(client, request->handle, request->from,
data, request->len, errp);
}
--
1.8.3.1

96
0077-nbd-fix-NBD_FLAG_SEND_CACHE-value.patch Normal file
View File

@ -0,0 +1,96 @@
From 24022cbbfd2230d4781a079d1856e0315895c8ce Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Wed, 10 Oct 2018 18:19:24 +0100
Subject: nbd: fix NBD_FLAG_SEND_CACHE value
RH-Author: John Snow <jsnow@redhat.com>
Message-id: <20181010181924.30470-3-jsnow@redhat.com>
Patchwork-id: 82578
O-Subject: [RHEL8/rhel qemu-kvm PATCH 2/2] nbd: fix NBD_FLAG_SEND_CACHE value
Bugzilla: 1636142
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Danilo de Paula <ddepaula@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: "Denis V. Lunev" <den@openvz.org>
Commit bc37b06a5 added NBD_CMD_CACHE support, but used the wrong value
for NBD_FLAG_SEND_CACHE flag for negotiation. That commit picked bit 8,
which had already been assigned by the NBD specification to mean
NBD_FLAG_CAN_MULTI_CONN, and which was already implemented in the
Linux kernel as a part of stable userspace-kernel API since 4.10:
"bit 8, NBD_FLAG_CAN_MULTI_CONN: Indicates that the server operates
entirely without cache, or that the cache it uses is shared among all
connections to the given device. In particular, if this flag is
present, then the effects of NBD_CMD_FLUSH and NBD_CMD_FLAG_FUA
MUST be visible across all connections when the server sends its reply
to that command to the client. In the absense of this flag, clients
SHOULD NOT multiplex their commands over more than one connection to
the export.
...
bit 10, NBD_FLAG_SEND_CACHE: documents that the server understands
NBD_CMD_CACHE; however, note that server implementations exist
which support the command without advertising this bit, and
conversely that this bit does not guarantee that the command will
succeed or have an impact."
Consequences:
- a client trying to use NBD_CMD_CACHE per the NBD spec will not
see the feature as available from a qemu 3.0 server (not fatal,
clients already have to be prepared for caching to not exist)
- a client accidentally coded to the qemu 3.0 bit value instead
of following the spec may interpret NBD_CMD_CACHE as being available
when it is not (probably not fatal, the spec says the server should
gracefully fail unknown commands, and that clients of NBD_CMD_CACHE
should be prepared for failure even when the feature is advertised);
such clients are unlikely (perhaps only in unreleased Virtuozzo code),
and will disappear over time
- a client prepared to use multiple connections based on
NBD_FLAG_CAN_MULTI_CONN may cause data corruption when it assumes
that caching is consistent when in reality qemu 3.0 did not have
a consistent cache. Partially mitigated by using read-only
connections (where nothing needs to be flushed, so caching is
indeed consistent) or when using qemu-nbd with the default -e 1
(at most one client at a time); visible only when using -e 2 or
more for a writable export.
Thus the commit fixes negotiation flag in QEMU according to the
specification.
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
CC: Valery Vdovin <valery.vdovin@acronis.com>
CC: Eric Blake <eblake@redhat.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: qemu-stable@nongnu.org
Message-Id: <20181004100313.4253-1-den@openvz.org>
Reviewed-by: Eric Blake <eblake@redhat.com>
[eblake: enhance commit message, add defines for unimplemented flags]
Signed-off-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit df91328adab8490367776d2b21b35d790a606120)
Signed-off-by: John Snow <jsnow@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
include/block/nbd.h | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/include/block/nbd.h b/include/block/nbd.h
index 4638c83..a53b0cf 100644
--- a/include/block/nbd.h
+++ b/include/block/nbd.h
@@ -135,7 +135,9 @@ typedef struct NBDExtent {
#define NBD_FLAG_SEND_TRIM (1 << 5) /* Send TRIM (discard) */
#define NBD_FLAG_SEND_WRITE_ZEROES (1 << 6) /* Send WRITE_ZEROES */
#define NBD_FLAG_SEND_DF (1 << 7) /* Send DF (Do not Fragment) */
-#define NBD_FLAG_SEND_CACHE (1 << 8) /* Send CACHE (prefetch) */
+#define NBD_FLAG_CAN_MULTI_CONN (1 << 8) /* Multi-client cache consistent */
+#define NBD_FLAG_SEND_RESIZE (1 << 9) /* Send resize */
+#define NBD_FLAG_SEND_CACHE (1 << 10) /* Send CACHE (prefetch) */
/* New-style handshake (global) flags, sent from server to client, and
control what will happen during handshake phase. */
--
1.8.3.1

134
0078-block-linux-aio-acquire-AioContext-before-qemu_laio_.patch Normal file
View File

@ -0,0 +1,134 @@
From ca570895f9825c8ed6691bb520341ac9e07bac5a Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:21:52 +0100
Subject: block/linux-aio: acquire AioContext before
qemu_laio_process_completions
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-14-kwolf@redhat.com>
Patchwork-id: 82603
O-Subject: [RHEL-8 qemu-kvm PATCH 23/44] block/linux-aio: acquire AioContext before qemu_laio_process_completions
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Sergio Lopez <slp@redhat.com>
In qemu_laio_process_completions_and_submit, the AioContext is acquired
before the ioq_submit iteration and after qemu_laio_process_completions,
but the latter is not thread safe either.
This change avoids a number of random crashes when the Main Thread and
an IO Thread collide processing completions for the same AioContext.
This is an example of such crash:
- The IO Thread is trying to acquire the AioContext at aio_co_enter,
which evidences that it didn't lock it before:
Thread 3 (Thread 0x7fdfd8bd8700 (LWP 36743)):
#0 0x00007fdfe0dd542d in __lll_lock_wait () at ../nptl/sysdeps/unix/sysv/linux/x86_64/lowlevellock.S:135
#1 0x00007fdfe0dd0de6 in _L_lock_870 () at /lib64/libpthread.so.0
#2 0x00007fdfe0dd0cdf in __GI___pthread_mutex_lock (mutex=mutex@entry=0x5631fde0e6c0)
at ../nptl/pthread_mutex_lock.c:114
#3 0x00005631fc0603a7 in qemu_mutex_lock_impl (mutex=0x5631fde0e6c0, file=0x5631fc23520f "util/async.c", line=511) at util/qemu-thread-posix.c:66
#4 0x00005631fc05b558 in aio_co_enter (ctx=0x5631fde0e660, co=0x7fdfcc0c2b40) at util/async.c:493
#5 0x00005631fc05b5ac in aio_co_wake (co=<optimized out>) at util/async.c:478
#6 0x00005631fbfc51ad in qemu_laio_process_completion (laiocb=<optimized out>) at block/linux-aio.c:104
#7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670)
at block/linux-aio.c:222
#8 0x00005631fbfc5499 in qemu_laio_process_completions_and_submit (s=0x7fdfc0297670)
at block/linux-aio.c:237
#9 0x00005631fc05d978 in aio_dispatch_handlers (ctx=ctx@entry=0x5631fde0e660) at util/aio-posix.c:406
#10 0x00005631fc05e3ea in aio_poll (ctx=0x5631fde0e660, blocking=blocking@entry=true)
at util/aio-posix.c:693
#11 0x00005631fbd7ad96 in iothread_run (opaque=0x5631fde0e1c0) at iothread.c:64
#12 0x00007fdfe0dcee25 in start_thread (arg=0x7fdfd8bd8700) at pthread_create.c:308
#13 0x00007fdfe0afc34d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:113
- The Main Thread is also processing completions from the same
AioContext, and crashes due to failed assertion at util/iov.c:78:
Thread 1 (Thread 0x7fdfeb5eac80 (LWP 36740)):
#0 0x00007fdfe0a391f7 in __GI_raise (sig=sig@entry=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:56
#1 0x00007fdfe0a3a8e8 in __GI_abort () at abort.c:90
#2 0x00007fdfe0a32266 in __assert_fail_base (fmt=0x7fdfe0b84e68 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n", assertion=assertion@entry=0x5631fc238ccb "offset == 0", file=file@entry=0x5631fc23698e "util/iov.c", line=line@entry=78, function=function@entry=0x5631fc236adc <__PRETTY_FUNCTION__.15220> "iov_memset")
at assert.c:92
#3 0x00007fdfe0a32312 in __GI___assert_fail (assertion=assertion@entry=0x5631fc238ccb "offset == 0", file=file@entry=0x5631fc23698e "util/iov.c", line=line@entry=78, function=function@entry=0x5631fc236adc <__PRETTY_FUNCTION__.15220> "iov_memset") at assert.c:101
#4 0x00005631fc065287 in iov_memset (iov=<optimized out>, iov_cnt=<optimized out>, offset=<optimized out>, offset@entry=65536, fillc=fillc@entry=0, bytes=15515191315812405248) at util/iov.c:78
#5 0x00005631fc065a63 in qemu_iovec_memset (qiov=<optimized out>, offset=offset@entry=65536, fillc=fillc@entry=0, bytes=<optimized out>) at util/iov.c:410
#6 0x00005631fbfc5178 in qemu_laio_process_completion (laiocb=0x7fdd920df630) at block/linux-aio.c:88
#7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670)
at block/linux-aio.c:222
#8 0x00005631fbfc5499 in qemu_laio_process_completions_and_submit (s=0x7fdfc0297670)
at block/linux-aio.c:237
#9 0x00005631fbfc54ed in qemu_laio_poll_cb (opaque=<optimized out>) at block/linux-aio.c:272
#10 0x00005631fc05d85e in run_poll_handlers_once (ctx=ctx@entry=0x5631fde0e660) at util/aio-posix.c:497
#11 0x00005631fc05e2ca in aio_poll (blocking=false, ctx=0x5631fde0e660) at util/aio-posix.c:574
#12 0x00005631fc05e2ca in aio_poll (ctx=0x5631fde0e660, blocking=blocking@entry=false)
at util/aio-posix.c:604
#13 0x00005631fbfcb8a3 in bdrv_do_drained_begin (ignore_parent=<optimized out>, recursive=<optimized out>, bs=<optimized out>) at block/io.c:273
#14 0x00005631fbfcb8a3 in bdrv_do_drained_begin (bs=0x5631fe8b6200, recursive=<optimized out>, parent=0x0, ignore_bds_parents=<optimized out>, poll=<optimized out>) at block/io.c:390
#15 0x00005631fbfbcd2e in blk_drain (blk=0x5631fe83ac80) at block/block-backend.c:1590
#16 0x00005631fbfbe138 in blk_remove_bs (blk=blk@entry=0x5631fe83ac80) at block/block-backend.c:774
#17 0x00005631fbfbe3d6 in blk_unref (blk=0x5631fe83ac80) at block/block-backend.c:401
#18 0x00005631fbfbe3d6 in blk_unref (blk=0x5631fe83ac80) at block/block-backend.c:449
#19 0x00005631fbfc9a69 in commit_complete (job=0x5631fe8b94b0, opaque=0x7fdfcc1bb080)
at block/commit.c:92
#20 0x00005631fbf7d662 in job_defer_to_main_loop_bh (opaque=0x7fdfcc1b4560) at job.c:973
#21 0x00005631fc05ad41 in aio_bh_poll (bh=0x7fdfcc01ad90) at util/async.c:90
#22 0x00005631fc05ad41 in aio_bh_poll (ctx=ctx@entry=0x5631fddffdb0) at util/async.c:118
#23 0x00005631fc05e210 in aio_dispatch (ctx=0x5631fddffdb0) at util/aio-posix.c:436
#24 0x00005631fc05ac1e in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) at util/async.c:261
#25 0x00007fdfeaae44c9 in g_main_context_dispatch (context=0x5631fde00140) at gmain.c:3201
#26 0x00007fdfeaae44c9 in g_main_context_dispatch (context=context@entry=0x5631fde00140) at gmain.c:3854
#27 0x00005631fc05d503 in main_loop_wait () at util/main-loop.c:215
#28 0x00005631fc05d503 in main_loop_wait (timeout=<optimized out>) at util/main-loop.c:238
#29 0x00005631fc05d503 in main_loop_wait (nonblocking=nonblocking@entry=0) at util/main-loop.c:497
#30 0x00005631fbd81412 in main_loop () at vl.c:1866
#31 0x00005631fbc18ff3 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>)
at vl.c:4647
- A closer examination shows that s->io_q.in_flight appears to have
gone backwards:
(gdb) frame 7
#7 0x00005631fbfc523c in qemu_laio_process_completions (s=s@entry=0x7fdfc0297670)
at block/linux-aio.c:222
222 qemu_laio_process_completion(laiocb);
(gdb) p s
$2 = (LinuxAioState *) 0x7fdfc0297670
(gdb) p *s
$3 = {aio_context = 0x5631fde0e660, ctx = 0x7fdfeb43b000, e = {rfd = 33, wfd = 33}, io_q = {plugged = 0,
in_queue = 0, in_flight = 4294967280, blocked = false, pending = {sqh_first = 0x0,
sqh_last = 0x7fdfc0297698}}, completion_bh = 0x7fdfc0280ef0, event_idx = 21, event_max = 241}
(gdb) p/x s->io_q.in_flight
$4 = 0xfffffff0
Signed-off-by: Sergio Lopez <slp@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit e091f0e905a4481f347913420f327d427f18d9d4)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/linux-aio.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/block/linux-aio.c b/block/linux-aio.c
index 19eb922..217ce60 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -234,9 +234,9 @@ static void qemu_laio_process_completions(LinuxAioState *s)
static void qemu_laio_process_completions_and_submit(LinuxAioState *s)
{
+ aio_context_acquire(s->aio_context);
qemu_laio_process_completions(s);
- aio_context_acquire(s->aio_context);
if (!s->io_q.plugged && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
ioq_submit(s);
}
--
1.8.3.1

78
0079-util-async-use-qemu_aio_coroutine_enter-in-co_schedu.patch Normal file
View File

@ -0,0 +1,78 @@
From faa3d5106cb296858227cc240e045ca16cb28c81 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:21:53 +0100
Subject: util/async: use qemu_aio_coroutine_enter in co_schedule_bh_cb
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-15-kwolf@redhat.com>
Patchwork-id: 82604
O-Subject: [RHEL-8 qemu-kvm PATCH 24/44] util/async: use qemu_aio_coroutine_enter in co_schedule_bh_cb
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Sergio Lopez <slp@redhat.com>
AIO Coroutines shouldn't by managed by an AioContext different than the
one assigned when they are created. aio_co_enter avoids entering a
coroutine from a different AioContext, calling aio_co_schedule instead.
Scheduled coroutines are then entered by co_schedule_bh_cb using
qemu_coroutine_enter, which just calls qemu_aio_coroutine_enter with the
current AioContext obtained with qemu_get_current_aio_context.
Eventually, co->ctx will be set to the AioContext passed as an argument
to qemu_aio_coroutine_enter.
This means that, if an IO Thread's AioConext is being processed by the
Main Thread (due to aio_poll being called with a BDS AioContext, as it
happens in AIO_WAIT_WHILE among other places), the AioContext from some
coroutines may be wrongly replaced with the one from the Main Thread.
This is the root cause behind some crashes, mainly triggered by the
drain code at block/io.c. The most common are these abort and failed
assertion:
util/async.c:aio_co_schedule
456 if (scheduled) {
457 fprintf(stderr,
458 "%s: Co-routine was already scheduled in '%s'\n",
459 __func__, scheduled);
460 abort();
461 }
util/qemu-coroutine-lock.c:
286 assert(mutex->holder == self);
But it's also known to cause random errors at different locations, and
even SIGSEGV with broken coroutine backtraces.
By using qemu_aio_coroutine_enter directly in co_schedule_bh_cb, we can
pass the correct AioContext as an argument, making sure co->ctx is not
wrongly altered.
Signed-off-by: Sergio Lopez <slp@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 6808ae0417131f8dbe7b051256dff7a16634dc1d)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
util/async.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/util/async.c b/util/async.c
index 05979f8..c10642a 100644
--- a/util/async.c
+++ b/util/async.c
@@ -400,7 +400,7 @@ static void co_schedule_bh_cb(void *opaque)
/* Protected by write barrier in qemu_aio_coroutine_enter */
atomic_set(&co->scheduled, NULL);
- qemu_coroutine_enter(co);
+ qemu_aio_coroutine_enter(ctx, co);
aio_context_release(ctx);
}
}
--
1.8.3.1

105
0080-job-Fix-nested-aio_poll-hanging-in-job_txn_apply.patch Normal file
View File

@ -0,0 +1,105 @@
From f78998e365809f77ed146ee2afdcf132b12c838c Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:21:54 +0100
Subject: job: Fix nested aio_poll() hanging in job_txn_apply
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-16-kwolf@redhat.com>
Patchwork-id: 82605
O-Subject: [RHEL-8 qemu-kvm PATCH 25/44] job: Fix nested aio_poll() hanging in job_txn_apply
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Fam Zheng <famz@redhat.com>
All callers have acquired ctx already. Doing that again results in
aio_poll() hang. This fixes the problem that a BDRV_POLL_WHILE() in the
callback cannot make progress because ctx is recursively locked, for
example, when drive-backup finishes.
There are two callers of job_finalize():
fam@lemon:~/work/qemu [master]$ git grep -w -A1 '^\s*job_finalize'
blockdev.c: job_finalize(&job->job, errp);
blockdev.c- aio_context_release(aio_context);
--
job-qmp.c: job_finalize(job, errp);
job-qmp.c- aio_context_release(aio_context);
--
tests/test-blockjob.c: job_finalize(&job->job, &error_abort);
tests/test-blockjob.c- assert(job->job.status == JOB_STATUS_CONCLUDED);
Ignoring the test, it's easy to see both callers to job_finalize (and
job_do_finalize) have acquired the context.
Cc: qemu-stable@nongnu.org
Reported-by: Gu Nini <ngu@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 49880165a44f26dc84651858750facdee31f2513)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
job.c | 18 +++++-------------
1 file changed, 5 insertions(+), 13 deletions(-)
diff --git a/job.c b/job.c
index bb322de..82b4692 100644
--- a/job.c
+++ b/job.c
@@ -136,21 +136,13 @@ static void job_txn_del_job(Job *job)
}
}
-static int job_txn_apply(JobTxn *txn, int fn(Job *), bool lock)
+static int job_txn_apply(JobTxn *txn, int fn(Job *))
{
- AioContext *ctx;
Job *job, *next;
int rc = 0;
QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) {
- if (lock) {
- ctx = job->aio_context;
- aio_context_acquire(ctx);
- }
rc = fn(job);
- if (lock) {
- aio_context_release(ctx);
- }
if (rc) {
break;
}
@@ -780,11 +772,11 @@ static void job_do_finalize(Job *job)
assert(job && job->txn);
/* prepare the transaction to complete */
- rc = job_txn_apply(job->txn, job_prepare, true);
+ rc = job_txn_apply(job->txn, job_prepare);
if (rc) {
job_completed_txn_abort(job);
} else {
- job_txn_apply(job->txn, job_finalize_single, true);
+ job_txn_apply(job->txn, job_finalize_single);
}
}
@@ -830,10 +822,10 @@ static void job_completed_txn_success(Job *job)
assert(other_job->ret == 0);
}
- job_txn_apply(txn, job_transition_to_pending, false);
+ job_txn_apply(txn, job_transition_to_pending);
/* If no jobs need manual finalization, automatically do so */
- if (job_txn_apply(txn, job_needs_finalize, false) == 0) {
+ if (job_txn_apply(txn, job_needs_finalize) == 0) {
job_do_finalize(job);
}
}
--
1.8.3.1

55
0081-job-Fix-missing-locking-due-to-mismerge.patch Normal file
View File

@ -0,0 +1,55 @@
From bb58f00a6c09bd1fe9af6dabe9ea173adc406d7b Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:21:55 +0100
Subject: job: Fix missing locking due to mismerge
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-17-kwolf@redhat.com>
Patchwork-id: 82607
O-Subject: [RHEL-8 qemu-kvm PATCH 26/44] job: Fix missing locking due to mismerge
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
job_completed() had a problem with double locking that was recently
fixed independently by two different commits:
"job: Fix nested aio_poll() hanging in job_txn_apply"
"jobs: add exit shim"
One fix removed the first aio_context_acquire(), the other fix removed
the other one. Now we have a bug again and the code is run without any
locking.
Add it back in one of the places.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
(cherry picked from commit d1756c780b7879fb64e41135feac781d84a1f995)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
job.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/job.c b/job.c
index 82b4692..5c4e84f 100644
--- a/job.c
+++ b/job.c
@@ -847,7 +847,11 @@ static void job_completed(Job *job)
static void job_exit(void *opaque)
{
Job *job = (Job *)opaque;
+ AioContext *ctx = job->aio_context;
+
+ aio_context_acquire(ctx);
job_completed(job);
+ aio_context_release(ctx);
}
/**
--
1.8.3.1

161
0082-blockjob-Wake-up-BDS-when-job-becomes-idle.patch Normal file
View File

@ -0,0 +1,161 @@
From ac751d8909fa4b734fab48e27c0213df48ffd76b Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:21:56 +0100
Subject: blockjob: Wake up BDS when job becomes idle
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-18-kwolf@redhat.com>
Patchwork-id: 82610
O-Subject: [RHEL-8 qemu-kvm PATCH 27/44] blockjob: Wake up BDS when job becomes idle
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
In the context of draining a BDS, the .drained_poll callback of block
jobs is called. If this returns true (i.e. there is still some activity
pending), the drain operation may call aio_poll() with blocking=true to
wait for completion.
As soon as the pending activity is completed and the job finally arrives
in a quiescent state (i.e. its coroutine either yields with busy=false
or terminates), the block job must notify the aio_poll() loop to wake
up, otherwise we get a deadlock if both are running in different
threads.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit 34dc97b9a0e592bc466bdb0bbfe45d77304a72b6)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
blockjob.c | 18 ++++++++++++++++++
include/block/blockjob.h | 13 +++++++++++++
include/qemu/job.h | 3 +++
job.c | 7 +++++++
4 files changed, 41 insertions(+)
diff --git a/blockjob.c b/blockjob.c
index be5903a..8d27e8e 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -221,6 +221,22 @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
return 0;
}
+void block_job_wakeup_all_bdrv(BlockJob *job)
+{
+ GSList *l;
+
+ for (l = job->nodes; l; l = l->next) {
+ BdrvChild *c = l->data;
+ bdrv_wakeup(c->bs);
+ }
+}
+
+static void block_job_on_idle(Notifier *n, void *opaque)
+{
+ BlockJob *job = opaque;
+ block_job_wakeup_all_bdrv(job);
+}
+
bool block_job_is_internal(BlockJob *job)
{
return (job->job.id == NULL);
@@ -419,6 +435,7 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
job->finalize_completed_notifier.notify = block_job_event_completed;
job->pending_notifier.notify = block_job_event_pending;
job->ready_notifier.notify = block_job_event_ready;
+ job->idle_notifier.notify = block_job_on_idle;
notifier_list_add(&job->job.on_finalize_cancelled,
&job->finalize_cancelled_notifier);
@@ -426,6 +443,7 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
&job->finalize_completed_notifier);
notifier_list_add(&job->job.on_pending, &job->pending_notifier);
notifier_list_add(&job->job.on_ready, &job->ready_notifier);
+ notifier_list_add(&job->job.on_idle, &job->idle_notifier);
error_setg(&job->blocker, "block device is in use by block job: %s",
job_type_str(&job->job));
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index 32c00b7..2290bbb 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -70,6 +70,9 @@ typedef struct BlockJob {
/** Called when the job transitions to READY */
Notifier ready_notifier;
+ /** Called when the job coroutine yields or terminates */
+ Notifier idle_notifier;
+
/** BlockDriverStates that are involved in this block job */
GSList *nodes;
} BlockJob;
@@ -119,6 +122,16 @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
void block_job_remove_all_bdrv(BlockJob *job);
/**
+ * block_job_wakeup_all_bdrv:
+ * @job: The block job
+ *
+ * Calls bdrv_wakeup() for all BlockDriverStates that have been added to the
+ * job. This function is to be called whenever child_job_drained_poll() would
+ * go from true to false to notify waiting drain requests.
+ */
+void block_job_wakeup_all_bdrv(BlockJob *job);
+
+/**
* block_job_set_speed:
* @job: The job to set the speed for.
* @speed: The new value
diff --git a/include/qemu/job.h b/include/qemu/job.h
index 5cb0681..b4a784d 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -156,6 +156,9 @@ typedef struct Job {
/** Notifiers called when the job transitions to READY */
NotifierList on_ready;
+ /** Notifiers called when the job coroutine yields or terminates */
+ NotifierList on_idle;
+
/** Element of the list of jobs */
QLIST_ENTRY(Job) job_list;
diff --git a/job.c b/job.c
index 5c4e84f..48a767c 100644
--- a/job.c
+++ b/job.c
@@ -402,6 +402,11 @@ static void job_event_ready(Job *job)
notifier_list_notify(&job->on_ready, job);
}
+static void job_event_idle(Job *job)
+{
+ notifier_list_notify(&job->on_idle, job);
+}
+
void job_enter_cond(Job *job, bool(*fn)(Job *job))
{
if (!job_started(job)) {
@@ -447,6 +452,7 @@ static void coroutine_fn job_do_yield(Job *job, uint64_t ns)
timer_mod(&job->sleep_timer, ns);
}
job->busy = false;
+ job_event_idle(job);
job_unlock();
qemu_coroutine_yield();
@@ -865,6 +871,7 @@ static void coroutine_fn job_co_entry(void *opaque)
assert(job && job->driver && job->driver->run);
job_pause_point(job);
job->ret = job->driver->run(job, &job->err);
+ job_event_idle(job);
job->deferred_to_main_loop = true;
aio_bh_schedule_oneshot(qemu_get_aio_context(), job_exit, job);
}
--
1.8.3.1

64
0083-aio-wait-Increase-num_waiters-even-in-home-thread.patch Normal file
View File

@ -0,0 +1,64 @@
From 0e651f939d3fd65071a8edc8090a777bdb45b921 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:21:57 +0100
Subject: aio-wait: Increase num_waiters even in home thread
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-19-kwolf@redhat.com>
Patchwork-id: 82609
O-Subject: [RHEL-8 qemu-kvm PATCH 28/44] aio-wait: Increase num_waiters even in home thread
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
Even if AIO_WAIT_WHILE() is called in the home context of the
AioContext, we still want to allow the condition to change depending on
other threads as long as they kick the AioWait. Specfically block jobs
can be running in an I/O thread and should then be able to kick a drain
in the main loop context.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit 486574483aba988c83b20e7d3f1ccd50c4c333d8)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
include/block/aio-wait.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index c85a62f..600fad1 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -76,6 +76,8 @@ typedef struct {
bool waited_ = false; \
AioWait *wait_ = (wait); \
AioContext *ctx_ = (ctx); \
+ /* Increment wait_->num_waiters before evaluating cond. */ \
+ atomic_inc(&wait_->num_waiters); \
if (ctx_ && in_aio_context_home_thread(ctx_)) { \
while ((cond)) { \
aio_poll(ctx_, true); \
@@ -84,8 +86,6 @@ typedef struct {
} else { \
assert(qemu_get_current_aio_context() == \
qemu_get_aio_context()); \
- /* Increment wait_->num_waiters before evaluating cond. */ \
- atomic_inc(&wait_->num_waiters); \
while ((cond)) { \
if (ctx_) { \
aio_context_release(ctx_); \
@@ -96,8 +96,8 @@ typedef struct {
} \
waited_ = true; \
} \
- atomic_dec(&wait_->num_waiters); \
} \
+ atomic_dec(&wait_->num_waiters); \
waited_; })
/**
--
1.8.3.1

208
0084-test-bdrv-drain-Drain-with-block-jobs-in-an-I-O-thre.patch Normal file
View File

@ -0,0 +1,208 @@
From 6d374393478f0d57ec8cd338342687d043565662 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:21:58 +0100
Subject: test-bdrv-drain: Drain with block jobs in an I/O thread
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-20-kwolf@redhat.com>
Patchwork-id: 82608
O-Subject: [RHEL-8 qemu-kvm PATCH 29/44] test-bdrv-drain: Drain with block jobs in an I/O thread
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
This extends the existing drain test with a block job to include
variants where the block job runs in a different AioContext.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit f62c172959cd2b6de4dd8ba782e855d64d94764b)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
tests/test-bdrv-drain.c | 92 +++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 86 insertions(+), 6 deletions(-)
diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c
index 9bcb3c7..3cf3ba3 100644
--- a/tests/test-bdrv-drain.c
+++ b/tests/test-bdrv-drain.c
@@ -174,6 +174,28 @@ static void do_drain_end(enum drain_type drain_type, BlockDriverState *bs)
}
}
+static void do_drain_begin_unlocked(enum drain_type drain_type, BlockDriverState *bs)
+{
+ if (drain_type != BDRV_DRAIN_ALL) {
+ aio_context_acquire(bdrv_get_aio_context(bs));
+ }
+ do_drain_begin(drain_type, bs);
+ if (drain_type != BDRV_DRAIN_ALL) {
+ aio_context_release(bdrv_get_aio_context(bs));
+ }
+}
+
+static void do_drain_end_unlocked(enum drain_type drain_type, BlockDriverState *bs)
+{
+ if (drain_type != BDRV_DRAIN_ALL) {
+ aio_context_acquire(bdrv_get_aio_context(bs));
+ }
+ do_drain_end(drain_type, bs);
+ if (drain_type != BDRV_DRAIN_ALL) {
+ aio_context_release(bdrv_get_aio_context(bs));
+ }
+}
+
static void test_drv_cb_common(enum drain_type drain_type, bool recursive)
{
BlockBackend *blk;
@@ -785,11 +807,13 @@ BlockJobDriver test_job_driver = {
},
};
-static void test_blockjob_common(enum drain_type drain_type)
+static void test_blockjob_common(enum drain_type drain_type, bool use_iothread)
{
BlockBackend *blk_src, *blk_target;
BlockDriverState *src, *target;
BlockJob *job;
+ IOThread *iothread = NULL;
+ AioContext *ctx;
int ret;
src = bdrv_new_open_driver(&bdrv_test, "source", BDRV_O_RDWR,
@@ -797,21 +821,31 @@ static void test_blockjob_common(enum drain_type drain_type)
blk_src = blk_new(BLK_PERM_ALL, BLK_PERM_ALL);
blk_insert_bs(blk_src, src, &error_abort);
+ if (use_iothread) {
+ iothread = iothread_new();
+ ctx = iothread_get_aio_context(iothread);
+ blk_set_aio_context(blk_src, ctx);
+ } else {
+ ctx = qemu_get_aio_context();
+ }
+
target = bdrv_new_open_driver(&bdrv_test, "target", BDRV_O_RDWR,
&error_abort);
blk_target = blk_new(BLK_PERM_ALL, BLK_PERM_ALL);
blk_insert_bs(blk_target, target, &error_abort);
+ aio_context_acquire(ctx);
job = block_job_create("job0", &test_job_driver, NULL, src, 0, BLK_PERM_ALL,
0, 0, NULL, NULL, &error_abort);
block_job_add_bdrv(job, "target", target, 0, BLK_PERM_ALL, &error_abort);
job_start(&job->job);
+ aio_context_release(ctx);
g_assert_cmpint(job->job.pause_count, ==, 0);
g_assert_false(job->job.paused);
g_assert_true(job->job.busy); /* We're in job_sleep_ns() */
- do_drain_begin(drain_type, src);
+ do_drain_begin_unlocked(drain_type, src);
if (drain_type == BDRV_DRAIN_ALL) {
/* bdrv_drain_all() drains both src and target */
@@ -822,7 +856,14 @@ static void test_blockjob_common(enum drain_type drain_type)
g_assert_true(job->job.paused);
g_assert_false(job->job.busy); /* The job is paused */
- do_drain_end(drain_type, src);
+ do_drain_end_unlocked(drain_type, src);
+
+ if (use_iothread) {
+ /* paused is reset in the I/O thread, wait for it */
+ while (job->job.paused) {
+ aio_poll(qemu_get_aio_context(), false);
+ }
+ }
g_assert_cmpint(job->job.pause_count, ==, 0);
g_assert_false(job->job.paused);
@@ -841,32 +882,64 @@ static void test_blockjob_common(enum drain_type drain_type)
do_drain_end(drain_type, target);
+ if (use_iothread) {
+ /* paused is reset in the I/O thread, wait for it */
+ while (job->job.paused) {
+ aio_poll(qemu_get_aio_context(), false);
+ }
+ }
+
g_assert_cmpint(job->job.pause_count, ==, 0);
g_assert_false(job->job.paused);
g_assert_true(job->job.busy); /* We're in job_sleep_ns() */
+ aio_context_acquire(ctx);
ret = job_complete_sync(&job->job, &error_abort);
g_assert_cmpint(ret, ==, 0);
+ if (use_iothread) {
+ blk_set_aio_context(blk_src, qemu_get_aio_context());
+ }
+ aio_context_release(ctx);
+
blk_unref(blk_src);
blk_unref(blk_target);
bdrv_unref(src);
bdrv_unref(target);
+
+ if (iothread) {
+ iothread_join(iothread);
+ }
}
static void test_blockjob_drain_all(void)
{
- test_blockjob_common(BDRV_DRAIN_ALL);
+ test_blockjob_common(BDRV_DRAIN_ALL, false);
}
static void test_blockjob_drain(void)
{
- test_blockjob_common(BDRV_DRAIN);
+ test_blockjob_common(BDRV_DRAIN, false);
}
static void test_blockjob_drain_subtree(void)
{
- test_blockjob_common(BDRV_SUBTREE_DRAIN);
+ test_blockjob_common(BDRV_SUBTREE_DRAIN, false);
+}
+
+static void test_blockjob_iothread_drain_all(void)
+{
+ test_blockjob_common(BDRV_DRAIN_ALL, true);
+}
+
+static void test_blockjob_iothread_drain(void)
+{
+ test_blockjob_common(BDRV_DRAIN, true);
+}
+
+static void test_blockjob_iothread_drain_subtree(void)
+{
+ test_blockjob_common(BDRV_SUBTREE_DRAIN, true);
}
@@ -1337,6 +1410,13 @@ int main(int argc, char **argv)
g_test_add_func("/bdrv-drain/blockjob/drain_subtree",
test_blockjob_drain_subtree);
+ g_test_add_func("/bdrv-drain/blockjob/iothread/drain_all",
+ test_blockjob_iothread_drain_all);
+ g_test_add_func("/bdrv-drain/blockjob/iothread/drain",
+ test_blockjob_iothread_drain);
+ g_test_add_func("/bdrv-drain/blockjob/iothread/drain_subtree",
+ test_blockjob_iothread_drain_subtree);
+
g_test_add_func("/bdrv-drain/deletion/drain", test_delete_by_drain);
g_test_add_func("/bdrv-drain/detach/drain_all", test_detach_by_drain_all);
g_test_add_func("/bdrv-drain/detach/drain", test_detach_by_drain);
--
1.8.3.1

86
0085-test-blockjob-Acquire-AioContext-around-job_cancel_s.patch Normal file
View File

@ -0,0 +1,86 @@
From 99172abebcedfb48ca06d4c1bd0cd16372449600 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:21:59 +0100
Subject: test-blockjob: Acquire AioContext around job_cancel_sync()
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-21-kwolf@redhat.com>
Patchwork-id: 82606
O-Subject: [RHEL-8 qemu-kvm PATCH 30/44] test-blockjob: Acquire AioContext around job_cancel_sync()
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
All callers in QEMU proper hold the AioContext lock when calling
job_finish_sync(). test-blockjob should do the same when it calls the
function indirectly through job_cancel_sync().
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit 30c070a547322a5e41ce129d540bca3653b1a9c8)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
include/qemu/job.h | 6 ++++++
tests/test-blockjob.c | 6 ++++++
2 files changed, 12 insertions(+)
diff --git a/include/qemu/job.h b/include/qemu/job.h
index b4a784d..63c60ef 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -524,6 +524,8 @@ void job_user_cancel(Job *job, bool force, Error **errp);
*
* Returns the return value from the job if the job actually completed
* during the call, or -ECANCELED if it was canceled.
+ *
+ * Callers must hold the AioContext lock of job->aio_context.
*/
int job_cancel_sync(Job *job);
@@ -541,6 +543,8 @@ void job_cancel_sync_all(void);
* function).
*
* Returns the return value from the job.
+ *
+ * Callers must hold the AioContext lock of job->aio_context.
*/
int job_complete_sync(Job *job, Error **errp);
@@ -566,6 +570,8 @@ void job_dismiss(Job **job, Error **errp);
*
* Returns 0 if the job is successfully completed, -ECANCELED if the job was
* cancelled before completing, and -errno in other error cases.
+ *
+ * Callers must hold the AioContext lock of job->aio_context.
*/
int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp);
diff --git a/tests/test-blockjob.c b/tests/test-blockjob.c
index de4c1c2..652d1e8 100644
--- a/tests/test-blockjob.c
+++ b/tests/test-blockjob.c
@@ -223,6 +223,10 @@ static void cancel_common(CancelJob *s)
BlockJob *job = &s->common;
BlockBackend *blk = s->blk;
JobStatus sts = job->job.status;
+ AioContext *ctx;
+
+ ctx = job->job.aio_context;
+ aio_context_acquire(ctx);
job_cancel_sync(&job->job);
if (sts != JOB_STATUS_CREATED && sts != JOB_STATUS_CONCLUDED) {
@@ -232,6 +236,8 @@ static void cancel_common(CancelJob *s)
assert(job->job.status == JOB_STATUS_NULL);
job_unref(&job->job);
destroy_blk(blk);
+
+ aio_context_release(ctx);
}
static void test_cancel_created(void)
--
1.8.3.1

77
0086-job-Use-AIO_WAIT_WHILE-in-job_finish_sync.patch Normal file
View File

@ -0,0 +1,77 @@
From 3f3282c8ffa29e3dbcf58618beefb36afe8ba79b Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:00 +0100
Subject: job: Use AIO_WAIT_WHILE() in job_finish_sync()
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-22-kwolf@redhat.com>
Patchwork-id: 82612
O-Subject: [RHEL-8 qemu-kvm PATCH 31/44] job: Use AIO_WAIT_WHILE() in job_finish_sync()
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
job_finish_sync() needs to release the AioContext lock of the job before
calling aio_poll(). Otherwise, callbacks called by aio_poll() would
possibly take the lock a second time and run into a deadlock with a
nested AIO_WAIT_WHILE() call.
Also, job_drain() without aio_poll() isn't necessarily enough to make
progress on a job, it could depend on bottom halves to be executed.
Combine both open-coded while loops into a single AIO_WAIT_WHILE() call
that solves both of these problems.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit de0fbe64806321fc3e6399bfab360553db87a41d)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
job.c | 14 ++++++--------
1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/job.c b/job.c
index 48a767c..fa74558 100644
--- a/job.c
+++ b/job.c
@@ -29,6 +29,7 @@
#include "qemu/job.h"
#include "qemu/id.h"
#include "qemu/main-loop.h"
+#include "block/aio-wait.h"
#include "trace-root.h"
#include "qapi/qapi-events-job.h"
@@ -962,6 +963,7 @@ void job_complete(Job *job, Error **errp)
int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
{
Error *local_err = NULL;
+ AioWait dummy_wait = {};
int ret;
job_ref(job);
@@ -974,14 +976,10 @@ int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
job_unref(job);
return -EBUSY;
}
- /* job_drain calls job_enter, and it should be enough to induce progress
- * until the job completes or moves to the main thread. */
- while (!job->deferred_to_main_loop && !job_is_completed(job)) {
- job_drain(job);
- }
- while (!job_is_completed(job)) {
- aio_poll(qemu_get_aio_context(), true);
- }
+
+ AIO_WAIT_WHILE(&dummy_wait, job->aio_context,
+ (job_drain(job), !job_is_completed(job)));
+
ret = (job_is_cancelled(job) && job->ret == 0) ? -ECANCELED : job->ret;
job_unref(job);
return ret;
--
1.8.3.1

59
0087-test-bdrv-drain-Test-AIO_WAIT_WHILE-in-completion-ca.patch Normal file
View File

@ -0,0 +1,59 @@
From b9c555343b6567159effe1b3eb736fd1e02257bd Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:01 +0100
Subject: test-bdrv-drain: Test AIO_WAIT_WHILE() in completion callback
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-23-kwolf@redhat.com>
Patchwork-id: 82611
O-Subject: [RHEL-8 qemu-kvm PATCH 32/44] test-bdrv-drain: Test AIO_WAIT_WHILE() in completion callback
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
This is a regression test for a deadlock that occurred in block job
completion callbacks (via job_defer_to_main_loop) because the AioContext
lock was taken twice: once in job_finish_sync() and then again in
job_defer_to_main_loop_bh(). This would cause AIO_WAIT_WHILE() to hang.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit ae23dde9dd486e57e152a0ebc9802caddedc45fc)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
tests/test-bdrv-drain.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c
index 3cf3ba3..05f3b55 100644
--- a/tests/test-bdrv-drain.c
+++ b/tests/test-bdrv-drain.c
@@ -774,6 +774,15 @@ typedef struct TestBlockJob {
bool should_complete;
} TestBlockJob;
+static int test_job_prepare(Job *job)
+{
+ TestBlockJob *s = container_of(job, TestBlockJob, common.job);
+
+ /* Provoke an AIO_WAIT_WHILE() call to verify there is no deadlock */
+ blk_flush(s->common.blk);
+ return 0;
+}
+
static int coroutine_fn test_job_run(Job *job, Error **errp)
{
TestBlockJob *s = container_of(job, TestBlockJob, common.job);
@@ -804,6 +813,7 @@ BlockJobDriver test_job_driver = {
.drain = block_job_drain,
.run = test_job_run,
.complete = test_job_complete,
+ .prepare = test_job_prepare,
},
};
--
1.8.3.1

96
0088-block-Add-missing-locking-in-bdrv_co_drain_bh_cb.patch Normal file
View File

@ -0,0 +1,96 @@
From 51c1069568d78941554c70f9084531c279899c83 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:02 +0100
Subject: block: Add missing locking in bdrv_co_drain_bh_cb()
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-24-kwolf@redhat.com>
Patchwork-id: 82613
O-Subject: [RHEL-8 qemu-kvm PATCH 33/44] block: Add missing locking in bdrv_co_drain_bh_cb()
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
bdrv_do_drained_begin/end() assume that they are called with the
AioContext lock of bs held. If we call drain functions from a coroutine
with the AioContext lock held, we yield and schedule a BH to move out of
coroutine context. This means that the lock for the home context of the
coroutine is released and must be re-acquired in the bottom half.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit aa1361d54aac43094b98024b8b6c804eb6e41661)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/io.c | 15 +++++++++++++++
include/qemu/coroutine.h | 5 +++++
util/qemu-coroutine.c | 5 +++++
3 files changed, 25 insertions(+)
diff --git a/block/io.c b/block/io.c
index 7100344..914ba78 100644
--- a/block/io.c
+++ b/block/io.c
@@ -288,6 +288,18 @@ static void bdrv_co_drain_bh_cb(void *opaque)
BlockDriverState *bs = data->bs;
if (bs) {
+ AioContext *ctx = bdrv_get_aio_context(bs);
+ AioContext *co_ctx = qemu_coroutine_get_aio_context(co);
+
+ /*
+ * When the coroutine yielded, the lock for its home context was
+ * released, so we need to re-acquire it here. If it explicitly
+ * acquired a different context, the lock is still held and we don't
+ * want to lock it a second time (or AIO_WAIT_WHILE() would hang).
+ */
+ if (ctx == co_ctx) {
+ aio_context_acquire(ctx);
+ }
bdrv_dec_in_flight(bs);
if (data->begin) {
bdrv_do_drained_begin(bs, data->recursive, data->parent,
@@ -296,6 +308,9 @@ static void bdrv_co_drain_bh_cb(void *opaque)
bdrv_do_drained_end(bs, data->recursive, data->parent,
data->ignore_bds_parents);
}
+ if (ctx == co_ctx) {
+ aio_context_release(ctx);
+ }
} else {
assert(data->begin);
bdrv_drain_all_begin();
diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h
index 6f8a487..9801e7f 100644
--- a/include/qemu/coroutine.h
+++ b/include/qemu/coroutine.h
@@ -90,6 +90,11 @@ void qemu_aio_coroutine_enter(AioContext *ctx, Coroutine *co);
void coroutine_fn qemu_coroutine_yield(void);
/**
+ * Get the AioContext of the given coroutine
+ */
+AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co);
+
+/**
* Get the currently executing coroutine
*/
Coroutine *coroutine_fn qemu_coroutine_self(void);
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 1ba4191..2295928 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -198,3 +198,8 @@ bool qemu_coroutine_entered(Coroutine *co)
{
return co->caller;
}
+
+AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co)
+{
+ return co->ctx;
+}
--
1.8.3.1

66
0089-block-backend-Add-.drained_poll-callback.patch Normal file
View File

@ -0,0 +1,66 @@
From ea3026a59a3772f84697af9b62b6272cfb41f40c Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:03 +0100
Subject: block-backend: Add .drained_poll callback
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-25-kwolf@redhat.com>
Patchwork-id: 82614
O-Subject: [RHEL-8 qemu-kvm PATCH 34/44] block-backend: Add .drained_poll callback
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
A bdrv_drain operation must ensure that all parents are quiesced, this
includes BlockBackends. Otherwise, callbacks called by requests that are
completed on the BDS layer, but not quite yet on the BlockBackend layer
could still create new requests.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit fe5258a503a87e69be37c9ac48799e293809386e)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/block-backend.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/block/block-backend.c b/block/block-backend.c
index f2f75a9..2b837d1 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -121,6 +121,7 @@ static void blk_root_inherit_options(int *child_flags, QDict *child_options,
abort();
}
static void blk_root_drained_begin(BdrvChild *child);
+static bool blk_root_drained_poll(BdrvChild *child);
static void blk_root_drained_end(BdrvChild *child);
static void blk_root_change_media(BdrvChild *child, bool load);
@@ -294,6 +295,7 @@ static const BdrvChildRole child_root = {
.get_parent_desc = blk_root_get_parent_desc,
.drained_begin = blk_root_drained_begin,
+ .drained_poll = blk_root_drained_poll,
.drained_end = blk_root_drained_end,
.activate = blk_root_activate,
@@ -2192,6 +2194,13 @@ static void blk_root_drained_begin(BdrvChild *child)
}
}
+static bool blk_root_drained_poll(BdrvChild *child)
+{
+ BlockBackend *blk = child->opaque;
+ assert(blk->quiesce_counter);
+ return !!blk->in_flight;
+}
+
static void blk_root_drained_end(BdrvChild *child)
{
BlockBackend *blk = child->opaque;
--
1.8.3.1

67
0090-block-backend-Fix-potential-double-blk_delete.patch Normal file
View File

@ -0,0 +1,67 @@
From 21a2ef76c6aa33f0058d149b1bfdde1d27ba1df4 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:04 +0100
Subject: block-backend: Fix potential double blk_delete()
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-26-kwolf@redhat.com>
Patchwork-id: 82615
O-Subject: [RHEL-8 qemu-kvm PATCH 35/44] block-backend: Fix potential double blk_delete()
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
blk_unref() first decreases the refcount of the BlockBackend and calls
blk_delete() if the refcount reaches zero. Requests can still be in
flight at this point, they are only drained during blk_delete():
At this point, arbitrary callbacks can run. If any callback takes a
temporary BlockBackend reference, it will first increase the refcount to
1 and then decrease it to 0 again, triggering another blk_delete(). This
will cause a use-after-free crash in the outer blk_delete().
Fix it by draining the BlockBackend before decreasing to refcount to 0.
Assert in blk_ref() that it never takes the first refcount (which would
mean that the BlockBackend is already being deleted).
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit 5ca9d21bd1c8eeb578d0964e31bd03d47c25773d)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/block-backend.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/block/block-backend.c b/block/block-backend.c
index 2b837d1..94046f0 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -436,6 +436,7 @@ int blk_get_refcnt(BlockBackend *blk)
*/
void blk_ref(BlockBackend *blk)
{
+ assert(blk->refcnt > 0);
blk->refcnt++;
}
@@ -448,7 +449,13 @@ void blk_unref(BlockBackend *blk)
{
if (blk) {
assert(blk->refcnt > 0);
- if (!--blk->refcnt) {
+ if (blk->refcnt > 1) {
+ blk->refcnt--;
+ } else {
+ blk_drain(blk);
+ /* blk_drain() cannot resurrect blk, nobody held a reference */
+ assert(blk->refcnt == 1);
+ blk->refcnt = 0;
blk_delete(blk);
}
}
--
1.8.3.1

74
0091-block-backend-Decrease-in_flight-only-after-callback.patch Normal file
View File

@ -0,0 +1,74 @@
From 91ae719381f75ed3554b0c5e1d8bf58583a9208f Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:05 +0100
Subject: block-backend: Decrease in_flight only after callback
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-27-kwolf@redhat.com>
Patchwork-id: 82617
O-Subject: [RHEL-8 qemu-kvm PATCH 36/44] block-backend: Decrease in_flight only after callback
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
Request callbacks can do pretty much anything, including operations that
will yield from the coroutine (such as draining the backend). In that
case, a decreased in_flight would be visible to other code and could
lead to a drain completing while the callback hasn't actually completed
yet.
Note that reordering these operations forbids calling drain directly
inside an AIO callback. As Paolo explains, indirectly calling it is
okay:
- Calling it through a coroutine is okay, because then
bdrv_drained_begin() goes through bdrv_co_yield_to_drain() and you
have in_flight=2 when bdrv_co_yield_to_drain() yields, then soon
in_flight=1 when the aio_co_wake() in the AIO callback completes, then
in_flight=0 after the bottom half starts.
- Calling it through a bottom half would be okay too, as long as the AIO
callback remembers to do inc_in_flight/dec_in_flight just like
bdrv_co_yield_to_drain() and bdrv_co_drain_bh_cb() do
A few more important cases that come to mind:
- A coroutine that yields because of I/O is okay, with a sequence
similar to bdrv_co_yield_to_drain().
- A coroutine that yields with no I/O pending will correctly decrease
in_flight to zero before yielding.
- Calling more AIO from the callback won't overflow the counter just
because of mutual recursion, because AIO functions always yield at
least once before invoking the callback.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 46aaf2a566e364a62315219255099cbf1c9b990d)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/block-backend.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/block/block-backend.c b/block/block-backend.c
index 94046f0..9a3e060 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1341,8 +1341,8 @@ static const AIOCBInfo blk_aio_em_aiocb_info = {
static void blk_aio_complete(BlkAioEmAIOCB *acb)
{
if (acb->has_returned) {
- blk_dec_in_flight(acb->rwco.blk);
acb->common.cb(acb->common.opaque, acb->rwco.ret);
+ blk_dec_in_flight(acb->rwco.blk);
qemu_aio_unref(acb);
}
}
--
1.8.3.1

104
0092-blockjob-Lie-better-in-child_job_drained_poll.patch Normal file
View File

@ -0,0 +1,104 @@
From bc17446b1e7c9578a3e3079173891c93998dfa00 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:06 +0100
Subject: blockjob: Lie better in child_job_drained_poll()
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-28-kwolf@redhat.com>
Patchwork-id: 82616
O-Subject: [RHEL-8 qemu-kvm PATCH 37/44] blockjob: Lie better in child_job_drained_poll()
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
Block jobs claim in .drained_poll() that they are in a quiescent state
as soon as job->deferred_to_main_loop is true. This is obviously wrong,
they still have a completion BH to run. We only get away with this
because commit 91af091f923 added an unconditional aio_poll(false) to the
drain functions, but this is bypassing the regular drain mechanisms.
However, just removing this and telling that the job is still active
doesn't work either: The completion callbacks themselves call drain
functions (directly, or indirectly with bdrv_reopen), so they would
deadlock then.
As a better lie, tell that the job is active as long as the BH is
pending, but falsely call it quiescent from the point in the BH when the
completion callback is called. At this point, nested drain calls won't
deadlock because they ignore the job, and outer drains will wait for the
job to really reach a quiescent state because the callback is already
running.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit b5a7a0573530698ee448b063ac01d485e30446bd)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
blockjob.c | 2 +-
include/qemu/job.h | 3 +++
job.c | 11 ++++++++++-
3 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/blockjob.c b/blockjob.c
index 8d27e8e..617d86f 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -164,7 +164,7 @@ static bool child_job_drained_poll(BdrvChild *c)
/* An inactive or completed job doesn't have any pending requests. Jobs
* with !job->busy are either already paused or have a pause point after
* being reentered, so no job driver code will run before they pause. */
- if (!job->busy || job_is_completed(job) || job->deferred_to_main_loop) {
+ if (!job->busy || job_is_completed(job)) {
return false;
}
diff --git a/include/qemu/job.h b/include/qemu/job.h
index 63c60ef..9e7cd1e 100644
--- a/include/qemu/job.h
+++ b/include/qemu/job.h
@@ -76,6 +76,9 @@ typedef struct Job {
* Set to false by the job while the coroutine has yielded and may be
* re-entered by job_enter(). There may still be I/O or event loop activity
* pending. Accessed under block_job_mutex (in blockjob.c).
+ *
+ * When the job is deferred to the main loop, busy is true as long as the
+ * bottom half is still pending.
*/
bool busy;
diff --git a/job.c b/job.c
index fa74558..00a1cd1 100644
--- a/job.c
+++ b/job.c
@@ -857,7 +857,16 @@ static void job_exit(void *opaque)
AioContext *ctx = job->aio_context;
aio_context_acquire(ctx);
+
+ /* This is a lie, we're not quiescent, but still doing the completion
+ * callbacks. However, completion callbacks tend to involve operations that
+ * drain block nodes, and if .drained_poll still returned true, we would
+ * deadlock. */
+ job->busy = false;
+ job_event_idle(job);
+
job_completed(job);
+
aio_context_release(ctx);
}
@@ -872,8 +881,8 @@ static void coroutine_fn job_co_entry(void *opaque)
assert(job && job->driver && job->driver->run);
job_pause_point(job);
job->ret = job->driver->run(job, &job->err);
- job_event_idle(job);
job->deferred_to_main_loop = true;
+ job->busy = true;
aio_bh_schedule_oneshot(qemu_get_aio_context(), job_exit, job);
}
--
1.8.3.1

64
0093-block-Remove-aio_poll-in-bdrv_drain_poll-variants.patch Normal file
View File

@ -0,0 +1,64 @@
From ce7a9c21d6a43b736d5aa2041acbd5d1edca0070 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:07 +0100
Subject: block: Remove aio_poll() in bdrv_drain_poll variants
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-29-kwolf@redhat.com>
Patchwork-id: 82619
O-Subject: [RHEL-8 qemu-kvm PATCH 38/44] block: Remove aio_poll() in bdrv_drain_poll variants
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
bdrv_drain_poll_top_level() was buggy because it didn't release the
AioContext lock of the node to be drained before calling aio_poll().
This way, callbacks called by aio_poll() would possibly take the lock a
second time and run into a deadlock with a nested AIO_WAIT_WHILE() call.
However, it turns out that the aio_poll() call isn't actually needed any
more. It was introduced in commit 91af091f923, which is effectively
reverted by this patch. The cases it was supposed to fix are now covered
by bdrv_drain_poll(), which waits for block jobs to reach a quiescent
state.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit 4cf077b59fc73eec29f8b7d082919dbb278bdc86)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/io.c | 8 --------
1 file changed, 8 deletions(-)
diff --git a/block/io.c b/block/io.c
index 914ba78..8b81ff3 100644
--- a/block/io.c
+++ b/block/io.c
@@ -268,10 +268,6 @@ bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
static bool bdrv_drain_poll_top_level(BlockDriverState *bs, bool recursive,
BdrvChild *ignore_parent)
{
- /* Execute pending BHs first and check everything else only after the BHs
- * have executed. */
- while (aio_poll(bs->aio_context, false));
-
return bdrv_drain_poll(bs, recursive, ignore_parent, false);
}
@@ -511,10 +507,6 @@ static bool bdrv_drain_all_poll(void)
BlockDriverState *bs = NULL;
bool result = false;
- /* Execute pending BHs first (may modify the graph) and check everything
- * else only after the BHs have executed. */
- while (aio_poll(qemu_get_aio_context(), false));
-
/* bdrv_drain_poll() can't make changes to the graph and we are holding the
* main AioContext lock, so iterating bdrv_next_all_states() is safe. */
while ((bs = bdrv_next_all_states(bs))) {
--
1.8.3.1

63
0094-test-bdrv-drain-Test-nested-poll-in-bdrv_drain_poll_.patch Normal file
View File

@ -0,0 +1,63 @@
From 6c315602205e494dd084a4692a06c16b0e233875 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:08 +0100
Subject: test-bdrv-drain: Test nested poll in bdrv_drain_poll_top_level()
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-30-kwolf@redhat.com>
Patchwork-id: 82618
O-Subject: [RHEL-8 qemu-kvm PATCH 39/44] test-bdrv-drain: Test nested poll in bdrv_drain_poll_top_level()
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
This is a regression test for a deadlock that could occur in callbacks
called from the aio_poll() in bdrv_drain_poll_top_level(). The
AioContext lock wasn't released and therefore would be taken a second
time in the callback. This would cause a possible AIO_WAIT_WHILE() in
the callback to hang.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit ecc1a5c790cf2c7732cb9755ca388c2fe108d1a1)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
tests/test-bdrv-drain.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c
index 05f3b55..f4b57f7 100644
--- a/tests/test-bdrv-drain.c
+++ b/tests/test-bdrv-drain.c
@@ -636,6 +636,17 @@ static void test_iothread_aio_cb(void *opaque, int ret)
qemu_event_set(&done_event);
}
+static void test_iothread_main_thread_bh(void *opaque)
+{
+ struct test_iothread_data *data = opaque;
+
+ /* Test that the AioContext is not yet locked in a random BH that is
+ * executed during drain, otherwise this would deadlock. */
+ aio_context_acquire(bdrv_get_aio_context(data->bs));
+ bdrv_flush(data->bs);
+ aio_context_release(bdrv_get_aio_context(data->bs));
+}
+
/*
* Starts an AIO request on a BDS that runs in the AioContext of iothread 1.
* The request involves a BH on iothread 2 before it can complete.
@@ -705,6 +716,8 @@ static void test_iothread_common(enum drain_type drain_type, int drain_thread)
aio_context_acquire(ctx_a);
}
+ aio_bh_schedule_oneshot(ctx_a, test_iothread_main_thread_bh, &data);
+
/* The request is running on the IOThread a. Draining its block device
* will make sure that it has completed as far as the BDS is concerned,
* but the drain in this thread can continue immediately after
--
1.8.3.1

85
0095-job-Avoid-deadlocks-in-job_completed_txn_abort.patch Normal file
View File

@ -0,0 +1,85 @@
From 287d4267dcb2d5f262dba7f6e7f35dcd294b622a Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:09 +0100
Subject: job: Avoid deadlocks in job_completed_txn_abort()
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-31-kwolf@redhat.com>
Patchwork-id: 82622
O-Subject: [RHEL-8 qemu-kvm PATCH 40/44] job: Avoid deadlocks in job_completed_txn_abort()
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
Amongst others, job_finalize_single() calls the .prepare/.commit/.abort
callbacks of the individual job driver. Recently, their use was adapted
for all block jobs so that they involve code calling AIO_WAIT_WHILE()
now. Such code must be called under the AioContext lock for the
respective job, but without holding any other AioContext lock.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit 644f3a29bd4974aefd46d2adb5062d86063c8a50)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
job.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
diff --git a/job.c b/job.c
index 00a1cd1..0b02186 100644
--- a/job.c
+++ b/job.c
@@ -718,6 +718,7 @@ static void job_cancel_async(Job *job, bool force)
static void job_completed_txn_abort(Job *job)
{
+ AioContext *outer_ctx = job->aio_context;
AioContext *ctx;
JobTxn *txn = job->txn;
Job *other_job;
@@ -731,23 +732,26 @@ static void job_completed_txn_abort(Job *job)
txn->aborting = true;
job_txn_ref(txn);
- /* We are the first failed job. Cancel other jobs. */
- QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
- ctx = other_job->aio_context;
- aio_context_acquire(ctx);
- }
+ /* We can only hold the single job's AioContext lock while calling
+ * job_finalize_single() because the finalization callbacks can involve
+ * calls of AIO_WAIT_WHILE(), which could deadlock otherwise. */
+ aio_context_release(outer_ctx);
/* Other jobs are effectively cancelled by us, set the status for
* them; this job, however, may or may not be cancelled, depending
* on the caller, so leave it. */
QLIST_FOREACH(other_job, &txn->jobs, txn_list) {
if (other_job != job) {
+ ctx = other_job->aio_context;
+ aio_context_acquire(ctx);
job_cancel_async(other_job, false);
+ aio_context_release(ctx);
}
}
while (!QLIST_EMPTY(&txn->jobs)) {
other_job = QLIST_FIRST(&txn->jobs);
ctx = other_job->aio_context;
+ aio_context_acquire(ctx);
if (!job_is_completed(other_job)) {
assert(job_is_cancelled(other_job));
job_finish_sync(other_job, NULL, NULL);
@@ -756,6 +760,8 @@ static void job_completed_txn_abort(Job *job)
aio_context_release(ctx);
}
+ aio_context_acquire(outer_ctx);
+
job_txn_unref(txn);
}
--
1.8.3.1

241
0096-test-bdrv-drain-AIO_WAIT_WHILE-in-job-.commit-.abort.patch Normal file
View File

@ -0,0 +1,241 @@
From 10fbd3c89739a1879f47f2a2256831ce5e1ae7ad Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:10 +0100
Subject: test-bdrv-drain: AIO_WAIT_WHILE() in job .commit/.abort
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-32-kwolf@redhat.com>
Patchwork-id: 82620
O-Subject: [RHEL-8 qemu-kvm PATCH 41/44] test-bdrv-drain: AIO_WAIT_WHILE() in job .commit/.abort
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
This adds tests for calling AIO_WAIT_WHILE() in the .commit and .abort
callbacks. Both reasons why .abort could be called for a single job are
tested: Either .run or .prepare could return an error.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit d49725af46a7710cde02cc120b7f1e485154b483)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
tests/test-bdrv-drain.c | 116 +++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 104 insertions(+), 12 deletions(-)
diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c
index f4b57f7..d6202b2 100644
--- a/tests/test-bdrv-drain.c
+++ b/tests/test-bdrv-drain.c
@@ -784,6 +784,8 @@ static void test_iothread_drain_subtree(void)
typedef struct TestBlockJob {
BlockJob common;
+ int run_ret;
+ int prepare_ret;
bool should_complete;
} TestBlockJob;
@@ -793,7 +795,23 @@ static int test_job_prepare(Job *job)
/* Provoke an AIO_WAIT_WHILE() call to verify there is no deadlock */
blk_flush(s->common.blk);
- return 0;
+ return s->prepare_ret;
+}
+
+static void test_job_commit(Job *job)
+{
+ TestBlockJob *s = container_of(job, TestBlockJob, common.job);
+
+ /* Provoke an AIO_WAIT_WHILE() call to verify there is no deadlock */
+ blk_flush(s->common.blk);
+}
+
+static void test_job_abort(Job *job)
+{
+ TestBlockJob *s = container_of(job, TestBlockJob, common.job);
+
+ /* Provoke an AIO_WAIT_WHILE() call to verify there is no deadlock */
+ blk_flush(s->common.blk);
}
static int coroutine_fn test_job_run(Job *job, Error **errp)
@@ -809,7 +827,7 @@ static int coroutine_fn test_job_run(Job *job, Error **errp)
job_pause_point(&s->common.job);
}
- return 0;
+ return s->run_ret;
}
static void test_job_complete(Job *job, Error **errp)
@@ -827,14 +845,24 @@ BlockJobDriver test_job_driver = {
.run = test_job_run,
.complete = test_job_complete,
.prepare = test_job_prepare,
+ .commit = test_job_commit,
+ .abort = test_job_abort,
},
};
-static void test_blockjob_common(enum drain_type drain_type, bool use_iothread)
+enum test_job_result {
+ TEST_JOB_SUCCESS,
+ TEST_JOB_FAIL_RUN,
+ TEST_JOB_FAIL_PREPARE,
+};
+
+static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
+ enum test_job_result result)
{
BlockBackend *blk_src, *blk_target;
BlockDriverState *src, *target;
BlockJob *job;
+ TestBlockJob *tjob;
IOThread *iothread = NULL;
AioContext *ctx;
int ret;
@@ -858,9 +886,23 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread)
blk_insert_bs(blk_target, target, &error_abort);
aio_context_acquire(ctx);
- job = block_job_create("job0", &test_job_driver, NULL, src, 0, BLK_PERM_ALL,
- 0, 0, NULL, NULL, &error_abort);
+ tjob = block_job_create("job0", &test_job_driver, NULL, src,
+ 0, BLK_PERM_ALL,
+ 0, 0, NULL, NULL, &error_abort);
+ job = &tjob->common;
block_job_add_bdrv(job, "target", target, 0, BLK_PERM_ALL, &error_abort);
+
+ switch (result) {
+ case TEST_JOB_SUCCESS:
+ break;
+ case TEST_JOB_FAIL_RUN:
+ tjob->run_ret = -EIO;
+ break;
+ case TEST_JOB_FAIL_PREPARE:
+ tjob->prepare_ret = -EIO;
+ break;
+ }
+
job_start(&job->job);
aio_context_release(ctx);
@@ -918,7 +960,7 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread)
aio_context_acquire(ctx);
ret = job_complete_sync(&job->job, &error_abort);
- g_assert_cmpint(ret, ==, 0);
+ g_assert_cmpint(ret, ==, (result == TEST_JOB_SUCCESS ? 0 : -EIO));
if (use_iothread) {
blk_set_aio_context(blk_src, qemu_get_aio_context());
@@ -937,32 +979,68 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread)
static void test_blockjob_drain_all(void)
{
- test_blockjob_common(BDRV_DRAIN_ALL, false);
+ test_blockjob_common(BDRV_DRAIN_ALL, false, TEST_JOB_SUCCESS);
}
static void test_blockjob_drain(void)
{
- test_blockjob_common(BDRV_DRAIN, false);
+ test_blockjob_common(BDRV_DRAIN, false, TEST_JOB_SUCCESS);
}
static void test_blockjob_drain_subtree(void)
{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, false);
+ test_blockjob_common(BDRV_SUBTREE_DRAIN, false, TEST_JOB_SUCCESS);
+}
+
+static void test_blockjob_error_drain_all(void)
+{
+ test_blockjob_common(BDRV_DRAIN_ALL, false, TEST_JOB_FAIL_RUN);
+ test_blockjob_common(BDRV_DRAIN_ALL, false, TEST_JOB_FAIL_PREPARE);
+}
+
+static void test_blockjob_error_drain(void)
+{
+ test_blockjob_common(BDRV_DRAIN, false, TEST_JOB_FAIL_RUN);
+ test_blockjob_common(BDRV_DRAIN, false, TEST_JOB_FAIL_PREPARE);
+}
+
+static void test_blockjob_error_drain_subtree(void)
+{
+ test_blockjob_common(BDRV_SUBTREE_DRAIN, false, TEST_JOB_FAIL_RUN);
+ test_blockjob_common(BDRV_SUBTREE_DRAIN, false, TEST_JOB_FAIL_PREPARE);
}
static void test_blockjob_iothread_drain_all(void)
{
- test_blockjob_common(BDRV_DRAIN_ALL, true);
+ test_blockjob_common(BDRV_DRAIN_ALL, true, TEST_JOB_SUCCESS);
}
static void test_blockjob_iothread_drain(void)
{
- test_blockjob_common(BDRV_DRAIN, true);
+ test_blockjob_common(BDRV_DRAIN, true, TEST_JOB_SUCCESS);
}
static void test_blockjob_iothread_drain_subtree(void)
{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, true);
+ test_blockjob_common(BDRV_SUBTREE_DRAIN, true, TEST_JOB_SUCCESS);
+}
+
+static void test_blockjob_iothread_error_drain_all(void)
+{
+ test_blockjob_common(BDRV_DRAIN_ALL, true, TEST_JOB_FAIL_RUN);
+ test_blockjob_common(BDRV_DRAIN_ALL, true, TEST_JOB_FAIL_PREPARE);
+}
+
+static void test_blockjob_iothread_error_drain(void)
+{
+ test_blockjob_common(BDRV_DRAIN, true, TEST_JOB_FAIL_RUN);
+ test_blockjob_common(BDRV_DRAIN, true, TEST_JOB_FAIL_PREPARE);
+}
+
+static void test_blockjob_iothread_error_drain_subtree(void)
+{
+ test_blockjob_common(BDRV_SUBTREE_DRAIN, true, TEST_JOB_FAIL_RUN);
+ test_blockjob_common(BDRV_SUBTREE_DRAIN, true, TEST_JOB_FAIL_PREPARE);
}
@@ -1433,6 +1511,13 @@ int main(int argc, char **argv)
g_test_add_func("/bdrv-drain/blockjob/drain_subtree",
test_blockjob_drain_subtree);
+ g_test_add_func("/bdrv-drain/blockjob/error/drain_all",
+ test_blockjob_error_drain_all);
+ g_test_add_func("/bdrv-drain/blockjob/error/drain",
+ test_blockjob_error_drain);
+ g_test_add_func("/bdrv-drain/blockjob/error/drain_subtree",
+ test_blockjob_error_drain_subtree);
+
g_test_add_func("/bdrv-drain/blockjob/iothread/drain_all",
test_blockjob_iothread_drain_all);
g_test_add_func("/bdrv-drain/blockjob/iothread/drain",
@@ -1440,6 +1525,13 @@ int main(int argc, char **argv)
g_test_add_func("/bdrv-drain/blockjob/iothread/drain_subtree",
test_blockjob_iothread_drain_subtree);
+ g_test_add_func("/bdrv-drain/blockjob/iothread/error/drain_all",
+ test_blockjob_iothread_error_drain_all);
+ g_test_add_func("/bdrv-drain/blockjob/iothread/error/drain",
+ test_blockjob_iothread_error_drain);
+ g_test_add_func("/bdrv-drain/blockjob/iothread/error/drain_subtree",
+ test_blockjob_iothread_error_drain_subtree);
+
g_test_add_func("/bdrv-drain/deletion/drain", test_delete_by_drain);
g_test_add_func("/bdrv-drain/detach/drain_all", test_detach_by_drain_all);
g_test_add_func("/bdrv-drain/detach/drain", test_detach_by_drain);
--
1.8.3.1

69
0097-test-bdrv-drain-Fix-outdated-comments.patch Normal file
View File

@ -0,0 +1,69 @@
From 1eaa60bc24cb3fecba8da61f21c44e6f4c9ee4c1 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:11 +0100
Subject: test-bdrv-drain: Fix outdated comments
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-33-kwolf@redhat.com>
Patchwork-id: 82621
O-Subject: [RHEL-8 qemu-kvm PATCH 42/44] test-bdrv-drain: Fix outdated comments
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
Commit 89bd030533e changed the test case from using job_sleep_ns() to
using qemu_co_sleep_ns() instead. Also, block_job_sleep_ns() became
job_sleep_ns() in commit 5d43e86e11f.
In both cases, some comments in the test case were not updated. Do that
now.
Reported-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit 5599c162c3bec2bc8f0123e4d5802a70d9984b3b)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
tests/test-bdrv-drain.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c
index d6202b2..7e7ba9b 100644
--- a/tests/test-bdrv-drain.c
+++ b/tests/test-bdrv-drain.c
@@ -820,9 +820,9 @@ static int coroutine_fn test_job_run(Job *job, Error **errp)
job_transition_to_ready(&s->common.job);
while (!s->should_complete) {
- /* Avoid block_job_sleep_ns() because it marks the job as !busy. We
- * want to emulate some actual activity (probably some I/O) here so
- * that drain has to wait for this acitivity to stop. */
+ /* Avoid job_sleep_ns() because it marks the job as !busy. We want to
+ * emulate some actual activity (probably some I/O) here so that drain
+ * has to wait for this activity to stop. */
qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 100000);
job_pause_point(&s->common.job);
}
@@ -908,7 +908,7 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
g_assert_cmpint(job->job.pause_count, ==, 0);
g_assert_false(job->job.paused);
- g_assert_true(job->job.busy); /* We're in job_sleep_ns() */
+ g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */
do_drain_begin_unlocked(drain_type, src);
@@ -956,7 +956,7 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
g_assert_cmpint(job->job.pause_count, ==, 0);
g_assert_false(job->job.paused);
- g_assert_true(job->job.busy); /* We're in job_sleep_ns() */
+ g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */
aio_context_acquire(ctx);
ret = job_complete_sync(&job->job, &error_abort);
--
1.8.3.1

367
0098-block-Use-a-single-global-AioWait.patch Normal file
View File

@ -0,0 +1,367 @@
From ea2355d819127ace6195e1d007bc305a49e7d465 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:12 +0100
Subject: block: Use a single global AioWait
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-34-kwolf@redhat.com>
Patchwork-id: 82623
O-Subject: [RHEL-8 qemu-kvm PATCH 43/44] block: Use a single global AioWait
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
When draining a block node, we recurse to its parent and for subtree
drains also to its children. A single AIO_WAIT_WHILE() is then used to
wait for bdrv_drain_poll() to become true, which depends on all of the
nodes we recursed to. However, if the respective child or parent becomes
quiescent and calls bdrv_wakeup(), only the AioWait of the child/parent
is checked, while AIO_WAIT_WHILE() depends on the AioWait of the
original node.
Fix this by using a single AioWait for all callers of AIO_WAIT_WHILE().
This may mean that the draining thread gets a few more unnecessary
wakeups because an unrelated operation got completed, but we already
wake it up when something _could_ have changed rather than only if it
has certainly changed.
Apart from that, drain is a slow path anyway. In theory it would be
possible to use wakeups more selectively and still correctly, but the
gains are likely not worth the additional complexity. In fact, this
patch is a nice simplification for some places in the code.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit cfe29d8294e06420e15d4938421ae006c8ac49e7)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block.c | 5 -----
block/block-backend.c | 11 ++++-------
block/io.c | 7 ++-----
blockjob.c | 13 +------------
include/block/aio-wait.h | 22 +++++++++++-----------
include/block/block.h | 6 +-----
include/block/block_int.h | 3 ---
include/block/blockjob.h | 10 ----------
job.c | 3 +--
util/aio-wait.c | 11 ++++++-----
10 files changed, 26 insertions(+), 65 deletions(-)
diff --git a/block.c b/block.c
index 39f373e..9b55956 100644
--- a/block.c
+++ b/block.c
@@ -4865,11 +4865,6 @@ AioContext *bdrv_get_aio_context(BlockDriverState *bs)
return bs ? bs->aio_context : qemu_get_aio_context();
}
-AioWait *bdrv_get_aio_wait(BlockDriverState *bs)
-{
- return bs ? &bs->wait : NULL;
-}
-
void bdrv_coroutine_enter(BlockDriverState *bs, Coroutine *co)
{
aio_co_enter(bdrv_get_aio_context(bs), co);
diff --git a/block/block-backend.c b/block/block-backend.c
index 9a3e060..723ab5a 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -88,7 +88,6 @@ struct BlockBackend {
* Accessed with atomic ops.
*/
unsigned int in_flight;
- AioWait wait;
};
typedef struct BlockBackendAIOCB {
@@ -1300,7 +1299,7 @@ static void blk_inc_in_flight(BlockBackend *blk)
static void blk_dec_in_flight(BlockBackend *blk)
{
atomic_dec(&blk->in_flight);
- aio_wait_kick(&blk->wait);
+ aio_wait_kick();
}
static void error_callback_bh(void *opaque)
@@ -1601,9 +1600,8 @@ void blk_drain(BlockBackend *blk)
}
/* We may have -ENOMEDIUM completions in flight */
- AIO_WAIT_WHILE(&blk->wait,
- blk_get_aio_context(blk),
- atomic_mb_read(&blk->in_flight) > 0);
+ AIO_WAIT_WHILE(blk_get_aio_context(blk),
+ atomic_mb_read(&blk->in_flight) > 0);
if (bs) {
bdrv_drained_end(bs);
@@ -1622,8 +1620,7 @@ void blk_drain_all(void)
aio_context_acquire(ctx);
/* We may have -ENOMEDIUM completions in flight */
- AIO_WAIT_WHILE(&blk->wait, ctx,
- atomic_mb_read(&blk->in_flight) > 0);
+ AIO_WAIT_WHILE(ctx, atomic_mb_read(&blk->in_flight) > 0);
aio_context_release(ctx);
}
diff --git a/block/io.c b/block/io.c
index 8b81ff3..bd9d688 100644
--- a/block/io.c
+++ b/block/io.c
@@ -38,8 +38,6 @@
/* Maximum bounce buffer for copy-on-read and write zeroes, in bytes */
#define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS)
-static AioWait drain_all_aio_wait;
-
static void bdrv_parent_cb_resize(BlockDriverState *bs);
static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int bytes, BdrvRequestFlags flags);
@@ -557,7 +555,7 @@ void bdrv_drain_all_begin(void)
}
/* Now poll the in-flight requests */
- AIO_WAIT_WHILE(&drain_all_aio_wait, NULL, bdrv_drain_all_poll());
+ AIO_WAIT_WHILE(NULL, bdrv_drain_all_poll());
while ((bs = bdrv_next_all_states(bs))) {
bdrv_drain_assert_idle(bs);
@@ -713,8 +711,7 @@ void bdrv_inc_in_flight(BlockDriverState *bs)
void bdrv_wakeup(BlockDriverState *bs)
{
- aio_wait_kick(bdrv_get_aio_wait(bs));
- aio_wait_kick(&drain_all_aio_wait);
+ aio_wait_kick();
}
void bdrv_dec_in_flight(BlockDriverState *bs)
diff --git a/blockjob.c b/blockjob.c
index 617d86f..06f2429 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -221,20 +221,9 @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
return 0;
}
-void block_job_wakeup_all_bdrv(BlockJob *job)
-{
- GSList *l;
-
- for (l = job->nodes; l; l = l->next) {
- BdrvChild *c = l->data;
- bdrv_wakeup(c->bs);
- }
-}
-
static void block_job_on_idle(Notifier *n, void *opaque)
{
- BlockJob *job = opaque;
- block_job_wakeup_all_bdrv(job);
+ aio_wait_kick();
}
bool block_job_is_internal(BlockJob *job)
diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index 600fad1..afd0ff7 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -30,14 +30,15 @@
/**
* AioWait:
*
- * An object that facilitates synchronous waiting on a condition. The main
- * loop can wait on an operation running in an IOThread as follows:
+ * An object that facilitates synchronous waiting on a condition. A single
+ * global AioWait object (global_aio_wait) is used internally.
+ *
+ * The main loop can wait on an operation running in an IOThread as follows:
*
- * AioWait *wait = ...;
* AioContext *ctx = ...;
* MyWork work = { .done = false };
* schedule_my_work_in_iothread(ctx, &work);
- * AIO_WAIT_WHILE(wait, ctx, !work.done);
+ * AIO_WAIT_WHILE(ctx, !work.done);
*
* The IOThread must call aio_wait_kick() to notify the main loop when
* work.done changes:
@@ -46,7 +47,7 @@
* {
* ...
* work.done = true;
- * aio_wait_kick(wait);
+ * aio_wait_kick();
* }
*/
typedef struct {
@@ -54,9 +55,10 @@ typedef struct {
unsigned num_waiters;
} AioWait;
+extern AioWait global_aio_wait;
+
/**
* AIO_WAIT_WHILE:
- * @wait: the aio wait object
* @ctx: the aio context, or NULL if multiple aio contexts (for which the
* caller does not hold a lock) are involved in the polling condition.
* @cond: wait while this conditional expression is true
@@ -72,9 +74,9 @@ typedef struct {
* wait on conditions between two IOThreads since that could lead to deadlock,
* go via the main loop instead.
*/
-#define AIO_WAIT_WHILE(wait, ctx, cond) ({ \
+#define AIO_WAIT_WHILE(ctx, cond) ({ \
bool waited_ = false; \
- AioWait *wait_ = (wait); \
+ AioWait *wait_ = &global_aio_wait; \
AioContext *ctx_ = (ctx); \
/* Increment wait_->num_waiters before evaluating cond. */ \
atomic_inc(&wait_->num_waiters); \
@@ -102,14 +104,12 @@ typedef struct {
/**
* aio_wait_kick:
- * @wait: the aio wait object that should re-evaluate its condition
- *
* Wake up the main thread if it is waiting on AIO_WAIT_WHILE(). During
* synchronous operations performed in an IOThread, the main thread lets the
* IOThread's event loop run, waiting for the operation to complete. A
* aio_wait_kick() call will wake up the main thread.
*/
-void aio_wait_kick(AioWait *wait);
+void aio_wait_kick(void);
/**
* aio_wait_bh_oneshot:
diff --git a/include/block/block.h b/include/block/block.h
index 4e0871a..4edc1e8 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -410,13 +410,9 @@ void bdrv_drain_all_begin(void);
void bdrv_drain_all_end(void);
void bdrv_drain_all(void);
-/* Returns NULL when bs == NULL */
-AioWait *bdrv_get_aio_wait(BlockDriverState *bs);
-
#define BDRV_POLL_WHILE(bs, cond) ({ \
BlockDriverState *bs_ = (bs); \
- AIO_WAIT_WHILE(bdrv_get_aio_wait(bs_), \
- bdrv_get_aio_context(bs_), \
+ AIO_WAIT_WHILE(bdrv_get_aio_context(bs_), \
cond); })
int bdrv_pdiscard(BdrvChild *child, int64_t offset, int bytes);
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 4000d2a..92ecbd8 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -794,9 +794,6 @@ struct BlockDriverState {
unsigned int in_flight;
unsigned int serialising_in_flight;
- /* Kicked to signal main loop when a request completes. */
- AioWait wait;
-
/* counter for nested bdrv_io_plug.
* Accessed with atomic ops.
*/
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index 2290bbb..ede0bd8 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -122,16 +122,6 @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
void block_job_remove_all_bdrv(BlockJob *job);
/**
- * block_job_wakeup_all_bdrv:
- * @job: The block job
- *
- * Calls bdrv_wakeup() for all BlockDriverStates that have been added to the
- * job. This function is to be called whenever child_job_drained_poll() would
- * go from true to false to notify waiting drain requests.
- */
-void block_job_wakeup_all_bdrv(BlockJob *job);
-
-/**
* block_job_set_speed:
* @job: The job to set the speed for.
* @speed: The new value
diff --git a/job.c b/job.c
index 0b02186..ed4da6f 100644
--- a/job.c
+++ b/job.c
@@ -978,7 +978,6 @@ void job_complete(Job *job, Error **errp)
int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
{
Error *local_err = NULL;
- AioWait dummy_wait = {};
int ret;
job_ref(job);
@@ -992,7 +991,7 @@ int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
return -EBUSY;
}
- AIO_WAIT_WHILE(&dummy_wait, job->aio_context,
+ AIO_WAIT_WHILE(job->aio_context,
(job_drain(job), !job_is_completed(job)));
ret = (job_is_cancelled(job) && job->ret == 0) ? -ECANCELED : job->ret;
diff --git a/util/aio-wait.c b/util/aio-wait.c
index b8a8f86..b487749 100644
--- a/util/aio-wait.c
+++ b/util/aio-wait.c
@@ -26,21 +26,22 @@
#include "qemu/main-loop.h"
#include "block/aio-wait.h"
+AioWait global_aio_wait;
+
static void dummy_bh_cb(void *opaque)
{
/* The point is to make AIO_WAIT_WHILE()'s aio_poll() return */
}
-void aio_wait_kick(AioWait *wait)
+void aio_wait_kick(void)
{
/* The barrier (or an atomic op) is in the caller. */
- if (atomic_read(&wait->num_waiters)) {
+ if (atomic_read(&global_aio_wait.num_waiters)) {
aio_bh_schedule_oneshot(qemu_get_aio_context(), dummy_bh_cb, NULL);
}
}
typedef struct {
- AioWait wait;
bool done;
QEMUBHFunc *cb;
void *opaque;
@@ -54,7 +55,7 @@ static void aio_wait_bh(void *opaque)
data->cb(data->opaque);
data->done = true;
- aio_wait_kick(&data->wait);
+ aio_wait_kick();
}
void aio_wait_bh_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
@@ -67,5 +68,5 @@ void aio_wait_bh_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
assert(qemu_get_current_aio_context() == qemu_get_aio_context());
aio_bh_schedule_oneshot(ctx, aio_wait_bh, &data);
- AIO_WAIT_WHILE(&data.wait, ctx, !data.done);
+ AIO_WAIT_WHILE(ctx, !data.done);
}
--
1.8.3.1

198
0099-test-bdrv-drain-Test-draining-job-source-child-and-p.patch Normal file
View File

@ -0,0 +1,198 @@
From f31ce5e7d486c860d44cb103b672f81de9bc537c Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 10 Oct 2018 20:22:13 +0100
Subject: test-bdrv-drain: Test draining job source child and parent
RH-Author: Kevin Wolf <kwolf@redhat.com>
Message-id: <20181010202213.7372-35-kwolf@redhat.com>
Patchwork-id: 82624
O-Subject: [RHEL-8 qemu-kvm PATCH 44/44] test-bdrv-drain: Test draining job source child and parent
Bugzilla: 1637976
RH-Acked-by: Max Reitz <mreitz@redhat.com>
RH-Acked-by: John Snow <jsnow@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
For the block job drain test, don't only test draining the source and
the target node, but create a backing chain for the source
(source_backing <- source <- source_overlay) and test draining each of
the nodes in it.
When using iothreads, the source node (and therefore the job) is in a
different AioContext than the drain, which happens from the main
thread. This way, the main thread waits in AIO_WAIT_WHILE() for the
iothread to make process and aio_wait_kick() is required to notify it.
The test validates that calling bdrv_wakeup() for a child or a parent
node will actually notify AIO_WAIT_WHILE() instead of letting it hang.
Increase the sleep time a bit (to 1 ms) because the test case is racy
and with the shorter sleep, it didn't reproduce the bug it is supposed
to test for me under 'rr record -n'.
This was because bdrv_drain_invoke_entry() (in the main thread) was only
called after the job had already reached the pause point, so we got a
bdrv_dec_in_flight() from the main thread and the additional
aio_wait_kick() when the job becomes idle (that we really wanted to test
here) wasn't even necessary any more to make progress.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit d8b3afd597d54e496809b05ac39ac29a5799664f)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
tests/test-bdrv-drain.c | 77 ++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 69 insertions(+), 8 deletions(-)
diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c
index 7e7ba9b..8641b54 100644
--- a/tests/test-bdrv-drain.c
+++ b/tests/test-bdrv-drain.c
@@ -786,6 +786,7 @@ typedef struct TestBlockJob {
BlockJob common;
int run_ret;
int prepare_ret;
+ bool running;
bool should_complete;
} TestBlockJob;
@@ -818,12 +819,17 @@ static int coroutine_fn test_job_run(Job *job, Error **errp)
{
TestBlockJob *s = container_of(job, TestBlockJob, common.job);
+ /* We are running the actual job code past the pause point in
+ * job_co_entry(). */
+ s->running = true;
+
job_transition_to_ready(&s->common.job);
while (!s->should_complete) {
/* Avoid job_sleep_ns() because it marks the job as !busy. We want to
* emulate some actual activity (probably some I/O) here so that drain
* has to wait for this activity to stop. */
- qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 100000);
+ qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 1000000);
+
job_pause_point(&s->common.job);
}
@@ -856,11 +862,19 @@ enum test_job_result {
TEST_JOB_FAIL_PREPARE,
};
-static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
- enum test_job_result result)
+enum test_job_drain_node {
+ TEST_JOB_DRAIN_SRC,
+ TEST_JOB_DRAIN_SRC_CHILD,
+ TEST_JOB_DRAIN_SRC_PARENT,
+};
+
+static void test_blockjob_common_drain_node(enum drain_type drain_type,
+ bool use_iothread,
+ enum test_job_result result,
+ enum test_job_drain_node drain_node)
{
BlockBackend *blk_src, *blk_target;
- BlockDriverState *src, *target;
+ BlockDriverState *src, *src_backing, *src_overlay, *target, *drain_bs;
BlockJob *job;
TestBlockJob *tjob;
IOThread *iothread = NULL;
@@ -869,8 +883,32 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
src = bdrv_new_open_driver(&bdrv_test, "source", BDRV_O_RDWR,
&error_abort);
+ src_backing = bdrv_new_open_driver(&bdrv_test, "source-backing",
+ BDRV_O_RDWR, &error_abort);
+ src_overlay = bdrv_new_open_driver(&bdrv_test, "source-overlay",
+ BDRV_O_RDWR, &error_abort);
+
+ bdrv_set_backing_hd(src_overlay, src, &error_abort);
+ bdrv_unref(src);
+ bdrv_set_backing_hd(src, src_backing, &error_abort);
+ bdrv_unref(src_backing);
+
blk_src = blk_new(BLK_PERM_ALL, BLK_PERM_ALL);
- blk_insert_bs(blk_src, src, &error_abort);
+ blk_insert_bs(blk_src, src_overlay, &error_abort);
+
+ switch (drain_node) {
+ case TEST_JOB_DRAIN_SRC:
+ drain_bs = src;
+ break;
+ case TEST_JOB_DRAIN_SRC_CHILD:
+ drain_bs = src_backing;
+ break;
+ case TEST_JOB_DRAIN_SRC_PARENT:
+ drain_bs = src_overlay;
+ break;
+ default:
+ g_assert_not_reached();
+ }
if (use_iothread) {
iothread = iothread_new();
@@ -906,11 +944,21 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
job_start(&job->job);
aio_context_release(ctx);
+ if (use_iothread) {
+ /* job_co_entry() is run in the I/O thread, wait for the actual job
+ * code to start (we don't want to catch the job in the pause point in
+ * job_co_entry(). */
+ while (!tjob->running) {
+ aio_poll(qemu_get_aio_context(), false);
+ }
+ }
+
g_assert_cmpint(job->job.pause_count, ==, 0);
g_assert_false(job->job.paused);
+ g_assert_true(tjob->running);
g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */
- do_drain_begin_unlocked(drain_type, src);
+ do_drain_begin_unlocked(drain_type, drain_bs);
if (drain_type == BDRV_DRAIN_ALL) {
/* bdrv_drain_all() drains both src and target */
@@ -921,7 +969,7 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
g_assert_true(job->job.paused);
g_assert_false(job->job.busy); /* The job is paused */
- do_drain_end_unlocked(drain_type, src);
+ do_drain_end_unlocked(drain_type, drain_bs);
if (use_iothread) {
/* paused is reset in the I/O thread, wait for it */
@@ -969,7 +1017,7 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
blk_unref(blk_src);
blk_unref(blk_target);
- bdrv_unref(src);
+ bdrv_unref(src_overlay);
bdrv_unref(target);
if (iothread) {
@@ -977,6 +1025,19 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
}
}
+static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
+ enum test_job_result result)
+{
+ test_blockjob_common_drain_node(drain_type, use_iothread, result,
+ TEST_JOB_DRAIN_SRC);
+ test_blockjob_common_drain_node(drain_type, use_iothread, result,
+ TEST_JOB_DRAIN_SRC_CHILD);
+ if (drain_type == BDRV_SUBTREE_DRAIN) {
+ test_blockjob_common_drain_node(drain_type, use_iothread, result,
+ TEST_JOB_DRAIN_SRC_PARENT);
+ }
+}
+
static void test_blockjob_drain_all(void)
{
test_blockjob_common(BDRV_DRAIN_ALL, false, TEST_JOB_SUCCESS);
--
1.8.3.1

95
0100-block-rbd-pull-out-qemu_rbd_convert_options.patch Normal file
View File

@ -0,0 +1,95 @@
From 5fcd80dc34d84739e75e6d1ec5e21ad73af14ff9 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Wed, 10 Oct 2018 20:30:12 +0100
Subject: block/rbd: pull out qemu_rbd_convert_options
RH-Author: John Snow <jsnow@redhat.com>
Message-id: <20181010203015.11719-2-jsnow@redhat.com>
Patchwork-id: 82627
O-Subject: [RHEL8/rhel qemu-kvm PATCH 1/4] block/rbd: pull out qemu_rbd_convert_options
Bugzilla: 1635585
RH-Acked-by: Markus Armbruster <armbru@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Jeff Cody <jcody@redhat.com>
Code movement to pull the conversion from Qdict to BlockdevOptionsRbd
into a helper function.
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: 5b49a980f2cde6610ab1df41bb0277d00b5db893.1536704901.git.jcody@redhat.com
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit f24b03b56cdb28d753b4ff9ae210d555f14cb0d8)
Signed-off-by: John Snow <jsnow@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/rbd.c | 36 ++++++++++++++++++++++++------------
1 file changed, 24 insertions(+), 12 deletions(-)
diff --git a/block/rbd.c b/block/rbd.c
index ca8e5bb..b199450 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -655,12 +655,34 @@ failed_opts:
return r;
}
+static int qemu_rbd_convert_options(QDict *options, BlockdevOptionsRbd **opts,
+ Error **errp)
+{
+ Visitor *v;
+ Error *local_err = NULL;
+
+ /* Convert the remaining options into a QAPI object */
+ v = qobject_input_visitor_new_flat_confused(options, errp);
+ if (!v) {
+ return -EINVAL;
+ }
+
+ visit_type_BlockdevOptionsRbd(v, NULL, opts, &local_err);
+ visit_free(v);
+
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVRBDState *s = bs->opaque;
BlockdevOptionsRbd *opts = NULL;
- Visitor *v;
const QDictEntry *e;
Error *local_err = NULL;
char *keypairs, *secretid;
@@ -676,19 +698,9 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
qdict_del(options, "password-secret");
}
- /* Convert the remaining options into a QAPI object */
- v = qobject_input_visitor_new_flat_confused(options, errp);
- if (!v) {
- r = -EINVAL;
- goto out;
- }
-
- visit_type_BlockdevOptionsRbd(v, NULL, &opts, &local_err);
- visit_free(v);
-
+ r = qemu_rbd_convert_options(options, &opts, &local_err);
if (local_err) {
error_propagate(errp, local_err);
- r = -EINVAL;
goto out;
}
--
1.8.3.1

120
0101-block-rbd-Attempt-to-parse-legacy-filenames.patch Normal file
View File

@ -0,0 +1,120 @@
From 6198ce651b242298fa6f5cc7ba79eb168789899c Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Wed, 10 Oct 2018 20:30:13 +0100
Subject: block/rbd: Attempt to parse legacy filenames
RH-Author: John Snow <jsnow@redhat.com>
Message-id: <20181010203015.11719-3-jsnow@redhat.com>
Patchwork-id: 82629
O-Subject: [RHEL8/rhel qemu-kvm PATCH 2/4] block/rbd: Attempt to parse legacy filenames
Bugzilla: 1635585
RH-Acked-by: Markus Armbruster <armbru@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Jeff Cody <jcody@redhat.com>
When we converted rbd to get rid of the older key/value-centric
encoding format, we broke compatibility with image files with backing
file strings encoded in the old format.
This leaves a bit of an ugly conundrum, and a hacky solution.
If the initial attempt to parse the "proper" options fails, it assumes
that we may have an older key/value encoded filename. Fall back to
attempting to parse the filename, and extract the required options from
it. If that fails, pass along the original error message.
We do not support mixed modern usage alongside legacy keyvalue pair
usage.
A deprecation warning has been added, although care should be taken
when actually deprecating since the impact is not limited to
commandline or qapi usage, but also opening existing images.
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: 15b332e5432ad069441f7275a46080f465d789a0.1536704901.git.jcody@redhat.com
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit 084d1d13bdb753d558b991996e7686c077bd6d80)
Signed-off-by: John Snow <jsnow@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
block/rbd.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 52 insertions(+), 2 deletions(-)
diff --git a/block/rbd.c b/block/rbd.c
index b199450..014c68d 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -678,6 +678,33 @@ static int qemu_rbd_convert_options(QDict *options, BlockdevOptionsRbd **opts,
return 0;
}
+static int qemu_rbd_attempt_legacy_options(QDict *options,
+ BlockdevOptionsRbd **opts,
+ char **keypairs)
+{
+ char *filename;
+ int r;
+
+ filename = g_strdup(qdict_get_try_str(options, "filename"));
+ if (!filename) {
+ return -EINVAL;
+ }
+ qdict_del(options, "filename");
+
+ qemu_rbd_parse_filename(filename, options, NULL);
+
+ /* keypairs freed by caller */
+ *keypairs = g_strdup(qdict_get_try_str(options, "=keyvalue-pairs"));
+ if (*keypairs) {
+ qdict_del(options, "=keyvalue-pairs");
+ }
+
+ r = qemu_rbd_convert_options(options, opts, NULL);
+
+ g_free(filename);
+ return r;
+}
+
static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
@@ -700,8 +727,31 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
r = qemu_rbd_convert_options(options, &opts, &local_err);
if (local_err) {
- error_propagate(errp, local_err);
- goto out;
+ /* If keypairs are present, that means some options are present in
+ * the modern option format. Don't attempt to parse legacy option
+ * formats, as we won't support mixed usage. */
+ if (keypairs) {
+ error_propagate(errp, local_err);
+ goto out;
+ }
+
+ /* If the initial attempt to convert and process the options failed,
+ * we may be attempting to open an image file that has the rbd options
+ * specified in the older format consisting of all key/value pairs
+ * encoded in the filename. Go ahead and attempt to parse the
+ * filename, and see if we can pull out the required options. */
+ r = qemu_rbd_attempt_legacy_options(options, &opts, &keypairs);
+ if (r < 0) {
+ /* Propagate the original error, not the legacy parsing fallback
+ * error, as the latter was just a best-effort attempt. */
+ error_propagate(errp, local_err);
+ goto out;
+ }
+ /* Take care whenever deciding to actually deprecate; once this ability
+ * is removed, we will not be able to open any images with legacy-styled
+ * backing image strings. */
+ error_report("RBD options encoded in the filename as keyvalue pairs "
+ "is deprecated");
}
/* Remove the processed options from the QDict (the visitor processes
--
1.8.3.1

59
0102-block-rbd-add-deprecation-documentation-for-filename.patch Normal file
View File

@ -0,0 +1,59 @@
From aed464e31c9f6d92aa67960dc1a0891461393305 Mon Sep 17 00:00:00 2001
From: John Snow <jsnow@redhat.com>
Date: Tue, 11 Sep 2018 18:32:33 -0400
Subject: block/rbd: add deprecation documentation for filename keyvalue pairs
RH-Author: John Snow <jsnow@redhat.com>
Message-id: <20181010203015.11719-5-jsnow@redhat.com>
Patchwork-id: 82625
O-Subject: [RHEL8/rhel qemu-kvm PATCH 4/4] block/rbd: add deprecation docume
Bugzilla: 1635585
RH-Acked-by: Markus Armbruster <armbru@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
From: Jeff Cody <jcody@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: 647f5b5ab7efd8bf567a504c832b1d2d6f719b23.1536704901.git.jcody@re
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit 3bebd37e04f972775b1ece1bdda95451bc9fb14c)
Signed-off-by: John Snow <jsnow@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
Signed-off-by: John Snow <jsnow@redhat.com>
Rebase notes (3.0.0):
- Used upstream version
---
qemu-deprecated.texi | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/qemu-deprecated.texi b/qemu-deprecated.texi
index 9920a85..cff0e8b 100644
--- a/qemu-deprecated.texi
+++ b/qemu-deprecated.texi
@@ -227,6 +227,21 @@ from old QEMU versions anymore. A newer machine type should be used instead.
In order to prevent QEMU from automatically opening an image's backing
chain, use ``"backing": null'' instead.
+@subsubsection rbd keyvalue pair encoded filenames: "" (since 3.1.0)
+
+Options for ``rbd'' should be specified according to its runtime options,
+like other block drivers. Legacy parsing of keyvalue pair encoded
+filenames is useful to open images with the old format for backing files;
+These image files should be updated to use the current format.
+
+Example of legacy encoding:
+
+@code{json:@{"file.driver":"rbd", "file.filename":"rbd:rbd/name"@}}
+
+The above, converted to the current supported format:
+
+@code{json:@{"file.driver":"rbd", "file.pool":"rbd", "file.image":"name"@}}
+
@subsection vio-spapr-device device options
@subsubsection "irq": "" (since 3.0.0)
--
1.8.3.1

Some files were not shown because too many files have changed in this diff Show More