July 2024 - Devel - Libvirt List Archives

[PATCH] conf: virtiofs: add rlimit_nofile element

by Adam Julis

Add an element to configure the rlimit nofile size: ... <binary> <rlimit_nofile size='122333'/> </binary> ... Non-positive values are forbidden in 'domaincommon.rng'. Added separate test file, created by modifying the 'vhost-user-fs-fd-memory.xml'. Resolves: https://gitlab.com/libvirt/libvirt/-/issues/485 Signed-off-by: Adam Julis <ajulis(a)redhat.com> --- docs/formatdomain.rst | 4 ++ src/conf/domain_conf.c | 12 +++++ src/conf/domain_conf.h | 1 + src/conf/schemas/domaincommon.rng | 9 ++++ ...vhost-user-fs-fd-rlimit.x86_64-latest.args | 34 +++++++++++++ .../vhost-user-fs-fd-rlimit.x86_64-latest.xml | 50 +++++++++++++++++++ .../vhost-user-fs-fd-rlimit.xml | 50 +++++++++++++++++++ tests/qemuxmlconftest.c | 1 + 8 files changed, 161 insertions(+) create mode 100644 tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.x86_64-latest.args create mode 100644 tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.x86_64-latest.xml create mode 100644 tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.xml diff --git a/docs/formatdomain.rst b/docs/formatdomain.rst index ca33a2a570..10584dfe83 100644 --- a/docs/formatdomain.rst +++ b/docs/formatdomain.rst @@ -3734,6 +3734,10 @@ A directory on the host that can be accessed directly from the guest. The thread pool helps increase the number of requests in flight when used with storage that has a higher latency. However, it has an overhead, and so for fast, low latency filesystems, it may be best to turn it off. ( :since:`Since 8.5.0` ) + Element ``rlimit_profile`` accepts one attribute ``size`` which defines the + maximum number of file descriptors. Non-positive values are forbidden. + Although numbers greater than 1M are allowed, the virtiofsd documentation + states that in this case its set by virtiofsd to the 1M. ( :since:`Since 10.6.0` ) ``source`` The resource on the host that is being accessed in the guest. The ``name`` attribute must be used with ``type='template'``, and the ``dir`` attribute diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c index 32df908d95..6733857a3a 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -8868,6 +8868,7 @@ virDomainFSDefParseXML(virDomainXMLOption *xmlopt, g_autofree char *queue_size = virXPathString("string(./driver/@queue)", ctxt); g_autofree char *binary = virXPathString("string(./binary/@path)", ctxt); g_autofree char *thread_pool_size = virXPathString("string(./binary/thread_pool/@size)", ctxt); + g_autofree char *rlimit_nofile = virXPathString("string(./binary/rlimit_nofile/@size)", ctxt); xmlNodePtr binary_node = virXPathNode("./binary", ctxt); xmlNodePtr binary_lock_node = virXPathNode("./binary/lock", ctxt); xmlNodePtr binary_cache_node = virXPathNode("./binary/cache", ctxt); @@ -8891,6 +8892,14 @@ virDomainFSDefParseXML(virDomainXMLOption *xmlopt, goto error; } + if (rlimit_nofile && + virStrToLong_ull(rlimit_nofile, NULL, 10, &def->rlimit_nofile) < 0) { + virReportError(VIR_ERR_XML_ERROR, + _("cannot parse rlimit_nofile '%1$s' for virtiofs"), + rlimit_nofile); + goto error; + } + if (binary) def->binary = virFileSanitizePath(binary); @@ -23415,6 +23424,9 @@ virDomainFSDefFormat(virBuffer *buf, if (def->thread_pool_size >= 0) virBufferAsprintf(&binaryBuf, "<thread_pool size='%d'/>\n", def->thread_pool_size); + if (def->rlimit_nofile > 0) + virBufferAsprintf(&binaryBuf, "<rlimit_nofile size='%lld'/>\n", def->rlimit_nofile); + } virDomainVirtioOptionsFormat(&driverAttrBuf, def->virtio); diff --git a/src/conf/domain_conf.h b/src/conf/domain_conf.h index 0fcc4f1f9b..8283493dfc 100644 --- a/src/conf/domain_conf.h +++ b/src/conf/domain_conf.h @@ -890,6 +890,7 @@ struct _virDomainFSDef { bool symlinksResolved; char *binary; unsigned long long queue_size; + unsigned long long rlimit_nofile; virTristateSwitch xattr; virDomainFSCacheMode cache; virTristateSwitch posix_lock; diff --git a/src/conf/schemas/domaincommon.rng b/src/conf/schemas/domaincommon.rng index 2d23fcf123..ab5374d5f0 100644 --- a/src/conf/schemas/domaincommon.rng +++ b/src/conf/schemas/domaincommon.rng @@ -3380,6 +3380,15 @@ </optional> </element> </optional> + <optional> + <element name="rlimit_nofile"> + <optional> + <attribute name="size"> + <data type="positiveInteger"/> + </attribute> + </optional> + </element> + </optional> </interleave> </element> </define> diff --git a/tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.x86_64-latest.args b/tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.x86_64-latest.args new file mode 100644 index 0000000000..b4c2e3fe98 --- /dev/null +++ b/tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.x86_64-latest.args @@ -0,0 +1,34 @@ +LC_ALL=C \ +PATH=/bin \ +HOME=/var/lib/libvirt/qemu/domain--1-guest \ +USER=test \ +LOGNAME=test \ +XDG_DATA_HOME=/var/lib/libvirt/qemu/domain--1-guest/.local/share \ +XDG_CACHE_HOME=/var/lib/libvirt/qemu/domain--1-guest/.cache \ +XDG_CONFIG_HOME=/var/lib/libvirt/qemu/domain--1-guest/.config \ +/usr/bin/qemu-system-x86_64 \ +-name guest=guest,debug-threads=on \ +-S \ +-object '{"qom-type":"secret","id":"masterKey0","format":"raw","file":"/var/lib/libvirt/qemu/domain--1-guest/master-key.aes"}' \ +-machine pc,usb=off,dump-guest-core=off,acpi=off \ +-accel kvm \ +-cpu qemu64 \ +-m size=14680064k \ +-overcommit mem-lock=off \ +-smp 2,sockets=2,cores=1,threads=1 \ +-object '{"qom-type":"memory-backend-file","id":"ram-node0","mem-path":"/var/lib/libvirt/qemu/ram/-1-guest/ram-node0","share":true,"size":15032385536}' \ +-numa node,nodeid=0,cpus=0-1,memdev=ram-node0 \ +-uuid 126f2720-6f8e-45ab-a886-ec9277079a67 \ +-display none \ +-no-user-config \ +-nodefaults \ +-chardev socket,id=charmonitor,fd=1729,server=on,wait=off \ +-mon chardev=charmonitor,id=monitor,mode=control \ +-rtc base=utc \ +-no-shutdown \ +-boot strict=on \ +-chardev socket,id=chr-vu-fs0,path=/var/lib/libvirt/qemu/domain--1-guest/fs0-fs.sock \ +-device '{"driver":"vhost-user-fs-pci","id":"fs0","chardev":"chr-vu-fs0","queue-size":1027,"tag":"mount_tag","bus":"pci.0","addr":"0x2"}' \ +-audiodev '{"id":"audio1","driver":"none"}' \ +-sandbox on,obsolete=deny,elevateprivileges=deny,spawn=deny,resourcecontrol=deny \ +-msg timestamp=on diff --git a/tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.x86_64-latest.xml b/tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.x86_64-latest.xml new file mode 100644 index 0000000000..2983d3f275 --- /dev/null +++ b/tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.x86_64-latest.xml @@ -0,0 +1,50 @@ +<domain type='kvm'> + <name>guest</name> + <uuid>126f2720-6f8e-45ab-a886-ec9277079a67</uuid> + <memory unit='KiB'>14680064</memory> + <currentMemory unit='KiB'>14680064</currentMemory> + <memoryBacking> + <source type='file'/> + <access mode='shared'/> + </memoryBacking> + <vcpu placement='static'>2</vcpu> + <os> + <type arch='x86_64' machine='pc'>hvm</type> + <boot dev='hd'/> + </os> + <cpu mode='custom' match='exact' check='none'> + <model fallback='forbid'>qemu64</model> + <numa> + <cell id='0' cpus='0-1' memory='14680064' unit='KiB' memAccess='shared'/> + </numa> + </cpu> + <clock offset='utc'/> + <on_poweroff>destroy</on_poweroff> + <on_reboot>restart</on_reboot> + <on_crash>destroy</on_crash> + <devices> + <emulator>/usr/bin/qemu-system-x86_64</emulator> + <controller type='usb' index='0' model='none'/> + <controller type='pci' index='0' model='pci-root'/> + <filesystem type='mount' accessmode='passthrough'> + <driver type='virtiofs' queue='1027'/> + <binary xattr='on'> + <cache mode='always'/> + <sandbox mode='chroot'/> + <thread_pool size='16'/> + <rlimit_nofile size='122333'/> + </binary> + <idmap> + <uid start='0' target='100000' count='65535'/> + <gid start='0' target='100000' count='65535'/> + </idmap> + <source dir='/path'/> + <target dir='mount_tag'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x02' function='0x0'/> + </filesystem> + <input type='mouse' bus='ps2'/> + <input type='keyboard' bus='ps2'/> + <audio id='1' type='none'/> + <memballoon model='none'/> + </devices> +</domain> diff --git a/tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.xml b/tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.xml new file mode 100644 index 0000000000..2983d3f275 --- /dev/null +++ b/tests/qemuxmlconfdata/vhost-user-fs-fd-rlimit.xml @@ -0,0 +1,50 @@ +<domain type='kvm'> + <name>guest</name> + <uuid>126f2720-6f8e-45ab-a886-ec9277079a67</uuid> + <memory unit='KiB'>14680064</memory> + <currentMemory unit='KiB'>14680064</currentMemory> + <memoryBacking> + <source type='file'/> + <access mode='shared'/> + </memoryBacking> + <vcpu placement='static'>2</vcpu> + <os> + <type arch='x86_64' machine='pc'>hvm</type> + <boot dev='hd'/> + </os> + <cpu mode='custom' match='exact' check='none'> + <model fallback='forbid'>qemu64</model> + <numa> + <cell id='0' cpus='0-1' memory='14680064' unit='KiB' memAccess='shared'/> + </numa> + </cpu> + <clock offset='utc'/> + <on_poweroff>destroy</on_poweroff> + <on_reboot>restart</on_reboot> + <on_crash>destroy</on_crash> + <devices> + <emulator>/usr/bin/qemu-system-x86_64</emulator> + <controller type='usb' index='0' model='none'/> + <controller type='pci' index='0' model='pci-root'/> + <filesystem type='mount' accessmode='passthrough'> + <driver type='virtiofs' queue='1027'/> + <binary xattr='on'> + <cache mode='always'/> + <sandbox mode='chroot'/> + <thread_pool size='16'/> + <rlimit_nofile size='122333'/> + </binary> + <idmap> + <uid start='0' target='100000' count='65535'/> + <gid start='0' target='100000' count='65535'/> + </idmap> + <source dir='/path'/> + <target dir='mount_tag'/> + <address type='pci' domain='0x0000' bus='0x00' slot='0x02' function='0x0'/> + </filesystem> + <input type='mouse' bus='ps2'/> + <input type='keyboard' bus='ps2'/> + <audio id='1' type='none'/> + <memballoon model='none'/> + </devices> +</domain> diff --git a/tests/qemuxmlconftest.c b/tests/qemuxmlconftest.c index 389d31800b..2aaf6103db 100644 --- a/tests/qemuxmlconftest.c +++ b/tests/qemuxmlconftest.c @@ -2814,6 +2814,7 @@ mymain(void) DO_TEST_CAPS_ARCH_LATEST("launch-security-s390-pv", "s390x"); DO_TEST_CAPS_LATEST("vhost-user-fs-fd-memory"); + DO_TEST_CAPS_LATEST("vhost-user-fs-fd-rlimit"); DO_TEST_CAPS_LATEST("vhost-user-fs-hugepages"); DO_TEST_CAPS_LATEST_PARSE_ERROR("vhost-user-fs-readonly"); -- 2.45.2

8 months, 3 weeks

3
2
0 / 0

[PATCH v2 0/1] Expose availability of SEV-ES

by Takashi Kajinami

This introduces the new "model" field in sev elements so that clients can check whether SEV-ES, the 2nd generation of AMD SEV, is available in the taget hyprvisor. There is the maxESGuests field (along with the maxGuests field) but this field does not explain whether SEV-ES is actually enabled in KVM. Takashi Kajinami (1): Expose available AMD SEV models in domain capabilities Changes since v1: * Fixed one code path where available models are not added * Fixed missing update of "report" flag * Updated the documentation to explain the new model field in addition to the existing but undocumanted cpu0Id field Takashi Kajinami (1): Expose available AMD SEV models in domain capabilities docs/formatdomaincaps.rst | 5 ++ src/conf/domain_capabilities.c | 2 + src/conf/domain_capabilities.h | 1 + src/conf/domain_conf.c | 7 +++ src/conf/domain_conf.h | 8 ++++ src/qemu/qemu_capabilities.c | 84 +++++++++++++++++++++++++--------- 6 files changed, 85 insertions(+), 22 deletions(-) -- 2.43.0

8 months, 3 weeks

2
3
0 / 0

[PATCH 0/2] Add Granite Rapids cpu model

by Tim Wiederhake

Also, update the sync tool with new features introduced in qemu. Tim Wiederhake (2): sync_qemu_models_i386.py: Add missing features cpu_map: Add GraniteRapids CPU model src/cpu_map/index.xml | 1 + src/cpu_map/meson.build | 1 + src/cpu_map/sync_qemu_models_i386.py | 5 + src/cpu_map/x86_GraniteRapids.xml | 200 ++++++++++++++++++ .../domaincapsdata/qemu_8.1.0-q35.x86_64.xml | 1 + .../domaincapsdata/qemu_8.1.0-tcg.x86_64.xml | 1 + tests/domaincapsdata/qemu_8.1.0.x86_64.xml | 1 + .../domaincapsdata/qemu_8.2.0-q35.x86_64.xml | 1 + .../domaincapsdata/qemu_8.2.0-tcg.x86_64.xml | 1 + tests/domaincapsdata/qemu_8.2.0.x86_64.xml | 1 + .../domaincapsdata/qemu_9.0.0-q35.x86_64.xml | 1 + .../domaincapsdata/qemu_9.0.0-tcg.x86_64.xml | 1 + tests/domaincapsdata/qemu_9.0.0.x86_64.xml | 1 + .../domaincapsdata/qemu_9.1.0-q35.x86_64.xml | 1 + .../domaincapsdata/qemu_9.1.0-tcg.x86_64.xml | 1 + tests/domaincapsdata/qemu_9.1.0.x86_64.xml | 1 + 16 files changed, 219 insertions(+) create mode 100644 src/cpu_map/x86_GraniteRapids.xml -- 2.43.0

8 months, 3 weeks

2
3
0 / 0

[PATCH] cpu_map: Add libcpuinfo as optional data source

by Tim Wiederhake

This adds an option to use libcpuinfo [1] as data source for libvirt's list of x86 cpu features. This is purely optional and does not change the script's behavior if libcpuinfo is not installed. libcpuinfo is a cross-vendor, cross-architecture source for CPU related information that has the capability to replace libvirt's dependence on qemu's cpu feature list. [1] https://gitlab.com/twiederh/libcpuinfo Signed-off-by: Tim Wiederhake <twiederh(a)redhat.com> --- src/cpu_map/libcpuinfo_aliases.xml | 75 +++++++++++++++++++++++++ src/cpu_map/sync_qemu_features_i386.py | 77 +++++++++++++++++++++++--- 2 files changed, 145 insertions(+), 7 deletions(-) create mode 100644 src/cpu_map/libcpuinfo_aliases.xml diff --git a/src/cpu_map/libcpuinfo_aliases.xml b/src/cpu_map/libcpuinfo_aliases.xml new file mode 100644 index 0000000000..75d243fead --- /dev/null +++ b/src/cpu_map/libcpuinfo_aliases.xml @@ -0,0 +1,75 @@ + + +<external_aliases> + <external_alias> + <type>feature</type> + <canonical>pclmulqdq</canonical> + <name>pclmuldq</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>ds-cpl</canonical> + <name>ds_cpl</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>sse4-1</canonical> + <name>sse4.1</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>sse4-2</canonical> + <name>sse4.2</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>tsc-adjust</canonical> + <name>tsc_adjust</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>lahf-lm</canonical> + <name>lahf_lm</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>cmp-legacy</canonical> + <name>cmp_legacy</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>nodeid-msr</canonical> + <name>nodeid_msr</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>perfctr-core</canonical> + <name>perfctr_core</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>perfctr-nb</canonical> + <name>perfctr_nb</name> + <domain>libvirt</domain> + </external_alias> + <external_alias> + <type>feature</type> + <canonical>fxsr-opt</canonical> + <name>fxsr_opt</name> + <domain>libvirt</domain> + </external_alias> +</external_aliases> diff --git a/src/cpu_map/sync_qemu_features_i386.py b/src/cpu_map/sync_qemu_features_i386.py index e4b1f7275a..3b3ad5a643 100755 --- a/src/cpu_map/sync_qemu_features_i386.py +++ b/src/cpu_map/sync_qemu_features_i386.py @@ -4,6 +4,11 @@ import argparse import os import re +try: + import pycpuinfo +except ImportError: + pycpuinfo = None + # features in qemu that we do not want in libvirt FEATURES_IGNORE = ( @@ -22,6 +27,7 @@ FEATURES_IGNORE = ( "kvm-steal-time", "kvmclock", "kvmclock-stable-bit", + "kvmclock2", "xstore", "xstore-en", @@ -295,6 +301,53 @@ def add_feature_qemu(query, data): add_feature_cpuid(eax, ecx, reg, bit, name) +def add_features_cpuinfo(): + def decode_bit(value): + for i in range(0, 64): + if value == (1 << i): + return i + + def decode_cpuid(v): + if v[0] != 0 and v[1] == 0 and v[2] == 0 and v[3] == 0: + reg, val = "eax", v[0] + if v[0] == 0 and v[1] != 0 and v[2] == 0 and v[3] == 0: + reg, val = "ebx", v[1] + if v[0] == 0 and v[1] == 0 and v[2] != 0 and v[3] == 0: + reg, val = "ecx", v[2] + if v[0] == 0 and v[1] == 0 and v[2] == 0 and v[3] != 0: + reg, val = "edx", v[3] + + return reg, decode_bit(val) + + x86 = pycpuinfo.Family.find("x86", "") + + for feature in pycpuinfo.features(): + if feature.family() != x86: + continue + + if list(feature.features()): + continue + + name = feature.name("libvirt") + if name in FEATURES_IGNORE: + continue + + cpuid = feature.extra_x86_cpuid() + if cpuid: + eax = cpuid[0] + ecx = cpuid[1] + if ecx == pycpuinfo.x86.CPUINFO_X86_CPUID_ECX_NONE: + ecx = None + reg, bit = decode_cpuid(cpuid[2:]) + add_feature_cpuid(eax, ecx, reg, bit, name) + + msr = feature.extra_x86_msr() + if msr: + index = msr[0] + bit = decode_bit(msr[1] | (msr[2] << 32)) + add_feature_msr(index, bit, name) + + # read the `feature_word_info` struct from qemu's cpu.c into a list of strings def read_cpu_c(path): pattern_comment = re.compile("/\\*.*?\\*/") @@ -450,6 +503,12 @@ def main(): nargs="?", type=os.path.realpath, ) + if pycpuinfo: + parser.add_argument( + "--libcpuinfo", + help="Use libcpuinfo as data source instead", + action="store_true", + ) parser.add_argument( "--output", "-o", @@ -459,14 +518,18 @@ def main(): ) args = parser.parse_args() - if not os.path.isdir(args.qemu): - parser.print_help() - exit("qemu source directory not found") + if pycpuinfo and args.libcpuinfo: + add_features_cpuinfo() + else: + if not os.path.isdir(args.qemu): + parser.print_help() + exit("qemu source directory not found") + + read_headers(args.qemu) + lines = read_cpu_c(args.qemu) + parse_feature_words(lines) + add_extra_features() - read_headers(args.qemu) - lines = read_cpu_c(args.qemu) - parse_feature_words(lines) - add_extra_features() write_output(args.output) print( -- 2.43.0

8 months, 3 weeks

2
2
0 / 0

[PATCH] formatstorage: Document qcow2 default version change

by Peter Krempa

Based on discussion after commit f432114d9c was pushed it was pointed out that the documentation still mentions the older version. Fix the documentation to state the new version and introduce ambiguity for future updates. Fixes: f432114d9cf507a4047aa9dc1344b1c13356db08 Signed-off-by: Peter Krempa <pkrempa(a)redhat.com> --- Posting this documentation update to document what happened rather than introduce (almost pointless) complication in adding a config file which is unlikely to be ever used. docs/formatstorage.rst | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/docs/formatstorage.rst b/docs/formatstorage.rst index 86e167d9cb..9d9a4143eb 100644 --- a/docs/formatstorage.rst +++ b/docs/formatstorage.rst @@ -700,10 +700,15 @@ host filesystem. It can contain the following child elements: Encryption <formatstorageencryption.html>`__ page for more information. ``compat`` Specify compatibility level. So far, this is only used for ``type='qcow2'`` - volumes. Valid values are ``0.10`` and ``1.1`` so far, specifying QEMU - version the images should be compatible with. If the ``feature`` element is - present, 1.1 is used. :since:`Since 1.1.0` If omitted, 0.10 is used. - :since:`Since 1.1.2` + volumes. Valid values are ``0.10`` (QCOW2 v2) and ``1.1`` (QCOW2 v3) so far. + The values were meant to specify QEMU version the images should be compatible + with. + + The default, if the ``feature`` element is present is ``1.1``. :since:`Since 1.1.0` + If ``feature`` is not present, ``0.10`` was used :since:`Since 1.1.2` and + :since:`Since 10.2.0` ``1.1`` is used as it's the default of ``qemu-img``. + + Any tool depending on a specific version should specify this field explicitly. ``nocow`` Turn off COW of the newly created volume. So far, this is only valid for a file image in btrfs file system. It will improve performance when the file -- 2.44.0

8 months, 3 weeks

2
1
0 / 0

Plans for 10.6.0 release (freeze on Monday 29 Jul)

by Jiri Denemark

We are getting close to 10.6.0 release of libvirt. Since I'll be away from computers next week, I suggest moving the "last week in a month" freeze a bit and aim for the release on Monday 05 Aug after entering the freeze on Monday 29 Jul. There will be no RC2 this time. I hope this works for everyone. Jirka

8 months, 3 weeks

1
0
0 / 0

[PATCH v2] qemu: add a monitor to /proc/$pid when killing times out

by Boris Fiuczynski

In cases when a QEMU process takes longer than the time sigterm and sigkill are issued to kill the process do not simply fail and leave the VM in state VIR_DOMAIN_SHUTDOWN until the daemon stops. Instead set up an fd on /proc/$pid and get notified when the QEMU process finally has terminated to cleanup the VM state. Resolves: https://issues.redhat.com/browse/RHEL-28819 Signed-off-by: Boris Fiuczynski <fiuczy(a)linux.ibm.com> --- src/qemu/qemu_domain.c | 8 +++ src/qemu/qemu_domain.h | 2 + src/qemu/qemu_driver.c | 18 +++++++ src/qemu/qemu_process.c | 115 ++++++++++++++++++++++++++++++++++++++-- src/qemu/qemu_process.h | 1 + 5 files changed, 139 insertions(+), 5 deletions(-) diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index 2134b11038..8147ff02fd 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -1889,6 +1889,11 @@ qemuDomainObjPrivateFree(void *data) virChrdevFree(priv->devs); + if (priv->pidMonitored >= 0) { + virEventRemoveHandle(priv->pidMonitored); + priv->pidMonitored = -1; + } + /* This should never be non-NULL if we get here, but just in case... */ if (priv->mon) { VIR_ERROR(_("Unexpected QEMU monitor still active during domain deletion")); @@ -1934,6 +1939,8 @@ qemuDomainObjPrivateAlloc(void *opaque) priv->blockjobs = virHashNew(virObjectUnref); priv->fds = virHashNew(g_object_unref); + priv->pidMonitored = -1; + /* agent commands block by default, user can choose different behavior */ priv->agentTimeout = VIR_DOMAIN_AGENT_RESPONSE_TIMEOUT_BLOCK; priv->migMaxBandwidth = QEMU_DOMAIN_MIG_BANDWIDTH_MAX; @@ -11680,6 +11687,7 @@ qemuProcessEventFree(struct qemuProcessEvent *event) case QEMU_PROCESS_EVENT_RESET: case QEMU_PROCESS_EVENT_NBDKIT_EXITED: case QEMU_PROCESS_EVENT_MONITOR_EOF: + case QEMU_PROCESS_EVENT_SHUTDOWN_COMPLETED: case QEMU_PROCESS_EVENT_LAST: break; } diff --git a/src/qemu/qemu_domain.h b/src/qemu/qemu_domain.h index d777559119..a5092dd7f0 100644 --- a/src/qemu/qemu_domain.h +++ b/src/qemu/qemu_domain.h @@ -119,6 +119,7 @@ struct _qemuDomainObjPrivate { bool beingDestroyed; char *pidfile; + int pidMonitored; virDomainPCIAddressSet *pciaddrs; virDomainUSBAddressSet *usbaddrs; @@ -469,6 +470,7 @@ typedef enum { QEMU_PROCESS_EVENT_UNATTENDED_MIGRATION, QEMU_PROCESS_EVENT_RESET, QEMU_PROCESS_EVENT_NBDKIT_EXITED, + QEMU_PROCESS_EVENT_SHUTDOWN_COMPLETED, QEMU_PROCESS_EVENT_LAST } qemuProcessEventType; diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index 9f3013e231..6b1e4084f6 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -4041,6 +4041,21 @@ processNbdkitExitedEvent(virDomainObj *vm, } +static void +processShutdownCompletedEvent(virQEMUDriver *driver, + virDomainObj *vm) +{ + if (virDomainObjBeginJob(vm, VIR_JOB_MODIFY) < 0) + return; + + if (virDomainObjIsActive(vm)) + qemuProcessStop(driver, vm, VIR_DOMAIN_SHUTOFF_UNKNOWN, + VIR_ASYNC_JOB_NONE, 0); + + virDomainObjEndJob(vm); +} + + static void qemuProcessEventHandler(void *data, void *opaque) { struct qemuProcessEvent *processEvent = data; @@ -4101,6 +4116,9 @@ static void qemuProcessEventHandler(void *data, void *opaque) case QEMU_PROCESS_EVENT_NBDKIT_EXITED: processNbdkitExitedEvent(vm, processEvent->data); break; + case QEMU_PROCESS_EVENT_SHUTDOWN_COMPLETED: + processShutdownCompletedEvent(driver, vm); + break; case QEMU_PROCESS_EVENT_LAST: break; } diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 25dfd04272..86ca495a20 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -25,6 +25,7 @@ #include <unistd.h> #include <signal.h> #include <sys/stat.h> +#include <sys/syscall.h> #if defined(__linux__) # include <linux/capability.h> #elif defined(__FreeBSD__) @@ -8387,9 +8388,107 @@ qemuProcessCreatePretendCmdBuild(virDomainObj *vm, } +typedef struct { + virDomainObj *vm; + int pidfd; +} qemuProcessInShutdownEventData; + + +static qemuProcessInShutdownEventData* +qemuProcessInShutdownEventDataNew(virDomainObj *vm, int pidfd) +{ + qemuProcessInShutdownEventData *d = g_new(qemuProcessInShutdownEventData, 1); + d->vm = virObjectRef(vm); + d->pidfd = pidfd; + return d; +} + + +static void +qemuProcessInShutdownEventDataFree(qemuProcessInShutdownEventData *d) +{ + virObjectUnref(d->vm); + VIR_FORCE_CLOSE(d->pidfd); + g_free(d); +} + + +static void +qemuProcessInShutdownPidfdCb(int watch, + int fd, + int events G_GNUC_UNUSED, + void *opaque) +{ + qemuProcessInShutdownEventData *data = opaque; + virDomainObj *vm = data->vm; + + VIR_DEBUG("vm=%p name=%s pid=%lld fd=%d", + vm, vm->def->name, (long long)vm->pid, fd); + + virEventRemoveHandle(watch); + + virObjectLock(vm); + + VIR_INFO("QEMU process %lld finally completed termination", + (long long)vm->pid); + + QEMU_DOMAIN_PRIVATE(vm)->pidMonitored = -1; + qemuProcessEventSubmit(vm, QEMU_PROCESS_EVENT_SHUTDOWN_COMPLETED, + 0, 0, NULL); + + virObjectUnlock(vm); +} + + +static int +qemuProcessInShutdownStartMonitor(virDomainObj *vm) +{ + qemuDomainObjPrivate *priv = vm->privateData; + qemuProcessInShutdownEventData *data; + int pidfd; + int ret = -1; + + VIR_DEBUG("vm=%p name=%s pid=%lld pidMonitored=%d", + vm, vm->def->name, (long long)vm->pid, + priv->pidMonitored); + + if (priv->pidMonitored >= 0) { + VIR_DEBUG("Monitoring qemu in-shutdown process %i already set up", vm->pid); + goto cleanup; + } + + pidfd = syscall(SYS_pidfd_open, vm->pid, 0); + if (pidfd < 0) { + if (errno == ESRCH) /* process has already terminated */ + ret = 1; + goto cleanup; + } + + data = qemuProcessInShutdownEventDataNew(vm, pidfd); + if ((priv->pidMonitored = virEventAddHandle(pidfd, + VIR_EVENT_HANDLE_READABLE, + qemuProcessInShutdownPidfdCb, + data, + (virFreeCallback)qemuProcessInShutdownEventDataFree)) < 0) { + virReportError(VIR_ERR_INTERNAL_ERROR, + _("failed to monitor qemu in-shutdown process %1$i"), + vm->pid); + qemuProcessInShutdownEventDataFree(data); + goto cleanup; + } + VIR_DEBUG("Monitoring qemu in-shutdown process %i for termination", vm->pid); + ret = 0; + + cleanup: + return ret; +} + + int qemuProcessKill(virDomainObj *vm, unsigned int flags) { + int ret = -1; + VIR_DEBUG("vm=%p name=%s pid=%lld flags=0x%x", vm, vm->def->name, (long long)vm->pid, flags); @@ -8410,10 +8509,16 @@ qemuProcessKill(virDomainObj *vm, unsigned int flags) /* Request an extra delay of two seconds per current nhostdevs * to be safe against stalls by the kernel freeing up the resources */ - return virProcessKillPainfullyDelay(vm->pid, - !!(flags & VIR_QEMU_PROCESS_KILL_FORCE), - vm->def->nhostdevs * 2, - false); + ret = virProcessKillPainfullyDelay(vm->pid, + !!(flags & VIR_QEMU_PROCESS_KILL_FORCE), + vm->def->nhostdevs * 2, + false); + + if (ret < 0 && (flags & VIR_QEMU_PROCESS_KILL_MONITOR_ON_ERROR)) + if (qemuProcessInShutdownStartMonitor(vm) == 1) + ret = 0; /* process termination detected */ + + return ret; } @@ -8438,7 +8543,7 @@ qemuProcessBeginStopJob(virDomainObj *vm, * cleared inside qemuProcessStop */ priv->beingDestroyed = true; - if (qemuProcessKill(vm, killFlags) < 0) + if (qemuProcessKill(vm, killFlags|VIR_QEMU_PROCESS_KILL_MONITOR_ON_ERROR) < 0) goto error; /* Wake up anything waiting on domain condition */ diff --git a/src/qemu/qemu_process.h b/src/qemu/qemu_process.h index cb67bfcd2d..2324aeb7bd 100644 --- a/src/qemu/qemu_process.h +++ b/src/qemu/qemu_process.h @@ -180,6 +180,7 @@ typedef enum { VIR_QEMU_PROCESS_KILL_FORCE = 1 << 0, VIR_QEMU_PROCESS_KILL_NOWAIT = 1 << 1, VIR_QEMU_PROCESS_KILL_NOCHECK = 1 << 2, /* bypass the running vm check */ + VIR_QEMU_PROCESS_KILL_MONITOR_ON_ERROR = 1 << 3, /* on error enable process monitor */ } virQemuProcessKillMode; int qemuProcessKill(virDomainObj *vm, unsigned int flags); -- 2.45.0

8 months, 4 weeks

2
2
0 / 0

[PATCH] security: AppArmor allow write when os loader readonly=no

by Miroslav Los

Since libvirt commit 3ef9b51b10e52886e8fe8d75e36d0714957616b7, the pflash storage for the os loader file follows its read-only flag, and qemu tries to open the file for writing if set so. This patches virt-aa-helper to generate the VM's AppArmor rules that allow this, using the same domain definition flag and default. Signed-off-by: Miroslav Los <mirlos(a)cisco.com> --- src/security/virt-aa-helper.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/src/security/virt-aa-helper.c b/src/security/virt-aa-helper.c index 0374581f07..2f57664a4c 100644 --- a/src/security/virt-aa-helper.c +++ b/src/security/virt-aa-helper.c @@ -1001,9 +1001,14 @@ get_files(vahControl * ctl) if (vah_add_file(&buf, ctl->def->os.slic_table, "r") != 0) goto cleanup; - if (ctl->def->os.loader && ctl->def->os.loader->path) - if (vah_add_file(&buf, ctl->def->os.loader->path, "rk") != 0) + if (ctl->def->os.loader && ctl->def->os.loader->path) { + bool readonly = false; + virTristateBoolToBool(ctl->def->os.loader->readonly, &readonly); + if (vah_add_file(&buf, + ctl->def->os.loader->path, + readonly ? "rk" : "rwk") != 0) goto cleanup; + } if (ctl->def->os.loader && ctl->def->os.loader->nvram) { if (storage_source_add_files(ctl->def->os.loader->nvram, &buf, 0) < 0) -- 2.25.1

8 months, 4 weeks

4
8
0 / 0

[PATCH 0/2] Warn on pthread errors

by Tim Wiederhake

libvirt currently exhibits undefined behavior due to pthread mutex misuse, e.g. destroying a locked mutex or attempting to unlock an already unlocked mutex. Add a warning if such a case is detected, so we can start on fixing the issues. Tim Wiederhake (2): virMutex: Warn on error DO NOT MERGE: virMutex: Fail loudly src/util/virthread.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) -- 2.43.0

9 months

3
8
0 / 0

[PATCH] qemu: add a monitor to /proc/$pid when killing times out

by Boris Fiuczynski

In cases when a QEMU process takes longer than the time sigterm and sigkill are issued to kill the process do not simply fail and leave the VM in state VIR_DOMAIN_SHUTDOWN until the daemon stops. Instead set up an fd on /proc/$pid and get notified when the QEMU process finally has terminated to cleanup the VM state. Resolves: https://issues.redhat.com/browse/RHEL-28819 Signed-off-by: Boris Fiuczynski <fiuczy(a)linux.ibm.com> --- src/qemu/qemu_domain.c | 8 +++ src/qemu/qemu_domain.h | 2 + src/qemu/qemu_driver.c | 18 ++++++ src/qemu/qemu_process.c | 127 ++++++++++++++++++++++++++++++++++++++-- src/qemu/qemu_process.h | 1 + 5 files changed, 151 insertions(+), 5 deletions(-) diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index 2134b11038..96f4e41a11 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -1889,6 +1889,11 @@ qemuDomainObjPrivateFree(void *data) virChrdevFree(priv->devs); + if (priv->watchPid >= 0) { + virEventRemoveHandle(priv->watchPid); + priv->watchPid = -1; + } + /* This should never be non-NULL if we get here, but just in case... */ if (priv->mon) { VIR_ERROR(_("Unexpected QEMU monitor still active during domain deletion")); @@ -1934,6 +1939,8 @@ qemuDomainObjPrivateAlloc(void *opaque) priv->blockjobs = virHashNew(virObjectUnref); priv->fds = virHashNew(g_object_unref); + priv->watchPid = -1; + /* agent commands block by default, user can choose different behavior */ priv->agentTimeout = VIR_DOMAIN_AGENT_RESPONSE_TIMEOUT_BLOCK; priv->migMaxBandwidth = QEMU_DOMAIN_MIG_BANDWIDTH_MAX; @@ -11680,6 +11687,7 @@ qemuProcessEventFree(struct qemuProcessEvent *event) case QEMU_PROCESS_EVENT_RESET: case QEMU_PROCESS_EVENT_NBDKIT_EXITED: case QEMU_PROCESS_EVENT_MONITOR_EOF: + case QEMU_PROCESS_EVENT_SHUTDOWN_COMPLETED: case QEMU_PROCESS_EVENT_LAST: break; } diff --git a/src/qemu/qemu_domain.h b/src/qemu/qemu_domain.h index d777559119..e5366c6e8c 100644 --- a/src/qemu/qemu_domain.h +++ b/src/qemu/qemu_domain.h @@ -119,6 +119,7 @@ struct _qemuDomainObjPrivate { bool beingDestroyed; char *pidfile; + int watchPid; virDomainPCIAddressSet *pciaddrs; virDomainUSBAddressSet *usbaddrs; @@ -469,6 +470,7 @@ typedef enum { QEMU_PROCESS_EVENT_UNATTENDED_MIGRATION, QEMU_PROCESS_EVENT_RESET, QEMU_PROCESS_EVENT_NBDKIT_EXITED, + QEMU_PROCESS_EVENT_SHUTDOWN_COMPLETED, QEMU_PROCESS_EVENT_LAST } qemuProcessEventType; diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index 9f3013e231..6b1e4084f6 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -4041,6 +4041,21 @@ processNbdkitExitedEvent(virDomainObj *vm, } +static void +processShutdownCompletedEvent(virQEMUDriver *driver, + virDomainObj *vm) +{ + if (virDomainObjBeginJob(vm, VIR_JOB_MODIFY) < 0) + return; + + if (virDomainObjIsActive(vm)) + qemuProcessStop(driver, vm, VIR_DOMAIN_SHUTOFF_UNKNOWN, + VIR_ASYNC_JOB_NONE, 0); + + virDomainObjEndJob(vm); +} + + static void qemuProcessEventHandler(void *data, void *opaque) { struct qemuProcessEvent *processEvent = data; @@ -4101,6 +4116,9 @@ static void qemuProcessEventHandler(void *data, void *opaque) case QEMU_PROCESS_EVENT_NBDKIT_EXITED: processNbdkitExitedEvent(vm, processEvent->data); break; + case QEMU_PROCESS_EVENT_SHUTDOWN_COMPLETED: + processShutdownCompletedEvent(driver, vm); + break; case QEMU_PROCESS_EVENT_LAST: break; } diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 25dfd04272..d6dbd7ba53 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -25,6 +25,7 @@ #include <unistd.h> #include <signal.h> #include <sys/stat.h> +#include <sys/syscall.h> #if defined(__linux__) # include <linux/capability.h> #elif defined(__FreeBSD__) @@ -8387,9 +8388,119 @@ qemuProcessCreatePretendCmdBuild(virDomainObj *vm, } +typedef struct { + virDomainObj *vm; + int pidfd; +} qemuProcessInShutdownEventData; + + +static qemuProcessInShutdownEventData* +qemuProcessInShutdownEventDataNew(virDomainObj *vm, int pidfd) +{ + qemuProcessInShutdownEventData *d = g_new(qemuProcessInShutdownEventData, 1); + d->vm = virObjectRef(vm); + d->pidfd = pidfd; + return d; +} + + +static void +qemuProcessInShutdownEventDataFree(qemuProcessInShutdownEventData *d) +{ + virObjectUnref(d->vm); + VIR_FORCE_CLOSE(d->pidfd); + g_free(d); +} + + +static void +qemuProcessInShutdownStopMonitor(virDomainObj *vm) +{ + qemuDomainObjPrivate *priv = vm->privateData; + + VIR_DEBUG("vm=%p name=%s pid=%lld watchPid=%d", + vm, vm->def->name, (long long)vm->pid, + priv->watchPid); + + virObjectLock(vm); + if (priv->watchPid >= 0) { + virEventRemoveHandle(priv->watchPid); + priv->watchPid = -1; + } + virObjectUnlock(vm); +} + + +static void +qemuProcessInShutdownPidfdCb(int watch G_GNUC_UNUSED, + int fd, + int events G_GNUC_UNUSED, + void *opaque) +{ + qemuProcessInShutdownEventData *data = opaque; + virDomainObj *vm = data->vm; + + VIR_DEBUG("vm=%p name=%s pid=%lld fd=%d", + vm, vm->def->name, (long long)vm->pid, fd); + + VIR_DEBUG("QEMU process %lld finally completed termination", + (long long)vm->pid); + qemuProcessInShutdownStopMonitor(vm); + + qemuProcessEventSubmit(vm, QEMU_PROCESS_EVENT_SHUTDOWN_COMPLETED, + 0, 0, NULL); +} + + +static int +qemuProcessInShutdownStartMonitor(virDomainObj *vm) +{ + qemuDomainObjPrivate *priv = vm->privateData; + qemuProcessInShutdownEventData *data; + int pidfd; + int ret = -1; + + VIR_DEBUG("vm=%p name=%s pid=%lld watchPid=%d", + vm, vm->def->name, (long long)vm->pid, + priv->watchPid); + + if (priv->watchPid >= 0) { + VIR_DEBUG("Monitoring qemu in-shutdown process %i already set up", vm->pid); + goto cleanup; + } + + pidfd = syscall(SYS_pidfd_open, vm->pid, 0); + if (pidfd < 0) { + if (errno == ESRCH) /* process has already terminated */ + ret = 1; + goto cleanup; + } + + data = qemuProcessInShutdownEventDataNew(vm, pidfd); + if ((priv->watchPid = virEventAddHandle(pidfd, + VIR_EVENT_HANDLE_READABLE, + qemuProcessInShutdownPidfdCb, + data, + (virFreeCallback)qemuProcessInShutdownEventDataFree)) < 0) { + virReportError(VIR_ERR_INTERNAL_ERROR, + _("failed to monitor qemu in-shutdown process %1$i"), + vm->pid); + qemuProcessInShutdownEventDataFree(data); + goto cleanup; + } + VIR_DEBUG("Monitoring qemu in-shutdown process %i for termination", vm->pid); + ret = 0; + + cleanup: + return ret; +} + + int qemuProcessKill(virDomainObj *vm, unsigned int flags) { + int ret = -1; + VIR_DEBUG("vm=%p name=%s pid=%lld flags=0x%x", vm, vm->def->name, (long long)vm->pid, flags); @@ -8410,10 +8521,16 @@ qemuProcessKill(virDomainObj *vm, unsigned int flags) /* Request an extra delay of two seconds per current nhostdevs * to be safe against stalls by the kernel freeing up the resources */ - return virProcessKillPainfullyDelay(vm->pid, - !!(flags & VIR_QEMU_PROCESS_KILL_FORCE), - vm->def->nhostdevs * 2, - false); + ret = virProcessKillPainfullyDelay(vm->pid, + !!(flags & VIR_QEMU_PROCESS_KILL_FORCE), + vm->def->nhostdevs * 2, + false); + + if (ret < 0 && (flags & VIR_QEMU_PROCESS_KILL_MONITOR_ON_ERROR)) + if (qemuProcessInShutdownStartMonitor(vm) == 1) + ret = 0; /* process termination detected */ + + return ret; } @@ -8438,7 +8555,7 @@ qemuProcessBeginStopJob(virDomainObj *vm, * cleared inside qemuProcessStop */ priv->beingDestroyed = true; - if (qemuProcessKill(vm, killFlags) < 0) + if (qemuProcessKill(vm, killFlags|VIR_QEMU_PROCESS_KILL_MONITOR_ON_ERROR) < 0) goto error; /* Wake up anything waiting on domain condition */ diff --git a/src/qemu/qemu_process.h b/src/qemu/qemu_process.h index cb67bfcd2d..2324aeb7bd 100644 --- a/src/qemu/qemu_process.h +++ b/src/qemu/qemu_process.h @@ -180,6 +180,7 @@ typedef enum { VIR_QEMU_PROCESS_KILL_FORCE = 1 << 0, VIR_QEMU_PROCESS_KILL_NOWAIT = 1 << 1, VIR_QEMU_PROCESS_KILL_NOCHECK = 1 << 2, /* bypass the running vm check */ + VIR_QEMU_PROCESS_KILL_MONITOR_ON_ERROR = 1 << 3, /* on error enable process monitor */ } virQemuProcessKillMode; int qemuProcessKill(virDomainObj *vm, unsigned int flags); -- 2.45.0

9 months

1
0
0 / 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

Devel July 2024