import CS qemu-kvm-6.2.0-49.module_el8+991+097e156d

.gitignore

@@ -1 +1,5 @@
 SOURCES/qemu-6.2.0.tar.xz
+SOURCES/tests_data_acpi_pc_SSDT.dimmpxm
+SOURCES/tests_data_acpi_q35_FACP.slic
+SOURCES/tests_data_acpi_q35_SSDT.dimmpxm
+SOURCES/tests_data_acpi_virt_SSDT.memhp

.qemu-kvm.metadata

@@ -1 +1,5 @@
 68cd61a466170115b88817e2d52db2cd7a92f43a SOURCES/qemu-6.2.0.tar.xz
+c4b34092bc5af1ba7febfca1477320fb024e8acd SOURCES/tests_data_acpi_pc_SSDT.dimmpxm
+19349e3517143bd1af56a5444e927ba37a111f72 SOURCES/tests_data_acpi_q35_FACP.slic
+4632d10ae8cedad4d5d760ed211f83f0dc81005d SOURCES/tests_data_acpi_q35_SSDT.dimmpxm
+ef12eed43cc357fb134db6fa3c7ffc83e222a97d SOURCES/tests_data_acpi_virt_SSDT.memhp

SOURCES/kvm-KVM-keep-track-of-running-ioctls.patch

@@ -0,0 +1,82 @@
+From 9bacf8c4104ff3cff2e0e2c2179ec4fda633167f Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Mon, 16 Jan 2023 07:51:08 -0500
+Subject: [PATCH 05/11] KVM: keep track of running ioctls
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 247: accel: introduce accelerator blocker API
+RH-Bugzilla: 2161188
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [2/3] 357508389e2a0fd996206b406e9e235e50b5f0b6
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2161188
+
+commit a27dd2de68f37ba96fe164a42121daa5f0750afc
+Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date:   Fri Nov 11 10:47:57 2022 -0500
+
+    KVM: keep track of running ioctls
+
+    Using the new accel-blocker API, mark where ioctls are being called
+    in KVM. Next, we will implement the critical section that will take
+    care of performing memslots modifications atomically, therefore
+    preventing any new ioctl from running and allowing the running ones
+    to finish.
+
+    Signed-off-by: David Hildenbrand <david@redhat.com>
+    Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+    Message-Id: <20221111154758.1372674-3-eesposit@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ accel/kvm/kvm-all.c | 7 +++++++
+ 1 file changed, 7 insertions(+)
+
+diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
+index 8f2a53438f..221aadfda7 100644
+--- a/accel/kvm/kvm-all.c
++++ b/accel/kvm/kvm-all.c
+@@ -2337,6 +2337,7 @@ static int kvm_init(MachineState *ms)
+     assert(TARGET_PAGE_SIZE <= qemu_real_host_page_size);
+ 
+     s->sigmask_len = 8;
++    accel_blocker_init();
+ 
+ #ifdef KVM_CAP_SET_GUEST_DEBUG
+     QTAILQ_INIT(&s->kvm_sw_breakpoints);
+@@ -3018,7 +3019,9 @@ int kvm_vm_ioctl(KVMState *s, int type, ...)
+     va_end(ap);
+ 
+     trace_kvm_vm_ioctl(type, arg);
++    accel_ioctl_begin();
+     ret = ioctl(s->vmfd, type, arg);
++    accel_ioctl_end();
+     if (ret == -1) {
+         ret = -errno;
+     }
+@@ -3036,7 +3039,9 @@ int kvm_vcpu_ioctl(CPUState *cpu, int type, ...)
+     va_end(ap);
+ 
+     trace_kvm_vcpu_ioctl(cpu->cpu_index, type, arg);
++    accel_cpu_ioctl_begin(cpu);
+     ret = ioctl(cpu->kvm_fd, type, arg);
++    accel_cpu_ioctl_end(cpu);
+     if (ret == -1) {
+         ret = -errno;
+     }
+@@ -3054,7 +3059,9 @@ int kvm_device_ioctl(int fd, int type, ...)
+     va_end(ap);
+ 
+     trace_kvm_device_ioctl(fd, type, arg);
++    accel_ioctl_begin();
+     ret = ioctl(fd, type, arg);
++    accel_ioctl_end();
+     if (ret == -1) {
+         ret = -errno;
+     }
+-- 
+2.37.3
+

SOURCES/kvm-MAINTAINERS-split-out-s390x-sections.patch

@@ -0,0 +1,181 @@
+From 440ee491240f2f02f9a6082d8aad98d88c1039dd Mon Sep 17 00:00:00 2001
+From: Thomas Huth <thuth@redhat.com>
+Date: Mon, 15 Jan 2024 14:00:04 +0100
+Subject: [PATCH 1/5] MAINTAINERS: split out s390x sections
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Thomas Huth <thuth@redhat.com>
+RH-MergeRequest: 348: s390x: Provide some more useful information if decryption of a PV image fails
+RH-Jira: RHEL-18214
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Acked-by: Cédric Le Goater <clg@redhat.com>
+RH-Commit: [1/5] a71a3c11922481f97c36570e361088d17474e481
+
+JIRA: https://issues.redhat.com/browse/RHEL-18214
+
+commit 56e34834029c7c6862cb0095d95ad83c50485f88
+Author: Cornelia Huck <cohuck@redhat.com>
+Date:   Wed Dec 22 11:55:48 2021 +0100
+
+    MAINTAINERS: split out s390x sections
+
+    Split out some more specialized devices etc., so that we can build
+    smarter lists of people to be put on cc: in the future.
+
+    Signed-off-by: Cornelia Huck <cohuck@redhat.com>
+    Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
+    Acked-by: David Hildenbrand <david@redhat.com>
+    Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
+    Acked-by: Thomas Huth <thuth@redhat.com>
+    Acked-by: Halil Pasic <pasic@linux.ibm.com>
+    Acked-by: Eric Farman <farman@linux.ibm.com>
+    Message-Id: <20211222105548.356852-1-cohuck@redhat.com>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+---
+ MAINTAINERS | 85 ++++++++++++++++++++++++++++++++++++++++++++++-------
+ 1 file changed, 74 insertions(+), 11 deletions(-)
+
+diff --git a/MAINTAINERS b/MAINTAINERS
+index 7543eb4d59..b893206fc3 100644
+--- a/MAINTAINERS
++++ b/MAINTAINERS
+@@ -297,7 +297,6 @@ M: David Hildenbrand <david@redhat.com>
+ S: Maintained
+ F: target/s390x/
+ F: target/s390x/tcg
+-F: target/s390x/cpu_models_*.[ch]
+ F: hw/s390x/
+ F: disas/s390.c
+ F: tests/tcg/s390x/
+@@ -396,16 +395,10 @@ M: Halil Pasic <pasic@linux.ibm.com>
+ M: Christian Borntraeger <borntraeger@de.ibm.com>
+ S: Supported
+ F: target/s390x/kvm/
+-F: target/s390x/ioinst.[ch]
+ F: target/s390x/machine.c
+ F: target/s390x/sigp.c
+-F: target/s390x/cpu_features*.[ch]
+-F: target/s390x/cpu_models.[ch]
+ F: hw/s390x/pv.c
+ F: include/hw/s390x/pv.h
+-F: hw/intc/s390_flic.c
+-F: hw/intc/s390_flic_kvm.c
+-F: include/hw/s390x/s390_flic.h
+ F: gdb-xml/s390*.xml
+ T: git https://github.com/borntraeger/qemu.git s390-next
+ L: qemu-s390x@nongnu.org
+@@ -1529,12 +1522,8 @@ S390 Virtio-ccw
+ M: Halil Pasic <pasic@linux.ibm.com>
+ M: Christian Borntraeger <borntraeger@de.ibm.com>
+ S: Supported
+-F: hw/char/sclp*.[hc]
+-F: hw/char/terminal3270.c
+ F: hw/s390x/
+ F: include/hw/s390x/
+-F: hw/watchdog/wdt_diag288.c
+-F: include/hw/watchdog/wdt_diag288.h
+ F: configs/devices/s390x-softmmu/default.mak
+ F: tests/avocado/machine_s390_ccw_virtio.py
+ T: git https://github.com/borntraeger/qemu.git s390-next
+@@ -1559,6 +1548,37 @@ F: hw/s390x/s390-pci*
+ F: include/hw/s390x/s390-pci*
+ L: qemu-s390x@nongnu.org
+ 
++S390 channel subsystem
++M: Halil Pasic <pasic@linux.ibm.com>
++M: Christian Borntraeger <borntraeger@linux.ibm.com>
++S: Supported
++F: hw/s390x/ccw-device.[ch]
++F: hw/s390x/css.c
++F: hw/s390x/css-bridge.c
++F: include/hw/s390x/css.h
++F: include/hw/s390x/css-bridge.h
++F: include/hw/s390x/ioinst.h
++F: target/s390x/ioinst.c
++L: qemu-s390x@nongnu.org
++
++S390 CPU models
++M: David Hildenbrand <david@redhat.com>
++S: Maintained
++F: target/s390x/cpu_features*.[ch]
++F: target/s390x/cpu_models.[ch]
++L: qemu-s390x@nongnu.org
++
++S390 SCLP-backed devices
++M: Halil Pasic <pasic@linux.ibm.com>
++M: Christian Borntraeger <borntraeger@linux.ibm.com>
++S: Supported
++F: include/hw/s390x/event-facility.h
++F: include/hw/s390x/sclp.h
++F: hw/char/sclp*.[hc]
++F: hw/s390x/event-facility.c
++F: hw/s390x/sclp*.c
++L: qemu-s390x@nongnu.org
++
+ X86 Machines
+ ------------
+ PC
+@@ -1956,6 +1976,7 @@ M: Halil Pasic <pasic@linux.ibm.com>
+ S: Supported
+ F: hw/s390x/virtio-ccw*.[hc]
+ F: hw/s390x/vhost-vsock-ccw.c
++F: hw/s390x/vhost-user-fs-ccw.c
+ T: git https://gitlab.com/cohuck/qemu.git s390-next
+ T: git https://github.com/borntraeger/qemu.git s390-next
+ L: qemu-s390x@nongnu.org
+@@ -2294,6 +2315,48 @@ F: hw/timer/mips_gictimer.c
+ F: include/hw/intc/mips_gic.h
+ F: include/hw/timer/mips_gictimer.h
+ 
++S390 3270 device
++M: Halil Pasic <pasic@linux.ibm.com>
++M: Christian Borntraeger <borntraeger@linux.ibm.com>
++S: Odd fixes
++F: include/hw/s390x/3270-ccw.h
++F: hw/char/terminal3270.c
++F: hw/s390x/3270-ccw.c
++L: qemu-s390x@nongnu.org
++
++S390 diag 288 watchdog
++M: Halil Pasic <pasic@linux.ibm.com>
++M: Christian Borntraeger <borntraeger@linux.ibm.com>
++S: Supported
++F: hw/watchdog/wdt_diag288.c
++F: include/hw/watchdog/wdt_diag288.h
++L: qemu-s390x@nongnu.org
++
++S390 storage key device
++M: Halil Pasic <pasic@linux.ibm.com>
++M: Christian Borntraeger <borntraeger@linux.ibm.com>
++S: Supported
++F: hw/s390x/storage-keys.h
++F: hw/390x/s390-skeys*.c
++L: qemu-s390x@nongnu.org
++
++S390 storage attribute device
++M: Halil Pasic <pasic@linux.ibm.com>
++M: Christian Borntraeger <borntraeger@linux.ibm.com>
++S: Supported
++F: hw/s390x/storage-attributes.h
++F: hw/s390/s390-stattrib*.c
++L: qemu-s390x@nongnu.org
++
++S390 floating interrupt controller
++M: Halil Pasic <pasic@linux.ibm.com>
++M: Christian Borntraeger <borntraeger@linux.ibm.com>
++M: David Hildenbrand <david@redhat.com>
++S: Supported
++F: hw/intc/s390_flic*.c
++F: include/hw/s390x/s390_flic.h
++L: qemu-s390x@nongnu.org
++
+ Subsystems
+ ----------
+ Overall Audio backends
+-- 
+2.41.0
+

SOURCES/kvm-RHEL-Enable-x-not-migrate-acpi-index-for-all-pre-RHE.patch

@@ -0,0 +1,43 @@
+From f1480fe9a4054113ddacd218961e29f31c33d329 Mon Sep 17 00:00:00 2001
+From: Peter Xu <peterx@redhat.com>
+Date: Wed, 6 Sep 2023 16:29:23 -0400
+Subject: [PATCH 2/3] RHEL: Enable "x-not-migrate-acpi-index" for all pre-RHEL8
+ guests
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Peter Xu <peterx@redhat.com>
+RH-MergeRequest: 343: acpi: fix acpi_index migration
+RH-Jira: RHEL-20189
+RH-Acked-by: Leonardo Brás <leobras@redhat.com>
+RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
+RH-Acked-by: Prasad Pandit <None>
+RH-Commit: [2/2] 0a26a71236e68dd7feb5d2063254090e3852d6ba
+
+The acpi index migration is simply broken before for all pre-RHEL8
+branches.  Don't migrate it for all of them.
+
+Signed-off-by: Peter Xu <peterx@redhat.com>
+---
+ hw/core/machine.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+diff --git a/hw/core/machine.c b/hw/core/machine.c
+index 2724f6848a..6650a3d7b7 100644
+--- a/hw/core/machine.c
++++ b/hw/core/machine.c
+@@ -44,6 +44,10 @@ GlobalProperty hw_compat_rhel_8_6[] = {
+      * we need do disable it downstream on the latest hw_compat_rhel_8.
+      */
+     { "vhost-vsock-device", "seqpacket", "off" },
++    /*
++     * RHEL-2186: all rhel8 machines should not migrate acpi index.
++     */
++    { "PIIX4_PM", "x-not-migrate-acpi-index", "on"},
+ };
+ const size_t hw_compat_rhel_8_6_len = G_N_ELEMENTS(hw_compat_rhel_8_6);
+ 
+-- 
+2.41.0
+

SOURCES/kvm-Update-linux-headers-to-v6.0-rc4.patch

@@ -0,0 +1,171 @@
+From 10fc28b61a6fba1e6dc44fd544cf31c7f313c622 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
+Date: Fri, 28 Oct 2022 17:48:00 +0100
+Subject: [PATCH 05/42] Update linux headers to v6.0-rc4
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [5/41] ca55f497d1bf1e72179330f8f613781bf999d898
+
+Based on upstream commit d525f73f9186a5bc641b8caf0b2c9bb94e5aa963
+("Update linux headers to v6.0-rc4"), but this is focusing only on the
+ZPCI and protected dump changes.
+
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ linux-headers/linux/kvm.h       | 87 +++++++++++++++++++++++++++++++++
+ linux-headers/linux/vfio_zdev.h |  7 +++
+ 2 files changed, 94 insertions(+)
+
+diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
+index 0d05d02ee4..c65930288c 100644
+--- a/linux-headers/linux/kvm.h
++++ b/linux-headers/linux/kvm.h
+@@ -1150,6 +1150,9 @@ struct kvm_ppc_resize_hpt {
+ #define KVM_CAP_DISABLE_QUIRKS2 213
+ /* #define KVM_CAP_VM_TSC_CONTROL 214 */
+ #define KVM_CAP_SYSTEM_EVENT_DATA 215
++#define KVM_CAP_S390_PROTECTED_DUMP 217
++#define KVM_CAP_S390_ZPCI_OP 221
++#define KVM_CAP_S390_CPU_TOPOLOGY 222
+ 
+ #ifdef KVM_CAP_IRQ_ROUTING
+ 
+@@ -1651,6 +1654,55 @@ struct kvm_s390_pv_unp {
+ 	__u64 tweak;
+ };
+ 
++enum pv_cmd_dmp_id {
++	KVM_PV_DUMP_INIT,
++	KVM_PV_DUMP_CONFIG_STOR_STATE,
++	KVM_PV_DUMP_COMPLETE,
++	KVM_PV_DUMP_CPU,
++};
++
++struct kvm_s390_pv_dmp {
++	__u64 subcmd;
++	__u64 buff_addr;
++	__u64 buff_len;
++	__u64 gaddr;		/* For dump storage state */
++	__u64 reserved[4];
++};
++
++enum pv_cmd_info_id {
++	KVM_PV_INFO_VM,
++	KVM_PV_INFO_DUMP,
++};
++
++struct kvm_s390_pv_info_dump {
++	__u64 dump_cpu_buffer_len;
++	__u64 dump_config_mem_buffer_per_1m;
++	__u64 dump_config_finalize_len;
++};
++
++struct kvm_s390_pv_info_vm {
++	__u64 inst_calls_list[4];
++	__u64 max_cpus;
++	__u64 max_guests;
++	__u64 max_guest_addr;
++	__u64 feature_indication;
++};
++
++struct kvm_s390_pv_info_header {
++	__u32 id;
++	__u32 len_max;
++	__u32 len_written;
++	__u32 reserved;
++};
++
++struct kvm_s390_pv_info {
++	struct kvm_s390_pv_info_header header;
++	union {
++		struct kvm_s390_pv_info_dump dump;
++		struct kvm_s390_pv_info_vm vm;
++	};
++};
++
+ enum pv_cmd_id {
+ 	KVM_PV_ENABLE,
+ 	KVM_PV_DISABLE,
+@@ -1659,6 +1711,8 @@ enum pv_cmd_id {
+ 	KVM_PV_VERIFY,
+ 	KVM_PV_PREP_RESET,
+ 	KVM_PV_UNSHARE_ALL,
++	KVM_PV_INFO,
++	KVM_PV_DUMP,
+ };
+ 
+ struct kvm_pv_cmd {
+@@ -2066,4 +2120,37 @@ struct kvm_stats_desc {
+ /* Available with KVM_CAP_XSAVE2 */
+ #define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
+ 
++/* Available with KVM_CAP_S390_PROTECTED_DUMP */
++#define KVM_S390_PV_CPU_COMMAND	_IOWR(KVMIO, 0xd0, struct kvm_pv_cmd)
++
++/* Available with KVM_CAP_S390_ZPCI_OP */
++#define KVM_S390_ZPCI_OP         _IOW(KVMIO,  0xd1, struct kvm_s390_zpci_op)
++
++struct kvm_s390_zpci_op {
++	/* in */
++	__u32 fh;               /* target device */
++	__u8  op;               /* operation to perform */
++	__u8  pad[3];
++	union {
++		/* for KVM_S390_ZPCIOP_REG_AEN */
++		struct {
++			__u64 ibv;      /* Guest addr of interrupt bit vector */
++			__u64 sb;       /* Guest addr of summary bit */
++			__u32 flags;
++			__u32 noi;      /* Number of interrupts */
++			__u8 isc;       /* Guest interrupt subclass */
++			__u8 sbo;       /* Offset of guest summary bit vector */
++			__u16 pad;
++		} reg_aen;
++		__u64 reserved[8];
++	} u;
++};
++
++/* types for kvm_s390_zpci_op->op */
++#define KVM_S390_ZPCIOP_REG_AEN                0
++#define KVM_S390_ZPCIOP_DEREG_AEN      1
++
++/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
++#define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
++
+ #endif /* __LINUX_KVM_H */
+diff --git a/linux-headers/linux/vfio_zdev.h b/linux-headers/linux/vfio_zdev.h
+index b4309397b6..77f2aff1f2 100644
+--- a/linux-headers/linux/vfio_zdev.h
++++ b/linux-headers/linux/vfio_zdev.h
+@@ -29,6 +29,9 @@ struct vfio_device_info_cap_zpci_base {
+ 	__u16 fmb_length;	/* Measurement Block Length (in bytes) */
+ 	__u8 pft;		/* PCI Function Type */
+ 	__u8 gid;		/* PCI function group ID */
++	/* End of version 1 */
++	__u32 fh;		/* PCI function handle */
++	/* End of version 2 */
+ };
+ 
+ /**
+@@ -47,6 +50,10 @@ struct vfio_device_info_cap_zpci_group {
+ 	__u16 noi;		/* Maximum number of MSIs */
+ 	__u16 maxstbl;		/* Maximum Store Block Length */
+ 	__u8 version;		/* Supported PCI Version */
++	/* End of version 1 */
++	__u8 reserved;
++	__u16 imaxstbl;		/* Maximum Interpreted Store Block Length */
++	/* End of version 2 */
+ };
+ 
+ /**
+-- 
+2.37.3
+

SOURCES/kvm-accel-introduce-accelerator-blocker-API.patch

@@ -0,0 +1,349 @@
+From a5e7bb1f7a88efb5574266a76e80fd7604d19921 Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Mon, 16 Jan 2023 07:49:59 -0500
+Subject: [PATCH 04/11] accel: introduce accelerator blocker API
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 247: accel: introduce accelerator blocker API
+RH-Bugzilla: 2161188
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [1/3] 9d3d7f9554974a79042c915763288cce07aef135
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2161188
+
+commit bd688fc93120fb3e28aa70e3dfdf567ccc1e0bc1
+Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date:   Fri Nov 11 10:47:56 2022 -0500
+
+    accel: introduce accelerator blocker API
+
+    This API allows the accelerators to prevent vcpus from issuing
+    new ioctls while execting a critical section marked with the
+    accel_ioctl_inhibit_begin/end functions.
+
+    Note that all functions submitting ioctls must mark where the
+    ioctl is being called with accel_{cpu_}ioctl_begin/end().
+
+    This API requires the caller to always hold the BQL.
+    API documentation is in sysemu/accel-blocker.h
+
+    Internally, it uses a QemuLockCnt together with a per-CPU QemuLockCnt
+    (to minimize cache line bouncing) to keep avoid that new ioctls
+    run when the critical section starts, and a QemuEvent to wait
+    that all running ioctls finish.
+
+    Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+    Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+    Message-Id: <20221111154758.1372674-2-eesposit@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Conflicts:
+	util/meson.build: files are missing in rhel 8.8.0
+	namely int128.c, memalign.c and interval-tree.c
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ accel/accel-blocker.c          | 154 +++++++++++++++++++++++++++++++++
+ accel/meson.build              |   2 +-
+ hw/core/cpu-common.c           |   2 +
+ include/hw/core/cpu.h          |   3 +
+ include/sysemu/accel-blocker.h |  56 ++++++++++++
+ util/meson.build               |   2 +-
+ 6 files changed, 217 insertions(+), 2 deletions(-)
+ create mode 100644 accel/accel-blocker.c
+ create mode 100644 include/sysemu/accel-blocker.h
+
+diff --git a/accel/accel-blocker.c b/accel/accel-blocker.c
+new file mode 100644
+index 0000000000..1e7f423462
+--- /dev/null
++++ b/accel/accel-blocker.c
+@@ -0,0 +1,154 @@
++/*
++ * Lock to inhibit accelerator ioctls
++ *
++ * Copyright (c) 2022 Red Hat Inc.
++ *
++ * Author: Emanuele Giuseppe Esposito       <eesposit@redhat.com>
++ *
++ * Permission is hereby granted, free of charge, to any person obtaining a copy
++ * of this software and associated documentation files (the "Software"), to deal
++ * in the Software without restriction, including without limitation the rights
++ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
++ * copies of the Software, and to permit persons to whom the Software is
++ * furnished to do so, subject to the following conditions:
++ *
++ * The above copyright notice and this permission notice shall be included in
++ * all copies or substantial portions of the Software.
++ *
++ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
++ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
++ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
++ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
++ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
++ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
++ * THE SOFTWARE.
++ */
++
++#include "qemu/osdep.h"
++#include "qemu/thread.h"
++#include "qemu/main-loop.h"
++#include "hw/core/cpu.h"
++#include "sysemu/accel-blocker.h"
++
++static QemuLockCnt accel_in_ioctl_lock;
++static QemuEvent accel_in_ioctl_event;
++
++void accel_blocker_init(void)
++{
++    qemu_lockcnt_init(&accel_in_ioctl_lock);
++    qemu_event_init(&accel_in_ioctl_event, false);
++}
++
++void accel_ioctl_begin(void)
++{
++    if (likely(qemu_mutex_iothread_locked())) {
++        return;
++    }
++
++    /* block if lock is taken in kvm_ioctl_inhibit_begin() */
++    qemu_lockcnt_inc(&accel_in_ioctl_lock);
++}
++
++void accel_ioctl_end(void)
++{
++    if (likely(qemu_mutex_iothread_locked())) {
++        return;
++    }
++
++    qemu_lockcnt_dec(&accel_in_ioctl_lock);
++    /* change event to SET. If event was BUSY, wake up all waiters */
++    qemu_event_set(&accel_in_ioctl_event);
++}
++
++void accel_cpu_ioctl_begin(CPUState *cpu)
++{
++    if (unlikely(qemu_mutex_iothread_locked())) {
++        return;
++    }
++
++    /* block if lock is taken in kvm_ioctl_inhibit_begin() */
++    qemu_lockcnt_inc(&cpu->in_ioctl_lock);
++}
++
++void accel_cpu_ioctl_end(CPUState *cpu)
++{
++    if (unlikely(qemu_mutex_iothread_locked())) {
++        return;
++    }
++
++    qemu_lockcnt_dec(&cpu->in_ioctl_lock);
++    /* change event to SET. If event was BUSY, wake up all waiters */
++    qemu_event_set(&accel_in_ioctl_event);
++}
++
++static bool accel_has_to_wait(void)
++{
++    CPUState *cpu;
++    bool needs_to_wait = false;
++
++    CPU_FOREACH(cpu) {
++        if (qemu_lockcnt_count(&cpu->in_ioctl_lock)) {
++            /* exit the ioctl, if vcpu is running it */
++            qemu_cpu_kick(cpu);
++            needs_to_wait = true;
++        }
++    }
++
++    return needs_to_wait || qemu_lockcnt_count(&accel_in_ioctl_lock);
++}
++
++void accel_ioctl_inhibit_begin(void)
++{
++    CPUState *cpu;
++
++    /*
++     * We allow to inhibit only when holding the BQL, so we can identify
++     * when an inhibitor wants to issue an ioctl easily.
++     */
++    g_assert(qemu_mutex_iothread_locked());
++
++    /* Block further invocations of the ioctls outside the BQL.  */
++    CPU_FOREACH(cpu) {
++        qemu_lockcnt_lock(&cpu->in_ioctl_lock);
++    }
++    qemu_lockcnt_lock(&accel_in_ioctl_lock);
++
++    /* Keep waiting until there are running ioctls */
++    while (true) {
++
++        /* Reset event to FREE. */
++        qemu_event_reset(&accel_in_ioctl_event);
++
++        if (accel_has_to_wait()) {
++            /*
++             * If event is still FREE, and there are ioctls still in progress,
++             * wait.
++             *
++             *  If an ioctl finishes before qemu_event_wait(), it will change
++             * the event state to SET. This will prevent qemu_event_wait() from
++             * blocking, but it's not a problem because if other ioctls are
++             * still running the loop will iterate once more and reset the event
++             * status to FREE so that it can wait properly.
++             *
++             * If an ioctls finishes while qemu_event_wait() is blocking, then
++             * it will be waken up, but also here the while loop makes sure
++             * to re-enter the wait if there are other running ioctls.
++             */
++            qemu_event_wait(&accel_in_ioctl_event);
++        } else {
++            /* No ioctl is running */
++            return;
++        }
++    }
++}
++
++void accel_ioctl_inhibit_end(void)
++{
++    CPUState *cpu;
++
++    qemu_lockcnt_unlock(&accel_in_ioctl_lock);
++    CPU_FOREACH(cpu) {
++        qemu_lockcnt_unlock(&cpu->in_ioctl_lock);
++    }
++}
++
+diff --git a/accel/meson.build b/accel/meson.build
+index dfd808d2c8..801b4d44e8 100644
+--- a/accel/meson.build
++++ b/accel/meson.build
+@@ -1,4 +1,4 @@
+-specific_ss.add(files('accel-common.c'))
++specific_ss.add(files('accel-common.c', 'accel-blocker.c'))
+ softmmu_ss.add(files('accel-softmmu.c'))
+ user_ss.add(files('accel-user.c'))
+ 
+diff --git a/hw/core/cpu-common.c b/hw/core/cpu-common.c
+index 9e3241b430..b6e83acf0a 100644
+--- a/hw/core/cpu-common.c
++++ b/hw/core/cpu-common.c
+@@ -238,6 +238,7 @@ static void cpu_common_initfn(Object *obj)
+     cpu->nr_threads = 1;
+ 
+     qemu_mutex_init(&cpu->work_mutex);
++    qemu_lockcnt_init(&cpu->in_ioctl_lock);
+     QSIMPLEQ_INIT(&cpu->work_list);
+     QTAILQ_INIT(&cpu->breakpoints);
+     QTAILQ_INIT(&cpu->watchpoints);
+@@ -249,6 +250,7 @@ static void cpu_common_finalize(Object *obj)
+ {
+     CPUState *cpu = CPU(obj);
+ 
++    qemu_lockcnt_destroy(&cpu->in_ioctl_lock);
+     qemu_mutex_destroy(&cpu->work_mutex);
+ }
+ 
+diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
+index e948e81f1a..49d9c73f97 100644
+--- a/include/hw/core/cpu.h
++++ b/include/hw/core/cpu.h
+@@ -383,6 +383,9 @@ struct CPUState {
+     uint32_t kvm_fetch_index;
+     uint64_t dirty_pages;
+ 
++    /* Use by accel-block: CPU is executing an ioctl() */
++    QemuLockCnt in_ioctl_lock;
++
+     /* Used for events with 'vcpu' and *without* the 'disabled' properties */
+     DECLARE_BITMAP(trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS);
+     DECLARE_BITMAP(trace_dstate, CPU_TRACE_DSTATE_MAX_EVENTS);
+diff --git a/include/sysemu/accel-blocker.h b/include/sysemu/accel-blocker.h
+new file mode 100644
+index 0000000000..72020529ef
+--- /dev/null
++++ b/include/sysemu/accel-blocker.h
+@@ -0,0 +1,56 @@
++/*
++ * Accelerator blocking API, to prevent new ioctls from starting and wait the
++ * running ones finish.
++ * This mechanism differs from pause/resume_all_vcpus() in that it does not
++ * release the BQL.
++ *
++ *  Copyright (c) 2022 Red Hat Inc.
++ *
++ * Author: Emanuele Giuseppe Esposito       <eesposit@redhat.com>
++ *
++ * This work is licensed under the terms of the GNU GPL, version 2 or later.
++ * See the COPYING file in the top-level directory.
++ */
++#ifndef ACCEL_BLOCKER_H
++#define ACCEL_BLOCKER_H
++
++#include "qemu/osdep.h"
++#include "sysemu/cpus.h"
++
++extern void accel_blocker_init(void);
++
++/*
++ * accel_{cpu_}ioctl_begin/end:
++ * Mark when ioctl is about to run or just finished.
++ *
++ * accel_{cpu_}ioctl_begin will block after accel_ioctl_inhibit_begin() is
++ * called, preventing new ioctls to run. They will continue only after
++ * accel_ioctl_inibith_end().
++ */
++extern void accel_ioctl_begin(void);
++extern void accel_ioctl_end(void);
++extern void accel_cpu_ioctl_begin(CPUState *cpu);
++extern void accel_cpu_ioctl_end(CPUState *cpu);
++
++/*
++ * accel_ioctl_inhibit_begin: start critical section
++ *
++ * This function makes sure that:
++ * 1) incoming accel_{cpu_}ioctl_begin() calls block
++ * 2) wait that all ioctls that were already running reach
++ *    accel_{cpu_}ioctl_end(), kicking vcpus if necessary.
++ *
++ * This allows the caller to access shared data or perform operations without
++ * worrying of concurrent vcpus accesses.
++ */
++extern void accel_ioctl_inhibit_begin(void);
++
++/*
++ * accel_ioctl_inhibit_end: end critical section started by
++ * accel_ioctl_inhibit_begin()
++ *
++ * This function allows blocked accel_{cpu_}ioctl_begin() to continue.
++ */
++extern void accel_ioctl_inhibit_end(void);
++
++#endif /* ACCEL_BLOCKER_H */
+diff --git a/util/meson.build b/util/meson.build
+index 05b593055a..b5f153b0e8 100644
+--- a/util/meson.build
++++ b/util/meson.build
+@@ -48,6 +48,7 @@ util_ss.add(files('transactions.c'))
+ util_ss.add(when: 'CONFIG_POSIX', if_true: files('drm.c'))
+ util_ss.add(files('guest-random.c'))
+ util_ss.add(files('yank.c'))
++util_ss.add(files('lockcnt.c'))
+ 
+ if have_user
+   util_ss.add(files('selfmap.c'))
+@@ -69,7 +70,6 @@ if have_block
+   util_ss.add(files('hexdump.c'))
+   util_ss.add(files('iova-tree.c'))
+   util_ss.add(files('iov.c', 'qemu-sockets.c', 'uri.c'))
+-  util_ss.add(files('lockcnt.c'))
+   util_ss.add(files('main-loop.c'))
+   util_ss.add(files('nvdimm-utils.c'))
+   util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c'))
+-- 
+2.37.3
+

SOURCES/kvm-acpi-fix-acpi_index-migration.patch

@@ -0,0 +1,165 @@
+From 3deffc03c2e9b0053eec5aeb5b5d633dfe29f499 Mon Sep 17 00:00:00 2001
+From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
+Date: Wed, 6 Apr 2022 14:58:12 -0400
+Subject: [PATCH 1/3] acpi: fix acpi_index migration
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Peter Xu <peterx@redhat.com>
+RH-MergeRequest: 343: acpi: fix acpi_index migration
+RH-Jira: RHEL-20189
+RH-Acked-by: Leonardo Brás <leobras@redhat.com>
+RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
+RH-Acked-by: Prasad Pandit <None>
+RH-Commit: [1/2] c5b9cdf5791cd856207b7df7e2ef5df360ec8de4
+
+vmstate_acpi_pcihp_use_acpi_index() was expecting AcpiPciHpState
+as state but it actually received PIIX4PMState, because
+VMSTATE_PCI_HOTPLUG is a macro and not another struct.
+So it ended up accessing random pointer, which resulted
+in 'false' return value and acpi_index field wasn't ever
+sent.
+
+However in 7.0 that pointer de-references to value > 0, and
+destination QEMU starts to expect the field which isn't
+sent in migratioon stream from older QEMU (6.2 and older).
+As result migration fails with:
+  qemu-system-x86_64: Missing section footer for 0000:00:01.3/piix4_pm
+  qemu-system-x86_64: load of migration failed: Invalid argument
+
+In addition with QEMU-6.2, destination due to not expected
+state, also never expects the acpi_index field in migration
+stream.
+
+Q35 is not affected as it always sends/expects the field as
+long as acpi based PCI hotplug is enabled.
+
+Fix issue by introducing compat knob to never send/expect
+acpi_index in migration stream for 6.2 and older PC machine
+types and always send it for 7.0 and newer PC machine types.
+
+Diagnosed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+Fixes: b32bd76 ("pci: introduce acpi-index property for PCI device")
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/932
+Signed-off-by: Igor Mammedov <imammedo@redhat.com>
+Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+(cherry picked from commit a83c2844903c45aa7d32cdd17305f23ce2c56ab9)
+Signed-off-by: Peter Xu <peterx@redhat.com>
+---
+ hw/acpi/acpi-pci-hotplug-stub.c |  4 ----
+ hw/acpi/pcihp.c                 |  6 ------
+ hw/acpi/piix4.c                 | 15 ++++++++++++++-
+ hw/core/machine.c               |  5 +++++
+ include/hw/acpi/pcihp.h         |  2 --
+ 5 files changed, 19 insertions(+), 13 deletions(-)
+
+diff --git a/hw/acpi/acpi-pci-hotplug-stub.c b/hw/acpi/acpi-pci-hotplug-stub.c
+index 734e4c5986..a43f6dafc9 100644
+--- a/hw/acpi/acpi-pci-hotplug-stub.c
++++ b/hw/acpi/acpi-pci-hotplug-stub.c
+@@ -41,7 +41,3 @@ void acpi_pcihp_reset(AcpiPciHpState *s, bool acpihp_root_off)
+     return;
+ }
+ 
+-bool vmstate_acpi_pcihp_use_acpi_index(void *opaque, int version_id)
+-{
+-    return false;
+-}
+diff --git a/hw/acpi/pcihp.c b/hw/acpi/pcihp.c
+index be0e846b34..ec861661c3 100644
+--- a/hw/acpi/pcihp.c
++++ b/hw/acpi/pcihp.c
+@@ -559,12 +559,6 @@ void acpi_pcihp_init(Object *owner, AcpiPciHpState *s, PCIBus *root_bus,
+                                    OBJ_PROP_FLAG_READ);
+ }
+ 
+-bool vmstate_acpi_pcihp_use_acpi_index(void *opaque, int version_id)
+-{
+-     AcpiPciHpState *s = opaque;
+-     return s->acpi_index;
+-}
+-
+ const VMStateDescription vmstate_acpi_pcihp_pci_status = {
+     .name = "acpi_pcihp_pci_status",
+     .version_id = 1,
+diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
+index 8d6011c0a3..033e75ce5b 100644
+--- a/hw/acpi/piix4.c
++++ b/hw/acpi/piix4.c
+@@ -82,6 +82,7 @@ struct PIIX4PMState {
+     AcpiPciHpState acpi_pci_hotplug;
+     bool use_acpi_hotplug_bridge;
+     bool use_acpi_root_pci_hotplug;
++    bool not_migrate_acpi_index;
+ 
+     uint8_t disable_s3;
+     uint8_t disable_s4;
+@@ -269,6 +270,16 @@ static bool piix4_vmstate_need_smbus(void *opaque, int version_id)
+     return pm_smbus_vmstate_needed();
+ }
+ 
++/*
++ * This is a fudge to turn off the acpi_index field,
++ * whose test was always broken on piix4 with 6.2 and older machine types.
++ */
++static bool vmstate_test_migrate_acpi_index(void *opaque, int version_id)
++{
++    PIIX4PMState *s = PIIX4_PM(opaque);
++    return s->use_acpi_hotplug_bridge && !s->not_migrate_acpi_index;
++}
++
+ /* qemu-kvm 1.2 uses version 3 but advertised as 2
+  * To support incoming qemu-kvm 1.2 migration, change version_id
+  * and minimum_version_id to 2 below (which breaks migration from
+@@ -299,7 +310,7 @@ static const VMStateDescription vmstate_acpi = {
+             struct AcpiPciHpPciStatus),
+         VMSTATE_PCI_HOTPLUG(acpi_pci_hotplug, PIIX4PMState,
+                             vmstate_test_use_acpi_hotplug_bridge,
+-                            vmstate_acpi_pcihp_use_acpi_index),
++                            vmstate_test_migrate_acpi_index),
+         VMSTATE_END_OF_LIST()
+     },
+     .subsections = (const VMStateDescription*[]) {
+@@ -654,6 +665,8 @@ static Property piix4_pm_properties[] = {
+     DEFINE_PROP_BOOL("memory-hotplug-support", PIIX4PMState,
+                      acpi_memory_hotplug.is_enabled, true),
+     DEFINE_PROP_BOOL("smm-compat", PIIX4PMState, smm_compat, false),
++    DEFINE_PROP_BOOL("x-not-migrate-acpi-index", PIIX4PMState,
++                      not_migrate_acpi_index, false),
+     DEFINE_PROP_END_OF_LIST(),
+ };
+ 
+diff --git a/hw/core/machine.c b/hw/core/machine.c
+index 76fcabec7a..2724f6848a 100644
+--- a/hw/core/machine.c
++++ b/hw/core/machine.c
+@@ -331,6 +331,11 @@ GlobalProperty hw_compat_rhel_7_1[] = {
+ };
+ const size_t hw_compat_rhel_7_1_len = G_N_ELEMENTS(hw_compat_rhel_7_1);
+ 
++GlobalProperty hw_compat_6_2[] = {
++    { "PIIX4_PM", "x-not-migrate-acpi-index", "on"},
++};
++const size_t hw_compat_6_2_len = G_N_ELEMENTS(hw_compat_6_2);
++
+ GlobalProperty hw_compat_6_1[] = {
+     { "vhost-user-vsock-device", "seqpacket", "off" },
+     { "nvme-ns", "shared", "off" },
+diff --git a/include/hw/acpi/pcihp.h b/include/hw/acpi/pcihp.h
+index af1a169fc3..7e268c2c9c 100644
+--- a/include/hw/acpi/pcihp.h
++++ b/include/hw/acpi/pcihp.h
+@@ -73,8 +73,6 @@ void acpi_pcihp_reset(AcpiPciHpState *s, bool acpihp_root_off);
+ 
+ extern const VMStateDescription vmstate_acpi_pcihp_pci_status;
+ 
+-bool vmstate_acpi_pcihp_use_acpi_index(void *opaque, int version_id);
+-
+ #define VMSTATE_PCI_HOTPLUG(pcihp, state, test_pcihp, test_acpi_index) \
+         VMSTATE_UINT32_TEST(pcihp.hotplug_select, state, \
+                             test_pcihp), \
+-- 
+2.41.0
+

SOURCES/kvm-aio-wait-switch-to-smp_mb__after_rmw.patch

@@ -0,0 +1,50 @@
+From 953c5c0982b61b0a3f8f03452844b5487eb22fc7 Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Thu, 9 Mar 2023 08:13:17 -0500
+Subject: [PATCH 06/13] aio-wait: switch to smp_mb__after_rmw()
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw()
+RH-Bugzilla: 2168472
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Eric Auger <eric.auger@redhat.com>
+RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Commit: [6/10] 9f30f97754139ffd18d36b2350f9ed4e59ac496e
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472
+
+commit b532526a07ef3b903ead2e055fe6cc87b41057a3
+Author: Paolo Bonzini <pbonzini@redhat.com>
+Date:   Fri Mar 3 11:03:52 2023 +0100
+
+    aio-wait: switch to smp_mb__after_rmw()
+
+    The barrier comes after an atomic increment, so it is enough to use
+    smp_mb__after_rmw(); this avoids a double barrier on x86 systems.
+
+    Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+    Reviewed-by: David Hildenbrand <david@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ include/block/aio-wait.h | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
+index 54840f8622..03b6394c78 100644
+--- a/include/block/aio-wait.h
++++ b/include/block/aio-wait.h
+@@ -82,7 +82,7 @@ extern AioWait global_aio_wait;
+     /* Increment wait_->num_waiters before evaluating cond. */     \
+     qatomic_inc(&wait_->num_waiters);                              \
+     /* Paired with smp_mb in aio_wait_kick(). */                   \
+-    smp_mb();                                                      \
++    smp_mb__after_rmw();                                           \
+     if (ctx_ && in_aio_context_home_thread(ctx_)) {                \
+         while ((cond)) {                                           \
+             aio_poll(ctx_, true);                                  \
+-- 
+2.37.3
+

SOURCES/kvm-aio_wait_kick-add-missing-memory-barrier.patch

@@ -0,0 +1,86 @@
+From d7eae0ff4c7f7f7bf10f10272adf7c6971c0db9b Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Thu, 9 Mar 2023 09:26:35 -0500
+Subject: [PATCH 01/13] aio_wait_kick: add missing memory barrier
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw()
+RH-Bugzilla: 2168472
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Eric Auger <eric.auger@redhat.com>
+RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Commit: [1/10] eb774aee79864052e14e706d931e52e7bd1162c8
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472
+
+commit 7455ff1aa01564cc175db5b2373e610503ad4411
+Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date:   Tue May 24 13:30:54 2022 -0400
+
+    aio_wait_kick: add missing memory barrier
+
+    It seems that aio_wait_kick always required a memory barrier
+    or atomic operation in the caller, but nobody actually
+    took care of doing it.
+
+    Let's put the barrier in the function instead, and pair it
+    with another one in AIO_WAIT_WHILE. Read aio_wait_kick()
+    comment for further explanation.
+
+    Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
+    Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+    Message-Id: <20220524173054.12651-1-eesposit@redhat.com>
+    Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+    Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ include/block/aio-wait.h |  2 ++
+ util/aio-wait.c          | 16 +++++++++++++++-
+ 2 files changed, 17 insertions(+), 1 deletion(-)
+
+diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
+index b39eefb38d..54840f8622 100644
+--- a/include/block/aio-wait.h
++++ b/include/block/aio-wait.h
+@@ -81,6 +81,8 @@ extern AioWait global_aio_wait;
+     AioContext *ctx_ = (ctx);                                      \
+     /* Increment wait_->num_waiters before evaluating cond. */     \
+     qatomic_inc(&wait_->num_waiters);                              \
++    /* Paired with smp_mb in aio_wait_kick(). */                   \
++    smp_mb();                                                      \
+     if (ctx_ && in_aio_context_home_thread(ctx_)) {                \
+         while ((cond)) {                                           \
+             aio_poll(ctx_, true);                                  \
+diff --git a/util/aio-wait.c b/util/aio-wait.c
+index bdb3d3af22..98c5accd29 100644
+--- a/util/aio-wait.c
++++ b/util/aio-wait.c
+@@ -35,7 +35,21 @@ static void dummy_bh_cb(void *opaque)
+ 
+ void aio_wait_kick(void)
+ {
+-    /* The barrier (or an atomic op) is in the caller.  */
++    /*
++     * Paired with smp_mb in AIO_WAIT_WHILE. Here we have:
++     * write(condition);
++     * aio_wait_kick() {
++     *      smp_mb();
++     *      read(num_waiters);
++     * }
++     *
++     * And in AIO_WAIT_WHILE:
++     * write(num_waiters);
++     * smp_mb();
++     * read(condition);
++     */
++    smp_mb();
++
+     if (qatomic_read(&global_aio_wait.num_waiters)) {
+         aio_bh_schedule_oneshot(qemu_get_aio_context(), dummy_bh_cb, NULL);
+     }
+-- 
+2.37.3
+

SOURCES/kvm-apic-disable-reentrancy-detection-for-apic-msi.patch

@@ -0,0 +1,56 @@
+From 47d027147694fde94dd73305ee53b6a136cbeced Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Tue, 9 May 2023 10:29:03 -0400
+Subject: [PATCH 08/15] apic: disable reentrancy detection for apic-msi
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [8/12] 25c3cf99b00cd9adc10d6e7afa9c3e3b7da08de2 (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+
+commit 50795ee051a342c681a9b45671c552fbd6274db8
+Author: Alexander Bulekov <alxndr@bu.edu>
+Date:   Thu Apr 27 17:10:13 2023 -0400
+
+    apic: disable reentrancy detection for apic-msi
+
+    As the code is designed for re-entrant calls to apic-msi, mark apic-msi
+    as reentrancy-safe.
+
+    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
+    Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
+    Message-Id: <20230427211013.2994127-9-alxndr@bu.edu>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/intc/apic.c | 7 +++++++
+ 1 file changed, 7 insertions(+)
+
+diff --git a/hw/intc/apic.c b/hw/intc/apic.c
+index 3df11c34d6..a7c2b301a8 100644
+--- a/hw/intc/apic.c
++++ b/hw/intc/apic.c
+@@ -883,6 +883,13 @@ static void apic_realize(DeviceState *dev, Error **errp)
+     memory_region_init_io(&s->io_memory, OBJECT(s), &apic_io_ops, s, "apic-msi",
+                           APIC_SPACE_SIZE);
+ 
++    /*
++     * apic-msi's apic_mem_write can call into ioapic_eoi_broadcast, which can
++     * write back to apic-msi. As such mark the apic-msi region re-entrancy
++     * safe.
++     */
++    s->io_memory.disable_reentrancy_guard = true;
++
+     s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, apic_timer, s);
+     local_apics[s->id] = s;
+ 
+-- 
+2.37.3
+

SOURCES/kvm-async-Add-an-optional-reentrancy-guard-to-the-BH-API.patch

@@ -0,0 +1,235 @@
+From 8996ac4369de7e0cb6f911db6f47c3e4ae88c8aa Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Tue, 9 May 2023 10:29:03 -0400
+Subject: [PATCH 02/15] async: Add an optional reentrancy guard to the BH API
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [2/12] b03f247e242a6cdb3eebec36477234ac77dcd20c (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+Conflict: The file block/graph-lock.h, inluded from include/block/aio.h,
+          doesn't exist in this code version. The code compiles without
+          issues if this include is just omitted, so we do that.
+
+commit 9c86c97f12c060bf7484dd931f38634e166a81f0
+Author: Alexander Bulekov <alxndr@bu.edu>
+Date:   Thu Apr 27 17:10:07 2023 -0400
+
+    async: Add an optional reentrancy guard to the BH API
+
+    Devices can pass their MemoryReentrancyGuard (from their DeviceState),
+    when creating new BHes. Then, the async API will toggle the guard
+    before/after calling the BH call-back. This prevents bh->mmio reentrancy
+    issues.
+
+    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
+    Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
+    Message-Id: <20230427211013.2994127-3-alxndr@bu.edu>
+    [thuth: Fix "line over 90 characters" checkpatch.pl error]
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ docs/devel/multiple-iothreads.txt |  7 +++++++
+ include/block/aio.h               | 18 ++++++++++++++++--
+ include/qemu/main-loop.h          |  7 +++++--
+ tests/unit/ptimer-test-stubs.c    |  3 ++-
+ util/async.c                      | 18 +++++++++++++++++-
+ util/main-loop.c                  |  6 ++++--
+ util/trace-events                 |  1 +
+ 7 files changed, 52 insertions(+), 8 deletions(-)
+
+diff --git a/docs/devel/multiple-iothreads.txt b/docs/devel/multiple-iothreads.txt
+index aeb997bed5..a11576bc74 100644
+--- a/docs/devel/multiple-iothreads.txt
++++ b/docs/devel/multiple-iothreads.txt
+@@ -61,6 +61,7 @@ There are several old APIs that use the main loop AioContext:
+  * LEGACY qemu_aio_set_event_notifier() - monitor an event notifier
+  * LEGACY timer_new_ms() - create a timer
+  * LEGACY qemu_bh_new() - create a BH
++ * LEGACY qemu_bh_new_guarded() - create a BH with a device re-entrancy guard
+  * LEGACY qemu_aio_wait() - run an event loop iteration
+ 
+ Since they implicitly work on the main loop they cannot be used in code that
+@@ -72,8 +73,14 @@ Instead, use the AioContext functions directly (see include/block/aio.h):
+  * aio_set_event_notifier() - monitor an event notifier
+  * aio_timer_new() - create a timer
+  * aio_bh_new() - create a BH
++ * aio_bh_new_guarded() - create a BH with a device re-entrancy guard
+  * aio_poll() - run an event loop iteration
+ 
++The qemu_bh_new_guarded/aio_bh_new_guarded APIs accept a "MemReentrancyGuard"
++argument, which is used to check for and prevent re-entrancy problems. For
++BHs associated with devices, the reentrancy-guard is contained in the
++corresponding DeviceState and named "mem_reentrancy_guard".
++
+ The AioContext can be obtained from the IOThread using
+ iothread_get_aio_context() or for the main loop using qemu_get_aio_context().
+ Code that takes an AioContext argument works both in IOThreads or the main
+diff --git a/include/block/aio.h b/include/block/aio.h
+index 47fbe9d81f..c7da152985 100644
+--- a/include/block/aio.h
++++ b/include/block/aio.h
+@@ -22,6 +22,8 @@
+ #include "qemu/event_notifier.h"
+ #include "qemu/thread.h"
+ #include "qemu/timer.h"
++#include "hw/qdev-core.h"
++
+ 
+ typedef struct BlockAIOCB BlockAIOCB;
+ typedef void BlockCompletionFunc(void *opaque, int ret);
+@@ -321,9 +323,11 @@ void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
+  * is opaque and must be allocated prior to its use.
+  *
+  * @name: A human-readable identifier for debugging purposes.
++ * @reentrancy_guard: A guard set when entering a cb to prevent
++ * device-reentrancy issues
+  */
+ QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
+-                        const char *name);
++                        const char *name, MemReentrancyGuard *reentrancy_guard);
+ 
+ /**
+  * aio_bh_new: Allocate a new bottom half structure
+@@ -332,7 +336,17 @@ QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
+  * string.
+  */
+ #define aio_bh_new(ctx, cb, opaque) \
+-    aio_bh_new_full((ctx), (cb), (opaque), (stringify(cb)))
++    aio_bh_new_full((ctx), (cb), (opaque), (stringify(cb)), NULL)
++
++/**
++ * aio_bh_new_guarded: Allocate a new bottom half structure with a
++ * reentrancy_guard
++ *
++ * A convenience wrapper for aio_bh_new_full() that uses the cb as the name
++ * string.
++ */
++#define aio_bh_new_guarded(ctx, cb, opaque, guard) \
++    aio_bh_new_full((ctx), (cb), (opaque), (stringify(cb)), guard)
+ 
+ /**
+  * aio_notify: Force processing of pending events.
+diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h
+index 8dbc6fcb89..85dd5ada9e 100644
+--- a/include/qemu/main-loop.h
++++ b/include/qemu/main-loop.h
+@@ -294,9 +294,12 @@ void qemu_cond_timedwait_iothread(QemuCond *cond, int ms);
+ 
+ void qemu_fd_register(int fd);
+ 
++#define qemu_bh_new_guarded(cb, opaque, guard) \
++    qemu_bh_new_full((cb), (opaque), (stringify(cb)), guard)
+ #define qemu_bh_new(cb, opaque) \
+-    qemu_bh_new_full((cb), (opaque), (stringify(cb)))
+-QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name);
++    qemu_bh_new_full((cb), (opaque), (stringify(cb)), NULL)
++QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name,
++                         MemReentrancyGuard *reentrancy_guard);
+ void qemu_bh_schedule_idle(QEMUBH *bh);
+ 
+ enum {
+diff --git a/tests/unit/ptimer-test-stubs.c b/tests/unit/ptimer-test-stubs.c
+index 2a3ef58799..a7a2d08e7e 100644
+--- a/tests/unit/ptimer-test-stubs.c
++++ b/tests/unit/ptimer-test-stubs.c
+@@ -108,7 +108,8 @@ int64_t qemu_clock_deadline_ns_all(QEMUClockType type, int attr_mask)
+     return deadline;
+ }
+ 
+-QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name)
++QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name,
++                         MemReentrancyGuard *reentrancy_guard)
+ {
+     QEMUBH *bh = g_new(QEMUBH, 1);
+ 
+diff --git a/util/async.c b/util/async.c
+index 2a63bf90f2..1fff02e7fc 100644
+--- a/util/async.c
++++ b/util/async.c
+@@ -62,6 +62,7 @@ struct QEMUBH {
+     void *opaque;
+     QSLIST_ENTRY(QEMUBH) next;
+     unsigned flags;
++    MemReentrancyGuard *reentrancy_guard;
+ };
+ 
+ /* Called concurrently from any thread */
+@@ -127,7 +128,7 @@ void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb,
+ }
+ 
+ QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
+-                        const char *name)
++                        const char *name, MemReentrancyGuard *reentrancy_guard)
+ {
+     QEMUBH *bh;
+     bh = g_new(QEMUBH, 1);
+@@ -136,13 +137,28 @@ QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
+         .cb = cb,
+         .opaque = opaque,
+         .name = name,
++        .reentrancy_guard = reentrancy_guard,
+     };
+     return bh;
+ }
+ 
+ void aio_bh_call(QEMUBH *bh)
+ {
++    bool last_engaged_in_io = false;
++
++    if (bh->reentrancy_guard) {
++        last_engaged_in_io = bh->reentrancy_guard->engaged_in_io;
++        if (bh->reentrancy_guard->engaged_in_io) {
++            trace_reentrant_aio(bh->ctx, bh->name);
++        }
++        bh->reentrancy_guard->engaged_in_io = true;
++    }
++
+     bh->cb(bh->opaque);
++
++    if (bh->reentrancy_guard) {
++        bh->reentrancy_guard->engaged_in_io = last_engaged_in_io;
++    }
+ }
+ 
+ /* Multiple occurrences of aio_bh_poll cannot be called concurrently. */
+diff --git a/util/main-loop.c b/util/main-loop.c
+index 06b18b195c..1eacf04691 100644
+--- a/util/main-loop.c
++++ b/util/main-loop.c
+@@ -544,9 +544,11 @@ void main_loop_wait(int nonblocking)
+ 
+ /* Functions to operate on the main QEMU AioContext.  */
+ 
+-QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name)
++QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name,
++                         MemReentrancyGuard *reentrancy_guard)
+ {
+-    return aio_bh_new_full(qemu_aio_context, cb, opaque, name);
++    return aio_bh_new_full(qemu_aio_context, cb, opaque, name,
++                           reentrancy_guard);
+ }
+ 
+ /*
+diff --git a/util/trace-events b/util/trace-events
+index c8f53d7d9f..dc3b1eb3bf 100644
+--- a/util/trace-events
++++ b/util/trace-events
+@@ -11,6 +11,7 @@ poll_remove(void *ctx, void *node, int fd) "ctx %p node %p fd %d"
+ # async.c
+ aio_co_schedule(void *ctx, void *co) "ctx %p co %p"
+ aio_co_schedule_bh_cb(void *ctx, void *co) "ctx %p co %p"
++reentrant_aio(void *ctx, const char *name) "ctx %p name %s"
+ 
+ # thread-pool.c
+ thread_pool_submit(void *pool, void *req, void *opaque) "pool %p req %p opaque %p"
+-- 
+2.37.3
+

SOURCES/kvm-async-avoid-use-after-free-on-re-entrancy-guard.patch

@@ -0,0 +1,71 @@
+From d754050d260e2ad890cecd975df6e163c531b40e Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Tue, 9 May 2023 10:29:03 -0400
+Subject: [PATCH 09/15] async: avoid use-after-free on re-entrancy guard
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [9/12] d357650e581c3921bbfe3e2fde5e3f55853b5fab (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+
+commit 7915bd06f25e1803778081161bf6fa10c42dc7cd
+Author: Alexander Bulekov <alxndr@bu.edu>
+Date:   Mon May 1 10:19:56 2023 -0400
+
+    async: avoid use-after-free on re-entrancy guard
+
+    A BH callback can free the BH, causing a use-after-free in aio_bh_call.
+    Fix that by keeping a local copy of the re-entrancy guard pointer.
+
+    Buglink: https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=58513
+    Fixes: 9c86c97f12 ("async: Add an optional reentrancy guard to the BH API")
+    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
+    Message-Id: <20230501141956.3444868-1-alxndr@bu.edu>
+    Reviewed-by: Thomas Huth <thuth@redhat.com>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ util/async.c | 14 ++++++++------
+ 1 file changed, 8 insertions(+), 6 deletions(-)
+
+diff --git a/util/async.c b/util/async.c
+index 1fff02e7fc..ffe0541c3b 100644
+--- a/util/async.c
++++ b/util/async.c
+@@ -146,18 +146,20 @@ void aio_bh_call(QEMUBH *bh)
+ {
+     bool last_engaged_in_io = false;
+ 
+-    if (bh->reentrancy_guard) {
+-        last_engaged_in_io = bh->reentrancy_guard->engaged_in_io;
+-        if (bh->reentrancy_guard->engaged_in_io) {
++    /* Make a copy of the guard-pointer as cb may free the bh */
++    MemReentrancyGuard *reentrancy_guard = bh->reentrancy_guard;
++    if (reentrancy_guard) {
++        last_engaged_in_io = reentrancy_guard->engaged_in_io;
++        if (reentrancy_guard->engaged_in_io) {
+             trace_reentrant_aio(bh->ctx, bh->name);
+         }
+-        bh->reentrancy_guard->engaged_in_io = true;
++        reentrancy_guard->engaged_in_io = true;
+     }
+ 
+     bh->cb(bh->opaque);
+ 
+-    if (bh->reentrancy_guard) {
+-        bh->reentrancy_guard->engaged_in_io = last_engaged_in_io;
++    if (reentrancy_guard) {
++        reentrancy_guard->engaged_in_io = last_engaged_in_io;
+     }
+ }
+ 
+-- 
+2.37.3
+

SOURCES/kvm-async-clarify-usage-of-barriers-in-the-polling-case.patch

@@ -0,0 +1,66 @@
+From 187eb7a418af93375e42298d06e231e2bec3cf00 Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Thu, 9 Mar 2023 08:15:42 -0500
+Subject: [PATCH 10/13] async: clarify usage of barriers in the polling case
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw()
+RH-Bugzilla: 2168472
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Eric Auger <eric.auger@redhat.com>
+RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Commit: [10/10] 3be07ccc6137a0336becfe63a818d9cbadb38e9c
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472
+
+commit 6229438cca037d42f44a96d38feb15cb102a444f
+Author: Paolo Bonzini <pbonzini@redhat.com>
+Date:   Mon Mar 6 10:43:52 2023 +0100
+
+    async: clarify usage of barriers in the polling case
+
+    Explain that aio_context_notifier_poll() relies on
+    aio_notify_accept() to catch all the memory writes that were
+    done before ctx->notified was set to true.
+
+    Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+    Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ util/async.c | 10 ++++++++--
+ 1 file changed, 8 insertions(+), 2 deletions(-)
+
+diff --git a/util/async.c b/util/async.c
+index 795fe699b6..2a63bf90f2 100644
+--- a/util/async.c
++++ b/util/async.c
+@@ -463,8 +463,9 @@ void aio_notify_accept(AioContext *ctx)
+     qatomic_set(&ctx->notified, false);
+ 
+     /*
+-     * Write ctx->notified before reading e.g. bh->flags.  Pairs with smp_wmb
+-     * in aio_notify.
++     * Order reads of ctx->notified (in aio_context_notifier_poll()) and the
++     * above clearing of ctx->notified before reads of e.g. bh->flags.  Pairs
++     * with smp_wmb() in aio_notify.
+      */
+     smp_mb();
+ }
+@@ -487,6 +488,11 @@ static bool aio_context_notifier_poll(void *opaque)
+     EventNotifier *e = opaque;
+     AioContext *ctx = container_of(e, AioContext, notifier);
+ 
++    /*
++     * No need for load-acquire because we just want to kick the
++     * event loop.  aio_notify_accept() takes care of synchronizing
++     * the event loop with the producers.
++     */
+     return qatomic_read(&ctx->notified);
+ }
+ 
+-- 
+2.37.3
+

SOURCES/kvm-async-update-documentation-of-the-memory-barriers.patch

@@ -0,0 +1,111 @@
+From ea3856bb545d19499602830cdc3076d83a981e7a Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Thu, 9 Mar 2023 08:15:36 -0500
+Subject: [PATCH 09/13] async: update documentation of the memory barriers
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw()
+RH-Bugzilla: 2168472
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Eric Auger <eric.auger@redhat.com>
+RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Commit: [9/10] d471da2acf7a107cf75f3327c5e8d7456307160e
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472
+
+commit 8dd48650b43dfde4ebea34191ac267e474bcc29e
+Author: Paolo Bonzini <pbonzini@redhat.com>
+Date:   Mon Mar 6 10:15:06 2023 +0100
+
+    async: update documentation of the memory barriers
+
+    Ever since commit 8c6b0356b539 ("util/async: make bh_aio_poll() O(1)",
+    2020-02-22), synchronization between qemu_bh_schedule() and aio_bh_poll()
+    is happening when the bottom half is enqueued in the bh_list; not
+    when the flags are set.  Update the documentation to match.
+
+    Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ util/async.c | 33 +++++++++++++++++++--------------
+ 1 file changed, 19 insertions(+), 14 deletions(-)
+
+diff --git a/util/async.c b/util/async.c
+index 6f6717a34b..795fe699b6 100644
+--- a/util/async.c
++++ b/util/async.c
+@@ -71,14 +71,21 @@ static void aio_bh_enqueue(QEMUBH *bh, unsigned new_flags)
+     unsigned old_flags;
+ 
+     /*
+-     * The memory barrier implicit in qatomic_fetch_or makes sure that:
+-     * 1. idle & any writes needed by the callback are done before the
+-     *    locations are read in the aio_bh_poll.
+-     * 2. ctx is loaded before the callback has a chance to execute and bh
+-     *    could be freed.
++     * Synchronizes with atomic_fetch_and() in aio_bh_dequeue(), ensuring that
++     * insertion starts after BH_PENDING is set.
+      */
+     old_flags = qatomic_fetch_or(&bh->flags, BH_PENDING | new_flags);
++
+     if (!(old_flags & BH_PENDING)) {
++        /*
++         * At this point the bottom half becomes visible to aio_bh_poll().
++         * This insertion thus synchronizes with QSLIST_MOVE_ATOMIC in
++         * aio_bh_poll(), ensuring that:
++         * 1. any writes needed by the callback are visible from the callback
++         *    after aio_bh_dequeue() returns bh.
++         * 2. ctx is loaded before the callback has a chance to execute and bh
++         *    could be freed.
++         */
+         QSLIST_INSERT_HEAD_ATOMIC(&ctx->bh_list, bh, next);
+     }
+ 
+@@ -97,11 +104,8 @@ static QEMUBH *aio_bh_dequeue(BHList *head, unsigned *flags)
+     QSLIST_REMOVE_HEAD(head, next);
+ 
+     /*
+-     * The qatomic_and is paired with aio_bh_enqueue().  The implicit memory
+-     * barrier ensures that the callback sees all writes done by the scheduling
+-     * thread.  It also ensures that the scheduling thread sees the cleared
+-     * flag before bh->cb has run, and thus will call aio_notify again if
+-     * necessary.
++     * Synchronizes with qatomic_fetch_or() in aio_bh_enqueue(), ensuring that
++     * the removal finishes before BH_PENDING is reset.
+      */
+     *flags = qatomic_fetch_and(&bh->flags,
+                               ~(BH_PENDING | BH_SCHEDULED | BH_IDLE));
+@@ -148,6 +152,7 @@ int aio_bh_poll(AioContext *ctx)
+     BHListSlice *s;
+     int ret = 0;
+ 
++    /* Synchronizes with QSLIST_INSERT_HEAD_ATOMIC in aio_bh_enqueue().  */
+     QSLIST_MOVE_ATOMIC(&slice.bh_list, &ctx->bh_list);
+     QSIMPLEQ_INSERT_TAIL(&ctx->bh_slice_list, &slice, next);
+ 
+@@ -437,15 +442,15 @@ LuringState *aio_get_linux_io_uring(AioContext *ctx)
+ void aio_notify(AioContext *ctx)
+ {
+     /*
+-     * Write e.g. bh->flags before writing ctx->notified.  Pairs with smp_mb in
+-     * aio_notify_accept.
++     * Write e.g. ctx->bh_list before writing ctx->notified.  Pairs with
++     * smp_mb() in aio_notify_accept().
+      */
+     smp_wmb();
+     qatomic_set(&ctx->notified, true);
+ 
+     /*
+-     * Write ctx->notified before reading ctx->notify_me.  Pairs
+-     * with smp_mb in aio_ctx_prepare or aio_poll.
++     * Write ctx->notified (and also ctx->bh_list) before reading ctx->notify_me.
++     * Pairs with smp_mb() in aio_ctx_prepare or aio_poll.
+      */
+     smp_mb();
+     if (qatomic_read(&ctx->notify_me)) {
+-- 
+2.37.3
+

SOURCES/kvm-backends-hostmem-Fix-support-of-memory-backend-memfd.patch

@@ -0,0 +1,71 @@
+From 60da56e3685969493ae483c3cc2c66af13d00baf Mon Sep 17 00:00:00 2001
+From: Thomas Huth <thuth@redhat.com>
+Date: Wed, 10 Aug 2022 14:57:18 +0200
+Subject: [PATCH 1/3] backends/hostmem: Fix support of memory-backend-memfd in
+ qemu_maxrampagesize()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <None>
+RH-MergeRequest: 221: backends/hostmem: Fix support of memory-backend-memfd in qemu_maxrampagesize()
+RH-Bugzilla: 2117149
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Commit: [1/1] b5a1047750af32c0a261b8385ea0e819eb16681a
+
+It is currently not possible yet to use "memory-backend-memfd" on s390x
+with hugepages enabled. This problem is caused by qemu_maxrampagesize()
+not taking memory-backend-memfd objects into account yet, so the code
+in s390_memory_init() fails to enable the huge page support there via
+s390_set_max_pagesize(). Fix it by generalizing the code, so that it
+looks at qemu_ram_pagesize(memdev->mr.ram_block) instead of re-trying
+to get the information from the filesystem.
+
+Suggested-by: David Hildenbrand <david@redhat.com>
+Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2116496
+Message-Id: <20220810125720.3849835-2-thuth@redhat.com>
+Reviewed-by: David Hildenbrand <david@redhat.com>
+Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+(cherry picked from commit 8be934b70e923104da883b990dee18f02552d40e)
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2117149
+[clg: Resolved conflict on qemu_real_host_page_size() ]
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ backends/hostmem.c | 14 ++------------
+ 1 file changed, 2 insertions(+), 12 deletions(-)
+
+diff --git a/backends/hostmem.c b/backends/hostmem.c
+index 4c05862ed5..0c4654ea85 100644
+--- a/backends/hostmem.c
++++ b/backends/hostmem.c
+@@ -305,22 +305,12 @@ bool host_memory_backend_is_mapped(HostMemoryBackend *backend)
+     return backend->is_mapped;
+ }
+ 
+-#ifdef __linux__
+ size_t host_memory_backend_pagesize(HostMemoryBackend *memdev)
+ {
+-    Object *obj = OBJECT(memdev);
+-    char *path = object_property_get_str(obj, "mem-path", NULL);
+-    size_t pagesize = qemu_mempath_getpagesize(path);
+-
+-    g_free(path);
++    size_t pagesize = qemu_ram_pagesize(memdev->mr.ram_block);
++    g_assert(pagesize >= qemu_real_host_page_size);
+     return pagesize;
+ }
+-#else
+-size_t host_memory_backend_pagesize(HostMemoryBackend *memdev)
+-{
+-    return qemu_real_host_page_size;
+-}
+-#endif
+ 
+ static void
+ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
+-- 
+2.35.3
+

SOURCES/kvm-bcm2835_property-disable-reentrancy-detection-for-io.patch

@@ -0,0 +1,58 @@
+From 7715635d018351e0a5c4c25aec2c71a2fe3b9e69 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Tue, 9 May 2023 10:29:03 -0400
+Subject: [PATCH 06/15] bcm2835_property: disable reentrancy detection for
+ iomem
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [6/12] 4d6187430ca1c4309a36824c0c6815d2a763db1a (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+
+commit 985c4a4e547afb9573b6bd6843d20eb2c3d1d1cd
+Author: Alexander Bulekov <alxndr@bu.edu>
+Date:   Thu Apr 27 17:10:11 2023 -0400
+
+    bcm2835_property: disable reentrancy detection for iomem
+
+    As the code is designed for re-entrant calls from bcm2835_property to
+    bcm2835_mbox and back into bcm2835_property, mark iomem as
+    reentrancy-safe.
+
+    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
+    Reviewed-by: Thomas Huth <thuth@redhat.com>
+    Message-Id: <20230427211013.2994127-7-alxndr@bu.edu>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/misc/bcm2835_property.c | 7 +++++++
+ 1 file changed, 7 insertions(+)
+
+diff --git a/hw/misc/bcm2835_property.c b/hw/misc/bcm2835_property.c
+index 73941bdae9..022b5a849c 100644
+--- a/hw/misc/bcm2835_property.c
++++ b/hw/misc/bcm2835_property.c
+@@ -377,6 +377,13 @@ static void bcm2835_property_init(Object *obj)
+ 
+     memory_region_init_io(&s->iomem, OBJECT(s), &bcm2835_property_ops, s,
+                           TYPE_BCM2835_PROPERTY, 0x10);
++
++    /*
++     * bcm2835_property_ops call into bcm2835_mbox, which in-turn reads from
++     * iomem. As such, mark iomem as re-entracy safe.
++     */
++    s->iomem.disable_reentrancy_guard = true;
++
+     sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem);
+     sysbus_init_irq(SYS_BUS_DEVICE(s), &s->mbox_irq);
+ }
+-- 
+2.37.3
+

SOURCES/kvm-block-Collapse-padded-I-O-vecs-exceeding-IOV_MAX.patch

@@ -0,0 +1,359 @@
+From 1f7520baa6f0bf02ccba2ebfe7d1d5bf6520f95a Mon Sep 17 00:00:00 2001
+From: Hanna Czenczek <hreitz@redhat.com>
+Date: Tue, 11 Apr 2023 19:34:16 +0200
+Subject: [PATCH 2/5] block: Collapse padded I/O vecs exceeding IOV_MAX
+
+RH-Author: Hanna Czenczek <hreitz@redhat.com>
+RH-MergeRequest: 291: block: Split padded I/O vectors exceeding IOV_MAX
+RH-Bugzilla: 2141964
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Commit: [2/5] 1d86ce8398e4ab66e308a686f9855c963e52b0a9
+
+When processing vectored guest requests that are not aligned to the
+storage request alignment, we pad them by adding head and/or tail
+buffers for a read-modify-write cycle.
+
+The guest can submit I/O vectors up to IOV_MAX (1024) in length, but
+with this padding, the vector can exceed that limit.  As of
+4c002cef0e9abe7135d7916c51abce47f7fc1ee2 ("util/iov: make
+qemu_iovec_init_extended() honest"), we refuse to pad vectors beyond the
+limit, instead returning an error to the guest.
+
+To the guest, this appears as a random I/O error.  We should not return
+an I/O error to the guest when it issued a perfectly valid request.
+
+Before 4c002cef0e9abe7135d7916c51abce47f7fc1ee2, we just made the vector
+longer than IOV_MAX, which generally seems to work (because the guest
+assumes a smaller alignment than we really have, file-posix's
+raw_co_prw() will generally see bdrv_qiov_is_aligned() return false, and
+so emulate the request, so that the IOV_MAX does not matter).  However,
+that does not seem exactly great.
+
+I see two ways to fix this problem:
+1. We split such long requests into two requests.
+2. We join some elements of the vector into new buffers to make it
+   shorter.
+
+I am wary of (1), because it seems like it may have unintended side
+effects.
+
+(2) on the other hand seems relatively simple to implement, with
+hopefully few side effects, so this patch does that.
+
+To do this, the use of qemu_iovec_init_extended() in bdrv_pad_request()
+is effectively replaced by the new function bdrv_create_padded_qiov(),
+which not only wraps the request IOV with padding head/tail, but also
+ensures that the resulting vector will not have more than IOV_MAX
+elements.  Putting that functionality into qemu_iovec_init_extended() is
+infeasible because it requires allocating a bounce buffer; doing so
+would require many more parameters (buffer alignment, how to initialize
+the buffer, and out parameters like the buffer, its length, and the
+original elements), which is not reasonable.
+
+Conversely, it is not difficult to move qemu_iovec_init_extended()'s
+functionality into bdrv_create_padded_qiov() by using public
+qemu_iovec_* functions, so that is what this patch does.
+
+Because bdrv_pad_request() was the only "serious" user of
+qemu_iovec_init_extended(), the next patch will remove the latter
+function, so the functionality is not implemented twice.
+
+Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2141964
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+Message-Id: <20230411173418.19549-3-hreitz@redhat.com>
+Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+(cherry picked from commit 18743311b829cafc1737a5f20bc3248d5f91ee2a)
+
+Conflicts:
+	block/io.c: Downstream bdrv_pad_request() has no @flags
+        parameter.
+
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+---
+ block/io.c | 166 ++++++++++++++++++++++++++++++++++++++++++++++++-----
+ 1 file changed, 151 insertions(+), 15 deletions(-)
+
+diff --git a/block/io.c b/block/io.c
+index c3e7301613..0fe8f0dd40 100644
+--- a/block/io.c
++++ b/block/io.c
+@@ -1624,6 +1624,14 @@ out:
+  * @merge_reads is true for small requests,
+  * if @buf_len == @head + bytes + @tail. In this case it is possible that both
+  * head and tail exist but @buf_len == align and @tail_buf == @buf.
++ *
++ * @write is true for write requests, false for read requests.
++ *
++ * If padding makes the vector too long (exceeding IOV_MAX), then we need to
++ * merge existing vector elements into a single one.  @collapse_bounce_buf acts
++ * as the bounce buffer in such cases.  @pre_collapse_qiov has the pre-collapse
++ * I/O vector elements so for read requests, the data can be copied back after
++ * the read is done.
+  */
+ typedef struct BdrvRequestPadding {
+     uint8_t *buf;
+@@ -1632,11 +1640,17 @@ typedef struct BdrvRequestPadding {
+     size_t head;
+     size_t tail;
+     bool merge_reads;
++    bool write;
+     QEMUIOVector local_qiov;
++
++    uint8_t *collapse_bounce_buf;
++    size_t collapse_len;
++    QEMUIOVector pre_collapse_qiov;
+ } BdrvRequestPadding;
+ 
+ static bool bdrv_init_padding(BlockDriverState *bs,
+                               int64_t offset, int64_t bytes,
++                              bool write,
+                               BdrvRequestPadding *pad)
+ {
+     int64_t align = bs->bl.request_alignment;
+@@ -1668,6 +1682,8 @@ static bool bdrv_init_padding(BlockDriverState *bs,
+         pad->tail_buf = pad->buf + pad->buf_len - align;
+     }
+ 
++    pad->write = write;
++
+     return true;
+ }
+ 
+@@ -1733,8 +1749,23 @@ zero_mem:
+     return 0;
+ }
+ 
+-static void bdrv_padding_destroy(BdrvRequestPadding *pad)
++/**
++ * Free *pad's associated buffers, and perform any necessary finalization steps.
++ */
++static void bdrv_padding_finalize(BdrvRequestPadding *pad)
+ {
++    if (pad->collapse_bounce_buf) {
++        if (!pad->write) {
++            /*
++             * If padding required elements in the vector to be collapsed into a
++             * bounce buffer, copy the bounce buffer content back
++             */
++            qemu_iovec_from_buf(&pad->pre_collapse_qiov, 0,
++                                pad->collapse_bounce_buf, pad->collapse_len);
++        }
++        qemu_vfree(pad->collapse_bounce_buf);
++        qemu_iovec_destroy(&pad->pre_collapse_qiov);
++    }
+     if (pad->buf) {
+         qemu_vfree(pad->buf);
+         qemu_iovec_destroy(&pad->local_qiov);
+@@ -1742,6 +1773,101 @@ static void bdrv_padding_destroy(BdrvRequestPadding *pad)
+     memset(pad, 0, sizeof(*pad));
+ }
+ 
++/*
++ * Create pad->local_qiov by wrapping @iov in the padding head and tail, while
++ * ensuring that the resulting vector will not exceed IOV_MAX elements.
++ *
++ * To ensure this, when necessary, the first two or three elements of @iov are
++ * merged into pad->collapse_bounce_buf and replaced by a reference to that
++ * bounce buffer in pad->local_qiov.
++ *
++ * After performing a read request, the data from the bounce buffer must be
++ * copied back into pad->pre_collapse_qiov (e.g. by bdrv_padding_finalize()).
++ */
++static int bdrv_create_padded_qiov(BlockDriverState *bs,
++                                   BdrvRequestPadding *pad,
++                                   struct iovec *iov, int niov,
++                                   size_t iov_offset, size_t bytes)
++{
++    int padded_niov, surplus_count, collapse_count;
++
++    /* Assert this invariant */
++    assert(niov <= IOV_MAX);
++
++    /*
++     * Cannot pad if resulting length would exceed SIZE_MAX.  Returning an error
++     * to the guest is not ideal, but there is little else we can do.  At least
++     * this will practically never happen on 64-bit systems.
++     */
++    if (SIZE_MAX - pad->head < bytes ||
++        SIZE_MAX - pad->head - bytes < pad->tail)
++    {
++        return -EINVAL;
++    }
++
++    /* Length of the resulting IOV if we just concatenated everything */
++    padded_niov = !!pad->head + niov + !!pad->tail;
++
++    qemu_iovec_init(&pad->local_qiov, MIN(padded_niov, IOV_MAX));
++
++    if (pad->head) {
++        qemu_iovec_add(&pad->local_qiov, pad->buf, pad->head);
++    }
++
++    /*
++     * If padded_niov > IOV_MAX, we cannot just concatenate everything.
++     * Instead, merge the first two or three elements of @iov to reduce the
++     * number of vector elements as necessary.
++     */
++    if (padded_niov > IOV_MAX) {
++        /*
++         * Only head and tail can have lead to the number of entries exceeding
++         * IOV_MAX, so we can exceed it by the head and tail at most.  We need
++         * to reduce the number of elements by `surplus_count`, so we merge that
++         * many elements plus one into one element.
++         */
++        surplus_count = padded_niov - IOV_MAX;
++        assert(surplus_count <= !!pad->head + !!pad->tail);
++        collapse_count = surplus_count + 1;
++
++        /*
++         * Move the elements to collapse into `pad->pre_collapse_qiov`, then
++         * advance `iov` (and associated variables) by those elements.
++         */
++        qemu_iovec_init(&pad->pre_collapse_qiov, collapse_count);
++        qemu_iovec_concat_iov(&pad->pre_collapse_qiov, iov,
++                              collapse_count, iov_offset, SIZE_MAX);
++        iov += collapse_count;
++        iov_offset = 0;
++        niov -= collapse_count;
++        bytes -= pad->pre_collapse_qiov.size;
++
++        /*
++         * Construct the bounce buffer to match the length of the to-collapse
++         * vector elements, and for write requests, initialize it with the data
++         * from those elements.  Then add it to `pad->local_qiov`.
++         */
++        pad->collapse_len = pad->pre_collapse_qiov.size;
++        pad->collapse_bounce_buf = qemu_blockalign(bs, pad->collapse_len);
++        if (pad->write) {
++            qemu_iovec_to_buf(&pad->pre_collapse_qiov, 0,
++                              pad->collapse_bounce_buf, pad->collapse_len);
++        }
++        qemu_iovec_add(&pad->local_qiov,
++                       pad->collapse_bounce_buf, pad->collapse_len);
++    }
++
++    qemu_iovec_concat_iov(&pad->local_qiov, iov, niov, iov_offset, bytes);
++
++    if (pad->tail) {
++        qemu_iovec_add(&pad->local_qiov,
++                       pad->buf + pad->buf_len - pad->tail, pad->tail);
++    }
++
++    assert(pad->local_qiov.niov == MIN(padded_niov, IOV_MAX));
++    return 0;
++}
++
+ /*
+  * bdrv_pad_request
+  *
+@@ -1749,6 +1875,8 @@ static void bdrv_padding_destroy(BdrvRequestPadding *pad)
+  * read of padding, bdrv_padding_rmw_read() should be called separately if
+  * needed.
+  *
++ * @write is true for write requests, false for read requests.
++ *
+  * Request parameters (@qiov, &qiov_offset, &offset, &bytes) are in-out:
+  *  - on function start they represent original request
+  *  - on failure or when padding is not needed they are unchanged
+@@ -1757,25 +1885,33 @@ static void bdrv_padding_destroy(BdrvRequestPadding *pad)
+ static int bdrv_pad_request(BlockDriverState *bs,
+                             QEMUIOVector **qiov, size_t *qiov_offset,
+                             int64_t *offset, int64_t *bytes,
++                            bool write,
+                             BdrvRequestPadding *pad, bool *padded)
+ {
+     int ret;
++    struct iovec *sliced_iov;
++    int sliced_niov;
++    size_t sliced_head, sliced_tail;
+ 
+     bdrv_check_qiov_request(*offset, *bytes, *qiov, *qiov_offset, &error_abort);
+ 
+-    if (!bdrv_init_padding(bs, *offset, *bytes, pad)) {
++    if (!bdrv_init_padding(bs, *offset, *bytes, write, pad)) {
+         if (padded) {
+             *padded = false;
+         }
+         return 0;
+     }
+ 
+-    ret = qemu_iovec_init_extended(&pad->local_qiov, pad->buf, pad->head,
+-                                   *qiov, *qiov_offset, *bytes,
+-                                   pad->buf + pad->buf_len - pad->tail,
+-                                   pad->tail);
++    sliced_iov = qemu_iovec_slice(*qiov, *qiov_offset, *bytes,
++                                  &sliced_head, &sliced_tail,
++                                  &sliced_niov);
++
++    /* Guaranteed by bdrv_check_qiov_request() */
++    assert(*bytes <= SIZE_MAX);
++    ret = bdrv_create_padded_qiov(bs, pad, sliced_iov, sliced_niov,
++                                  sliced_head, *bytes);
+     if (ret < 0) {
+-        bdrv_padding_destroy(pad);
++        bdrv_padding_finalize(pad);
+         return ret;
+     }
+     *bytes += pad->head + pad->tail;
+@@ -1836,8 +1972,8 @@ int coroutine_fn bdrv_co_preadv_part(BdrvChild *child,
+         flags |= BDRV_REQ_COPY_ON_READ;
+     }
+ 
+-    ret = bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad,
+-                           NULL);
++    ret = bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, false,
++                           &pad, NULL);
+     if (ret < 0) {
+         goto fail;
+     }
+@@ -1847,7 +1983,7 @@ int coroutine_fn bdrv_co_preadv_part(BdrvChild *child,
+                               bs->bl.request_alignment,
+                               qiov, qiov_offset, flags);
+     tracked_request_end(&req);
+-    bdrv_padding_destroy(&pad);
++    bdrv_padding_finalize(&pad);
+ 
+ fail:
+     bdrv_dec_in_flight(bs);
+@@ -2167,7 +2303,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
+     bool padding;
+     BdrvRequestPadding pad;
+ 
+-    padding = bdrv_init_padding(bs, offset, bytes, &pad);
++    padding = bdrv_init_padding(bs, offset, bytes, true, &pad);
+     if (padding) {
+         bdrv_make_request_serialising(req, align);
+ 
+@@ -2214,7 +2350,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
+     }
+ 
+ out:
+-    bdrv_padding_destroy(&pad);
++    bdrv_padding_finalize(&pad);
+ 
+     return ret;
+ }
+@@ -2280,8 +2416,8 @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
+          * bdrv_co_do_zero_pwritev() does aligning by itself, so, we do
+          * alignment only if there is no ZERO flag.
+          */
+-        ret = bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad,
+-                               &padded);
++        ret = bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, true,
++                               &pad, &padded);
+         if (ret < 0) {
+             return ret;
+         }
+@@ -2310,7 +2446,7 @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
+     ret = bdrv_aligned_pwritev(child, &req, offset, bytes, align,
+                                qiov, qiov_offset, flags);
+ 
+-    bdrv_padding_destroy(&pad);
++    bdrv_padding_finalize(&pad);
+ 
+ out:
+     tracked_request_end(&req);
+-- 
+2.39.3
+

SOURCES/kvm-block-Fix-pad_request-s-request-restriction.patch

@@ -0,0 +1,75 @@
+From b9866279996ee065cb524bf30bc70e22efbab303 Mon Sep 17 00:00:00 2001
+From: Hanna Czenczek <hreitz@redhat.com>
+Date: Fri, 14 Jul 2023 10:59:38 +0200
+Subject: [PATCH 5/5] block: Fix pad_request's request restriction
+
+RH-Author: Hanna Czenczek <hreitz@redhat.com>
+RH-MergeRequest: 291: block: Split padded I/O vectors exceeding IOV_MAX
+RH-Bugzilla: 2141964
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Commit: [5/5] f9188bd089d6c67185ea1accde20d491a2ed3193
+
+bdrv_pad_request() relies on requests' lengths not to exceed SIZE_MAX,
+which bdrv_check_qiov_request() does not guarantee.
+
+bdrv_check_request32() however will guarantee this, and both of
+bdrv_pad_request()'s callers (bdrv_co_preadv_part() and
+bdrv_co_pwritev_part()) already run it before calling
+bdrv_pad_request().  Therefore, bdrv_pad_request() can safely call
+bdrv_check_request32() without expecting error, too.
+
+In effect, this patch will not change guest-visible behavior.  It is a
+clean-up to tighten a condition to match what is guaranteed by our
+callers, and which exists purely to show clearly why the subsequent
+assertion (`assert(*bytes <= SIZE_MAX)`) is always true.
+
+Note there is a difference between the interfaces of
+bdrv_check_qiov_request() and bdrv_check_request32(): The former takes
+an errp, the latter does not, so we can no longer just pass
+&error_abort.  Instead, we need to check the returned value.  While we
+do expect success (because the callers have already run this function),
+an assert(ret == 0) is not much simpler than just to return an error if
+it occurs, so let us handle errors by returning them up the stack now.
+
+Reported-by: Peter Maydell <peter.maydell@linaro.org>
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+Message-id: 20230714085938.202730-1-hreitz@redhat.com
+Fixes: 18743311b829cafc1737a5f20bc3248d5f91ee2a
+       ("block: Collapse padded I/O vecs exceeding IOV_MAX")
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+---
+ block/io.c | 8 ++++++--
+ 1 file changed, 6 insertions(+), 2 deletions(-)
+
+diff --git a/block/io.c b/block/io.c
+index 0fe8f0dd40..8ae57728a6 100644
+--- a/block/io.c
++++ b/block/io.c
+@@ -1893,7 +1893,11 @@ static int bdrv_pad_request(BlockDriverState *bs,
+     int sliced_niov;
+     size_t sliced_head, sliced_tail;
+ 
+-    bdrv_check_qiov_request(*offset, *bytes, *qiov, *qiov_offset, &error_abort);
++    /* Should have been checked by the caller already */
++    ret = bdrv_check_request32(*offset, *bytes, *qiov, *qiov_offset);
++    if (ret < 0) {
++        return ret;
++    }
+ 
+     if (!bdrv_init_padding(bs, *offset, *bytes, write, pad)) {
+         if (padded) {
+@@ -1906,7 +1910,7 @@ static int bdrv_pad_request(BlockDriverState *bs,
+                                   &sliced_head, &sliced_tail,
+                                   &sliced_niov);
+ 
+-    /* Guaranteed by bdrv_check_qiov_request() */
++    /* Guaranteed by bdrv_check_request32() */
+     assert(*bytes <= SIZE_MAX);
+     ret = bdrv_create_padded_qiov(bs, pad, sliced_iov, sliced_niov,
+                                   sliced_head, *bytes);
+-- 
+2.39.3
+

SOURCES/kvm-block-mirror-Do-not-wait-for-active-writes.patch

@@ -0,0 +1,153 @@
+From 192f956f2b0761f270070555f8feb1f0544e5558 Mon Sep 17 00:00:00 2001
+From: Hanna Reitz <hreitz@redhat.com>
+Date: Wed, 9 Nov 2022 17:54:48 +0100
+Subject: [PATCH 01/11] block/mirror: Do not wait for active writes
+
+RH-Author: Hanna Czenczek <hreitz@redhat.com>
+RH-MergeRequest: 246: block/mirror: Make active mirror progress even under full load
+RH-Bugzilla: 2125119
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Commit: [1/3] 652d1e55b954f13eaec2c86f58735d4942837e16
+
+Waiting for all active writes to settle before daring to create a
+background copying operation means that we will never do background
+operations while the guest does anything (in write-blocking mode), and
+therefore cannot converge.  Yes, we also will not diverge, but actually
+converging would be even nicer.
+
+It is unclear why we did decide to wait for all active writes to settle
+before creating a background operation, but it just does not seem
+necessary.  Active writes will put themselves into the in_flight bitmap
+and thus properly block actually conflicting background requests.
+
+It is important for active requests to wait on overlapping background
+requests, which we do in active_write_prepare().  However, so far it was
+not documented why it is important.  Add such documentation now, and
+also to the other call of mirror_wait_on_conflicts(), so that it becomes
+more clear why and when requests need to actively wait for other
+requests to settle.
+
+Another thing to note is that of course we need to ensure that there are
+no active requests when the job completes, but that is done by virtue of
+the BDS being drained anyway, so there cannot be any active requests at
+that point.
+
+With this change, we will need to explicitly keep track of how many
+bytes are in flight in active requests so that
+job_progress_set_remaining() in mirror_run() can set the correct number
+of remaining bytes.
+
+Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2123297
+Signed-off-by: Hanna Reitz <hreitz@redhat.com>
+Message-Id: <20221109165452.67927-2-hreitz@redhat.com>
+Reviewed-by: Kevin Wolf <kwolf@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit d69a879bdf1aed586478eaa161ee064fe1b92f1a)
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+---
+ block/mirror.c | 37 ++++++++++++++++++++++++++++++-------
+ 1 file changed, 30 insertions(+), 7 deletions(-)
+
+diff --git a/block/mirror.c b/block/mirror.c
+index efec2c7674..282f428cb7 100644
+--- a/block/mirror.c
++++ b/block/mirror.c
+@@ -81,6 +81,7 @@ typedef struct MirrorBlockJob {
+     int max_iov;
+     bool initial_zeroing_ongoing;
+     int in_active_write_counter;
++    int64_t active_write_bytes_in_flight;
+     bool prepared;
+     bool in_drain;
+ } MirrorBlockJob;
+@@ -493,6 +494,13 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
+     }
+     bdrv_dirty_bitmap_unlock(s->dirty_bitmap);
+ 
++    /*
++     * Wait for concurrent requests to @offset.  The next loop will limit the
++     * copied area based on in_flight_bitmap so we only copy an area that does
++     * not overlap with concurrent in-flight requests.  Still, we would like to
++     * copy something, so wait until there are at least no more requests to the
++     * very beginning of the area.
++     */
+     mirror_wait_on_conflicts(NULL, s, offset, 1);
+ 
+     job_pause_point(&s->common.job);
+@@ -993,12 +1001,6 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
+         int64_t cnt, delta;
+         bool should_complete;
+ 
+-        /* Do not start passive operations while there are active
+-         * writes in progress */
+-        while (s->in_active_write_counter) {
+-            mirror_wait_for_any_operation(s, true);
+-        }
+-
+         if (s->ret < 0) {
+             ret = s->ret;
+             goto immediate_exit;
+@@ -1015,7 +1017,9 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
+         /* cnt is the number of dirty bytes remaining and s->bytes_in_flight is
+          * the number of bytes currently being processed; together those are
+          * the current remaining operation length */
+-        job_progress_set_remaining(&s->common.job, s->bytes_in_flight + cnt);
++        job_progress_set_remaining(&s->common.job,
++                                   s->bytes_in_flight + cnt +
++                                   s->active_write_bytes_in_flight);
+ 
+         /* Note that even when no rate limit is applied we need to yield
+          * periodically with no pending I/O so that bdrv_drain_all() returns.
+@@ -1073,6 +1077,10 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
+ 
+             s->in_drain = true;
+             bdrv_drained_begin(bs);
++
++            /* Must be zero because we are drained */
++            assert(s->in_active_write_counter == 0);
++
+             cnt = bdrv_get_dirty_count(s->dirty_bitmap);
+             if (cnt > 0 || mirror_flush(s) < 0) {
+                 bdrv_drained_end(bs);
+@@ -1306,6 +1314,7 @@ do_sync_target_write(MirrorBlockJob *job, MirrorMethod method,
+     }
+ 
+     job_progress_increase_remaining(&job->common.job, bytes);
++    job->active_write_bytes_in_flight += bytes;
+ 
+     switch (method) {
+     case MIRROR_METHOD_COPY:
+@@ -1327,6 +1336,7 @@ do_sync_target_write(MirrorBlockJob *job, MirrorMethod method,
+         abort();
+     }
+ 
++    job->active_write_bytes_in_flight -= bytes;
+     if (ret >= 0) {
+         job_progress_update(&job->common.job, bytes);
+     } else {
+@@ -1375,6 +1385,19 @@ static MirrorOp *coroutine_fn active_write_prepare(MirrorBlockJob *s,
+ 
+     s->in_active_write_counter++;
+ 
++    /*
++     * Wait for concurrent requests affecting the area.  If there are already
++     * running requests that are copying off now-to-be stale data in the area,
++     * we must wait for them to finish before we begin writing fresh data to the
++     * target so that the write operations appear in the correct order.
++     * Note that background requests (see mirror_iteration()) in contrast only
++     * wait for conflicting requests at the start of the dirty area, and then
++     * (based on the in_flight_bitmap) truncate the area to copy so it will not
++     * conflict with any requests beyond that.  For active writes, however, we
++     * cannot truncate that area.  The request from our parent must be blocked
++     * until the area is copied in full.  Therefore, we must wait for the whole
++     * area to become free of concurrent requests.
++     */
+     mirror_wait_on_conflicts(op, s, offset, bytes);
+ 
+     bitmap_set(s->in_flight_bitmap, start_chunk, end_chunk - start_chunk);
+-- 
+2.37.3
+

SOURCES/kvm-block-mirror-Drop-mirror_wait_for_any_operation.patch

@@ -0,0 +1,76 @@
+From 57c79ed20cb73aa9aa4dd7487379b85ea3f936f6 Mon Sep 17 00:00:00 2001
+From: Hanna Reitz <hreitz@redhat.com>
+Date: Wed, 9 Nov 2022 17:54:49 +0100
+Subject: [PATCH 02/11] block/mirror: Drop mirror_wait_for_any_operation()
+
+RH-Author: Hanna Czenczek <hreitz@redhat.com>
+RH-MergeRequest: 246: block/mirror: Make active mirror progress even under full load
+RH-Bugzilla: 2125119
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Commit: [2/3] dec37883bcc491441ae08d9592d1ec26a47765c0
+
+mirror_wait_for_free_in_flight_slot() is the only remaining user of
+mirror_wait_for_any_operation(), so inline the latter into the former.
+
+Signed-off-by: Hanna Reitz <hreitz@redhat.com>
+Message-Id: <20221109165452.67927-3-hreitz@redhat.com>
+Reviewed-by: Kevin Wolf <kwolf@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit eb994912993077f178ccb43b20e422ecf9ae4ac7)
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+---
+ block/mirror.c | 21 ++++++++-------------
+ 1 file changed, 8 insertions(+), 13 deletions(-)
+
+diff --git a/block/mirror.c b/block/mirror.c
+index 282f428cb7..6b02555ad7 100644
+--- a/block/mirror.c
++++ b/block/mirror.c
+@@ -304,19 +304,21 @@ static int mirror_cow_align(MirrorBlockJob *s, int64_t *offset,
+ }
+ 
+ static inline void coroutine_fn
+-mirror_wait_for_any_operation(MirrorBlockJob *s, bool active)
++mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s)
+ {
+     MirrorOp *op;
+ 
+     QTAILQ_FOREACH(op, &s->ops_in_flight, next) {
+-        /* Do not wait on pseudo ops, because it may in turn wait on
++        /*
++         * Do not wait on pseudo ops, because it may in turn wait on
+          * some other operation to start, which may in fact be the
+          * caller of this function.  Since there is only one pseudo op
+          * at any given time, we will always find some real operation
+-         * to wait on. */
+-        if (!op->is_pseudo_op && op->is_in_flight &&
+-            op->is_active_write == active)
+-        {
++         * to wait on.
++         * Also, do not wait on active operations, because they do not
++         * use up in-flight slots.
++         */
++        if (!op->is_pseudo_op && op->is_in_flight && !op->is_active_write) {
+             qemu_co_queue_wait(&op->waiting_requests, NULL);
+             return;
+         }
+@@ -324,13 +326,6 @@ mirror_wait_for_any_operation(MirrorBlockJob *s, bool active)
+     abort();
+ }
+ 
+-static inline void coroutine_fn
+-mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s)
+-{
+-    /* Only non-active operations use up in-flight slots */
+-    mirror_wait_for_any_operation(s, false);
+-}
+-
+ /* Perform a mirror copy operation.
+  *
+  * *op->bytes_handled is set to the number of bytes copied after and
+-- 
+2.37.3
+

SOURCES/kvm-block-mirror-Fix-NULL-s-job-in-active-writes.patch

@@ -0,0 +1,75 @@
+From b1f5aa5a342a25dc558ee9d435fed0643fe5155f Mon Sep 17 00:00:00 2001
+From: Hanna Reitz <hreitz@redhat.com>
+Date: Wed, 9 Nov 2022 17:54:50 +0100
+Subject: [PATCH 03/11] block/mirror: Fix NULL s->job in active writes
+
+RH-Author: Hanna Czenczek <hreitz@redhat.com>
+RH-MergeRequest: 246: block/mirror: Make active mirror progress even under full load
+RH-Bugzilla: 2125119
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Commit: [3/3] 49d7ebd15667151a6e14228a8260cfdd0aa27a78
+
+There is a small gap in mirror_start_job() before putting the mirror
+filter node into the block graph (bdrv_append() call) and the actual job
+being created.  Before the job is created, MirrorBDSOpaque.job is NULL.
+
+It is possible that requests come in when bdrv_drained_end() is called,
+and those requests would see MirrorBDSOpaque.job == NULL.  Have our
+filter node handle that case gracefully.
+
+Signed-off-by: Hanna Reitz <hreitz@redhat.com>
+Message-Id: <20221109165452.67927-4-hreitz@redhat.com>
+Reviewed-by: Kevin Wolf <kwolf@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit da93d5c84e56e6b4e84aa8e98b6b984c9b6bb528)
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+---
+ block/mirror.c | 20 ++++++++++++--------
+ 1 file changed, 12 insertions(+), 8 deletions(-)
+
+diff --git a/block/mirror.c b/block/mirror.c
+index 6b02555ad7..50289fca49 100644
+--- a/block/mirror.c
++++ b/block/mirror.c
+@@ -1438,11 +1438,13 @@ static int coroutine_fn bdrv_mirror_top_do_write(BlockDriverState *bs,
+     MirrorOp *op = NULL;
+     MirrorBDSOpaque *s = bs->opaque;
+     int ret = 0;
+-    bool copy_to_target;
++    bool copy_to_target = false;
+ 
+-    copy_to_target = s->job->ret >= 0 &&
+-                     !job_is_cancelled(&s->job->common.job) &&
+-                     s->job->copy_mode == MIRROR_COPY_MODE_WRITE_BLOCKING;
++    if (s->job) {
++        copy_to_target = s->job->ret >= 0 &&
++                         !job_is_cancelled(&s->job->common.job) &&
++                         s->job->copy_mode == MIRROR_COPY_MODE_WRITE_BLOCKING;
++    }
+ 
+     if (copy_to_target) {
+         op = active_write_prepare(s->job, offset, bytes);
+@@ -1487,11 +1489,13 @@ static int coroutine_fn bdrv_mirror_top_pwritev(BlockDriverState *bs,
+     QEMUIOVector bounce_qiov;
+     void *bounce_buf;
+     int ret = 0;
+-    bool copy_to_target;
++    bool copy_to_target = false;
+ 
+-    copy_to_target = s->job->ret >= 0 &&
+-                     !job_is_cancelled(&s->job->common.job) &&
+-                     s->job->copy_mode == MIRROR_COPY_MODE_WRITE_BLOCKING;
++    if (s->job) {
++        copy_to_target = s->job->ret >= 0 &&
++                         !job_is_cancelled(&s->job->common.job) &&
++                         s->job->copy_mode == MIRROR_COPY_MODE_WRITE_BLOCKING;
++    }
+ 
+     if (copy_to_target) {
+         /* The guest might concurrently modify the data to write; but
+-- 
+2.37.3
+

SOURCES/kvm-checkpatch-add-qemu_bh_new-aio_bh_new-checks.patch

@@ -0,0 +1,56 @@
+From 866a3b56f6a2d43f3cf7b3313fb41808bc5e6e1f Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Tue, 9 May 2023 10:29:03 -0400
+Subject: [PATCH 03/15] checkpatch: add qemu_bh_new/aio_bh_new checks
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [3/12] 620b480b0878c18223f3cc103450bc16aa6d7e21 (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+
+commit ef56ffbdd6b0605dc1e305611287b948c970e236
+Author: Alexander Bulekov <alxndr@bu.edu>
+Date:   Thu Apr 27 17:10:08 2023 -0400
+
+    checkpatch: add qemu_bh_new/aio_bh_new checks
+
+    Advise authors to use the _guarded versions of the APIs, instead.
+
+    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
+    Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
+    Message-Id: <20230427211013.2994127-4-alxndr@bu.edu>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ scripts/checkpatch.pl | 8 ++++++++
+ 1 file changed, 8 insertions(+)
+
+diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
+index cb8eff233e..b2428e80cc 100755
+--- a/scripts/checkpatch.pl
++++ b/scripts/checkpatch.pl
+@@ -2858,6 +2858,14 @@ sub process {
+ 		if ($line =~ /\bsignal\s*\(/ && !($line =~ /SIG_(?:IGN|DFL)/)) {
+ 			ERROR("use sigaction to establish signal handlers; signal is not portable\n" . $herecurr);
+ 		}
++# recommend qemu_bh_new_guarded instead of qemu_bh_new
++        if ($realfile =~ /.*\/hw\/.*/ && $line =~ /\bqemu_bh_new\s*\(/) {
++			ERROR("use qemu_bh_new_guarded() instead of qemu_bh_new() to avoid reentrancy problems\n" . $herecurr);
++		}
++# recommend aio_bh_new_guarded instead of aio_bh_new
++        if ($realfile =~ /.*\/hw\/.*/ && $line =~ /\baio_bh_new\s*\(/) {
++			ERROR("use aio_bh_new_guarded() instead of aio_bh_new() to avoid reentrancy problems\n" . $herecurr);
++		}
+ # check for module_init(), use category-specific init macros explicitly please
+ 		if ($line =~ /^module_init\s*\(/) {
+ 			ERROR("please use block_init(), type_init() etc. instead of module_init()\n" . $herecurr);
+-- 
+2.37.3
+

SOURCES/kvm-dma-helpers-prevent-dma_blk_cb-vs-dma_aio_cancel-rac.patch

@@ -0,0 +1,127 @@
+From 103608465b8bd2edf7f9aaef5c3c93309ccf9ec2 Mon Sep 17 00:00:00 2001
+From: Stefan Hajnoczi <stefanha@redhat.com>
+Date: Tue, 21 Feb 2023 16:22:17 -0500
+Subject: [PATCH 12/13] dma-helpers: prevent dma_blk_cb() vs dma_aio_cancel()
+ race
+
+RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
+RH-MergeRequest: 264: scsi: protect req->aiocb with AioContext lock
+RH-Bugzilla: 2090990
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Commit: [2/3] 14f5835093ba8c5111f3ada2fe87730371aca733
+
+dma_blk_cb() only takes the AioContext lock around ->io_func(). That
+means the rest of dma_blk_cb() is not protected. In particular, the
+DMAAIOCB field accesses happen outside the lock.
+
+There is a race when the main loop thread holds the AioContext lock and
+invokes scsi_device_purge_requests() -> bdrv_aio_cancel() ->
+dma_aio_cancel() while an IOThread executes dma_blk_cb(). The dbs->acb
+field determines how cancellation proceeds. If dma_aio_cancel() sees
+dbs->acb == NULL while dma_blk_cb() is still running, the request can be
+completed twice (-ECANCELED and the actual return value).
+
+The following assertion can occur with virtio-scsi when an IOThread is
+used:
+
+  ../hw/scsi/scsi-disk.c:368: scsi_dma_complete: Assertion `r->req.aiocb != NULL' failed.
+
+Fix the race by holding the AioContext across dma_blk_cb(). Now
+dma_aio_cancel() under the AioContext lock will not see
+inconsistent/intermediate states.
+
+Cc: Paolo Bonzini <pbonzini@redhat.com>
+Reviewed-by: Eric Blake <eblake@redhat.com>
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+Message-Id: <20230221212218.1378734-3-stefanha@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit abfcd2760b3e70727bbc0792221b8b98a733dc32)
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+---
+ hw/scsi/scsi-disk.c   |  4 +---
+ softmmu/dma-helpers.c | 12 +++++++-----
+ 2 files changed, 8 insertions(+), 8 deletions(-)
+
+diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
+index 179ce22c4a..c8109a673e 100644
+--- a/hw/scsi/scsi-disk.c
++++ b/hw/scsi/scsi-disk.c
+@@ -351,13 +351,12 @@ done:
+     scsi_req_unref(&r->req);
+ }
+ 
++/* Called with AioContext lock held */
+ static void scsi_dma_complete(void *opaque, int ret)
+ {
+     SCSIDiskReq *r = (SCSIDiskReq *)opaque;
+     SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev);
+ 
+-    aio_context_acquire(blk_get_aio_context(s->qdev.conf.blk));
+-
+     assert(r->req.aiocb != NULL);
+     r->req.aiocb = NULL;
+ 
+@@ -367,7 +366,6 @@ static void scsi_dma_complete(void *opaque, int ret)
+         block_acct_done(blk_get_stats(s->qdev.conf.blk), &r->acct);
+     }
+     scsi_dma_complete_noio(r, ret);
+-    aio_context_release(blk_get_aio_context(s->qdev.conf.blk));
+ }
+ 
+ static void scsi_read_complete_noio(SCSIDiskReq *r, int ret)
+diff --git a/softmmu/dma-helpers.c b/softmmu/dma-helpers.c
+index 7d766a5e89..42af18719a 100644
+--- a/softmmu/dma-helpers.c
++++ b/softmmu/dma-helpers.c
+@@ -127,17 +127,19 @@ static void dma_complete(DMAAIOCB *dbs, int ret)
+ static void dma_blk_cb(void *opaque, int ret)
+ {
+     DMAAIOCB *dbs = (DMAAIOCB *)opaque;
++    AioContext *ctx = dbs->ctx;
+     dma_addr_t cur_addr, cur_len;
+     void *mem;
+ 
+     trace_dma_blk_cb(dbs, ret);
+ 
++    aio_context_acquire(ctx);
+     dbs->acb = NULL;
+     dbs->offset += dbs->iov.size;
+ 
+     if (dbs->sg_cur_index == dbs->sg->nsg || ret < 0) {
+         dma_complete(dbs, ret);
+-        return;
++        goto out;
+     }
+     dma_blk_unmap(dbs);
+ 
+@@ -177,9 +179,9 @@ static void dma_blk_cb(void *opaque, int ret)
+ 
+     if (dbs->iov.size == 0) {
+         trace_dma_map_wait(dbs);
+-        dbs->bh = aio_bh_new(dbs->ctx, reschedule_dma, dbs);
++        dbs->bh = aio_bh_new(ctx, reschedule_dma, dbs);
+         cpu_register_map_client(dbs->bh);
+-        return;
++        goto out;
+     }
+ 
+     if (!QEMU_IS_ALIGNED(dbs->iov.size, dbs->align)) {
+@@ -187,11 +189,11 @@ static void dma_blk_cb(void *opaque, int ret)
+                                 QEMU_ALIGN_DOWN(dbs->iov.size, dbs->align));
+     }
+ 
+-    aio_context_acquire(dbs->ctx);
+     dbs->acb = dbs->io_func(dbs->offset, &dbs->iov,
+                             dma_blk_cb, dbs, dbs->io_func_opaque);
+-    aio_context_release(dbs->ctx);
+     assert(dbs->acb);
++out:
++    aio_context_release(ctx);
+ }
+ 
+ static void dma_aio_cancel(BlockAIOCB *acb)
+-- 
+2.37.3
+

SOURCES/kvm-docs-system-s390x-Document-the-loadparm-machine-prop.patch

@@ -0,0 +1,70 @@
+From 407e23d7f0c9020404247afe7d4df98505222bbb Mon Sep 17 00:00:00 2001
+From: Thomas Huth <thuth@redhat.com>
+Date: Mon, 14 Nov 2022 14:25:02 +0100
+Subject: [PATCH 1/3] docs/system/s390x: Document the "loadparm" machine
+ property
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Thomas Huth <thuth@redhat.com>
+RH-MergeRequest: 233: s390x: Document the "loadparm" machine property
+RH-Bugzilla: 2128225
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Cédric Le Goater <clg@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [1/2] e9589ea32d2a8f82971476b644e1063fa14cf822
+
+The "loadparm" machine property is useful for selecting alternative
+kernels on the disk of the guest, but so far we do not tell the users
+yet how to use it. Add some documentation to fill this gap.
+
+Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2128235
+Message-Id: <20221114132502.110213-1-thuth@redhat.com>
+Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+(cherry picked from commit be5df2edb5d69ff3107c5616aa035a9ba8d0422e)
+---
+ docs/system/s390x/bootdevices.rst | 26 ++++++++++++++++++++++++++
+ 1 file changed, 26 insertions(+)
+
+diff --git a/docs/system/s390x/bootdevices.rst b/docs/system/s390x/bootdevices.rst
+index 9e591cb9dc..d4bf3b9f0b 100644
+--- a/docs/system/s390x/bootdevices.rst
++++ b/docs/system/s390x/bootdevices.rst
+@@ -53,6 +53,32 @@ recommended to specify a CD-ROM device via ``-device scsi-cd`` (as mentioned
+ above) instead.
+ 
+ 
++Selecting kernels with the ``loadparm`` property
++------------------------------------------------
++
++The ``s390-ccw-virtio`` machine supports the so-called ``loadparm`` parameter
++which can be used to select the kernel on the disk of the guest that the
++s390-ccw bios should boot. When starting QEMU, it can be specified like this::
++
++ qemu-system-s390x -machine s390-ccw-virtio,loadparm=<string>
++
++The first way to use this parameter is to use the word ``PROMPT`` as the
++``<string>`` here. In that case the s390-ccw bios will show a list of
++installed kernels on the disk of the guest and ask the user to enter a number
++to chose which kernel should be booted -- similar to what can be achieved by
++specifying the ``-boot menu=on`` option when starting QEMU. Note that the menu
++list will only show the names of the installed kernels when using a DASD-like
++disk image with 4k byte sectors. On normal SCSI-style disks with 512-byte
++sectors, there is not enough space for the zipl loader on the disk to store
++the kernel names, so you only get a list without names here.
++
++The second way to use this parameter is to use a number in the range from 0
++to 31. The numbers that can be used here correspond to the numbers that are
++shown when using the ``PROMPT`` option, and the s390-ccw bios will then try
++to automatically boot the kernel that is associated with the given number.
++Note that ``0`` can be used to boot the default entry.
++
++
+ Booting from a network device
+ -----------------------------
+ 
+-- 
+2.37.3
+

SOURCES/kvm-dump-Add-arch-cleanup-function.patch

@@ -0,0 +1,69 @@
+From 837e09b1a8a38b53488f59aad090fbe6bb94e257 Mon Sep 17 00:00:00 2001
+From: Thomas Huth <thuth@redhat.com>
+Date: Fri, 17 Nov 2023 11:32:37 +0100
+Subject: [PATCH 2/3] dump: Add arch cleanup function
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Thomas Huth <thuth@redhat.com>
+RH-MergeRequest: 323: Fix problem that secure execution guest might remain in "paused" state after failed dump
+RH-Jira: RHEL-16696
+RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+RH-Acked-by: Cédric Le Goater <clg@redhat.com>
+RH-Commit: [2/3] b70f406dec88ffd4877f3d5d580fc8f821bdb252
+
+JIRA: https://issues.redhat.com/browse/RHEL-16696
+
+commit e72629e5149aba6f44122ea6d2a803ef136a0c6b
+Author: Janosch Frank <frankja@linux.ibm.com>
+Date:   Thu Nov 9 12:04:42 2023 +0000
+
+    dump: Add arch cleanup function
+
+    Some architectures (s390x) need to cleanup after a failed dump to be
+    able to continue to run the vm. Add a cleanup function pointer and
+    call it if it's set.
+
+    Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+    Reviewed-by: Thomas Huth <thuth@redhat.com>
+    Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+    Message-ID: <20231109120443.185979-3-frankja@linux.ibm.com>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+---
+ dump/dump.c                | 4 ++++
+ include/sysemu/dump-arch.h | 1 +
+ 2 files changed, 5 insertions(+)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 5dee060b73..93edb89547 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -100,6 +100,10 @@ uint64_t cpu_to_dump64(DumpState *s, uint64_t val)
+ 
+ static int dump_cleanup(DumpState *s)
+ {
++    if (s->dump_info.arch_cleanup_fn) {
++        s->dump_info.arch_cleanup_fn(s);
++    }
++
+     guest_phys_blocks_free(&s->guest_phys_blocks);
+     memory_mapping_list_free(&s->list);
+     close(s->fd);
+diff --git a/include/sysemu/dump-arch.h b/include/sysemu/dump-arch.h
+index 59bbc9be38..743916e46c 100644
+--- a/include/sysemu/dump-arch.h
++++ b/include/sysemu/dump-arch.h
+@@ -24,6 +24,7 @@ typedef struct ArchDumpInfo {
+     void (*arch_sections_add_fn)(DumpState *s);
+     uint64_t (*arch_sections_write_hdr_fn)(DumpState *s, uint8_t *buff);
+     int (*arch_sections_write_fn)(DumpState *s, uint8_t *buff);
++    void (*arch_cleanup_fn)(DumpState *s);
+ } ArchDumpInfo;
+ 
+ struct GuestPhysBlockList; /* memory_mapping.h */
+-- 
+2.39.3
+

SOURCES/kvm-dump-Add-architecture-section-and-section-string-tab.patch

@@ -0,0 +1,356 @@
+From f2f3efff83dddd38a97699cd2701f46f61a732e3 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Mon, 17 Oct 2022 11:32:10 +0000
+Subject: [PATCH 36/42] dump: Add architecture section and section string table
+ support
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [36/41] 83b98ff185e93e62703f686b65546d60c783d783
+
+Add hooks which architectures can use to add arbitrary data to custom
+sections.
+
+Also add a section name string table in order to identify section
+contents
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20221017113210.41674-1-frankja@linux.ibm.com>
+(cherry picked from commit 9b72224f44612ddd5b434a1bccf79346946d11da)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c                | 186 +++++++++++++++++++++++++++++++------
+ include/sysemu/dump-arch.h |   3 +
+ include/sysemu/dump.h      |   3 +
+ 3 files changed, 166 insertions(+), 26 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 7a42401790..4aa8fb64d2 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -104,6 +104,7 @@ static int dump_cleanup(DumpState *s)
+     memory_mapping_list_free(&s->list);
+     close(s->fd);
+     g_free(s->guest_note);
++    g_array_unref(s->string_table_buf);
+     s->guest_note = NULL;
+     if (s->resume) {
+         if (s->detached) {
+@@ -153,11 +154,10 @@ static void prepare_elf64_header(DumpState *s, Elf64_Ehdr *elf_header)
+     elf_header->e_phoff = cpu_to_dump64(s, s->phdr_offset);
+     elf_header->e_phentsize = cpu_to_dump16(s, sizeof(Elf64_Phdr));
+     elf_header->e_phnum = cpu_to_dump16(s, phnum);
+-    if (s->shdr_num) {
+-        elf_header->e_shoff = cpu_to_dump64(s, s->shdr_offset);
+-        elf_header->e_shentsize = cpu_to_dump16(s, sizeof(Elf64_Shdr));
+-        elf_header->e_shnum = cpu_to_dump16(s, s->shdr_num);
+-    }
++    elf_header->e_shoff = cpu_to_dump64(s, s->shdr_offset);
++    elf_header->e_shentsize = cpu_to_dump16(s, sizeof(Elf64_Shdr));
++    elf_header->e_shnum = cpu_to_dump16(s, s->shdr_num);
++    elf_header->e_shstrndx = cpu_to_dump16(s, s->shdr_num - 1);
+ }
+ 
+ static void prepare_elf32_header(DumpState *s, Elf32_Ehdr *elf_header)
+@@ -181,11 +181,10 @@ static void prepare_elf32_header(DumpState *s, Elf32_Ehdr *elf_header)
+     elf_header->e_phoff = cpu_to_dump32(s, s->phdr_offset);
+     elf_header->e_phentsize = cpu_to_dump16(s, sizeof(Elf32_Phdr));
+     elf_header->e_phnum = cpu_to_dump16(s, phnum);
+-    if (s->shdr_num) {
+-        elf_header->e_shoff = cpu_to_dump32(s, s->shdr_offset);
+-        elf_header->e_shentsize = cpu_to_dump16(s, sizeof(Elf32_Shdr));
+-        elf_header->e_shnum = cpu_to_dump16(s, s->shdr_num);
+-    }
++    elf_header->e_shoff = cpu_to_dump32(s, s->shdr_offset);
++    elf_header->e_shentsize = cpu_to_dump16(s, sizeof(Elf32_Shdr));
++    elf_header->e_shnum = cpu_to_dump16(s, s->shdr_num);
++    elf_header->e_shstrndx = cpu_to_dump16(s, s->shdr_num - 1);
+ }
+ 
+ static void write_elf_header(DumpState *s, Error **errp)
+@@ -196,6 +195,8 @@ static void write_elf_header(DumpState *s, Error **errp)
+     void *header_ptr;
+     int ret;
+ 
++    /* The NULL header and the shstrtab are always defined */
++    assert(s->shdr_num >= 2);
+     if (dump_is_64bit(s)) {
+         prepare_elf64_header(s, &elf64_header);
+         header_size = sizeof(elf64_header);
+@@ -394,17 +395,49 @@ static void prepare_elf_section_hdr_zero(DumpState *s)
+     }
+ }
+ 
+-static void prepare_elf_section_hdrs(DumpState *s)
++static void prepare_elf_section_hdr_string(DumpState *s, void *buff)
++{
++    uint64_t index = s->string_table_buf->len;
++    const char strtab[] = ".shstrtab";
++    Elf32_Shdr shdr32 = {};
++    Elf64_Shdr shdr64 = {};
++    int shdr_size;
++    void *shdr;
++
++    g_array_append_vals(s->string_table_buf, strtab, sizeof(strtab));
++    if (dump_is_64bit(s)) {
++        shdr_size = sizeof(Elf64_Shdr);
++        shdr64.sh_type = SHT_STRTAB;
++        shdr64.sh_offset = s->section_offset + s->elf_section_data_size;
++        shdr64.sh_name = index;
++        shdr64.sh_size = s->string_table_buf->len;
++        shdr = &shdr64;
++    } else {
++        shdr_size = sizeof(Elf32_Shdr);
++        shdr32.sh_type = SHT_STRTAB;
++        shdr32.sh_offset = s->section_offset + s->elf_section_data_size;
++        shdr32.sh_name = index;
++        shdr32.sh_size = s->string_table_buf->len;
++        shdr = &shdr32;
++    }
++    memcpy(buff, shdr, shdr_size);
++}
++
++static bool prepare_elf_section_hdrs(DumpState *s, Error **errp)
+ {
+     size_t len, sizeof_shdr;
++    void *buff_hdr;
+ 
+     /*
+      * Section ordering:
+      * - HDR zero
++     * - Arch section hdrs
++     * - String table hdr
+      */
+     sizeof_shdr = dump_is_64bit(s) ? sizeof(Elf64_Shdr) : sizeof(Elf32_Shdr);
+     len = sizeof_shdr * s->shdr_num;
+     s->elf_section_hdrs = g_malloc0(len);
++    buff_hdr = s->elf_section_hdrs;
+ 
+     /*
+      * The first section header is ALWAYS a special initial section
+@@ -420,6 +453,26 @@ static void prepare_elf_section_hdrs(DumpState *s)
+     if (s->phdr_num >= PN_XNUM) {
+         prepare_elf_section_hdr_zero(s);
+     }
++    buff_hdr += sizeof_shdr;
++
++    /* Add architecture defined section headers */
++    if (s->dump_info.arch_sections_write_hdr_fn
++        && s->shdr_num > 2) {
++        buff_hdr += s->dump_info.arch_sections_write_hdr_fn(s, buff_hdr);
++
++        if (s->shdr_num >= SHN_LORESERVE) {
++            error_setg_errno(errp, EINVAL,
++                             "dump: too many architecture defined sections");
++            return false;
++        }
++    }
++
++    /*
++     * String table is the last section since strings are added via
++     * arch_sections_write_hdr().
++     */
++    prepare_elf_section_hdr_string(s, buff_hdr);
++    return true;
+ }
+ 
+ static void write_elf_section_headers(DumpState *s, Error **errp)
+@@ -427,7 +480,9 @@ static void write_elf_section_headers(DumpState *s, Error **errp)
+     size_t sizeof_shdr = dump_is_64bit(s) ? sizeof(Elf64_Shdr) : sizeof(Elf32_Shdr);
+     int ret;
+ 
+-    prepare_elf_section_hdrs(s);
++    if (!prepare_elf_section_hdrs(s, errp)) {
++        return;
++    }
+ 
+     ret = fd_write_vmcore(s->elf_section_hdrs, s->shdr_num * sizeof_shdr, s);
+     if (ret < 0) {
+@@ -437,6 +492,29 @@ static void write_elf_section_headers(DumpState *s, Error **errp)
+     g_free(s->elf_section_hdrs);
+ }
+ 
++static void write_elf_sections(DumpState *s, Error **errp)
++{
++    int ret;
++
++    if (s->elf_section_data_size) {
++        /* Write architecture section data */
++        ret = fd_write_vmcore(s->elf_section_data,
++                              s->elf_section_data_size, s);
++        if (ret < 0) {
++            error_setg_errno(errp, -ret,
++                             "dump: failed to write architecture section data");
++            return;
++        }
++    }
++
++    /* Write string table */
++    ret = fd_write_vmcore(s->string_table_buf->data,
++                          s->string_table_buf->len, s);
++    if (ret < 0) {
++        error_setg_errno(errp, -ret, "dump: failed to write string table data");
++    }
++}
++
+ static void write_data(DumpState *s, void *buf, int length, Error **errp)
+ {
+     int ret;
+@@ -693,6 +771,31 @@ static void dump_iterate(DumpState *s, Error **errp)
+     }
+ }
+ 
++static void dump_end(DumpState *s, Error **errp)
++{
++    int rc;
++    ERRP_GUARD();
++
++    if (s->elf_section_data_size) {
++        s->elf_section_data = g_malloc0(s->elf_section_data_size);
++    }
++
++    /* Adds the architecture defined section data to s->elf_section_data  */
++    if (s->dump_info.arch_sections_write_fn &&
++        s->elf_section_data_size) {
++        rc = s->dump_info.arch_sections_write_fn(s, s->elf_section_data);
++        if (rc) {
++            error_setg_errno(errp, rc,
++                             "dump: failed to get arch section data");
++            g_free(s->elf_section_data);
++            return;
++        }
++    }
++
++    /* write sections to vmcore */
++    write_elf_sections(s, errp);
++}
++
+ static void create_vmcore(DumpState *s, Error **errp)
+ {
+     ERRP_GUARD();
+@@ -702,7 +805,14 @@ static void create_vmcore(DumpState *s, Error **errp)
+         return;
+     }
+ 
++    /* Iterate over memory and dump it to file */
+     dump_iterate(s, errp);
++    if (*errp) {
++        return;
++    }
++
++    /* Write the section data */
++    dump_end(s, errp);
+ }
+ 
+ static int write_start_flat_header(int fd)
+@@ -1720,6 +1830,14 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+     s->filter_area_begin = begin;
+     s->filter_area_length = length;
+ 
++    /* First index is 0, it's the special null name */
++    s->string_table_buf = g_array_new(FALSE, TRUE, 1);
++    /*
++     * Allocate the null name, due to the clearing option set to true
++     * it will be 0.
++     */
++    g_array_set_size(s->string_table_buf, 1);
++
+     memory_mapping_list_init(&s->list);
+ 
+     guest_phys_blocks_init(&s->guest_phys_blocks);
+@@ -1856,26 +1974,42 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+     }
+ 
+     /*
+-     * calculate phdr_num
++     * The first section header is always a special one in which most
++     * fields are 0. The section header string table is also always
++     * set.
++     */
++    s->shdr_num = 2;
++
++    /*
++     * Adds the number of architecture sections to shdr_num and sets
++     * elf_section_data_size so we know the offsets and sizes of all
++     * parts.
++     */
++    if (s->dump_info.arch_sections_add_fn) {
++        s->dump_info.arch_sections_add_fn(s);
++    }
++
++    /*
++     * calculate shdr_num so we know the offsets and sizes of all
++     * parts.
++     * Calculate phdr_num
+      *
+-     * the type of ehdr->e_phnum is uint16_t, so we should avoid overflow
++     * The absolute maximum amount of phdrs is UINT32_MAX - 1 as
++     * sh_info is 32 bit. There's special handling once we go over
++     * UINT16_MAX - 1 but that is handled in the ehdr and section
++     * code.
+      */
+-    s->phdr_num = 1; /* PT_NOTE */
+-    if (s->list.num < UINT16_MAX - 2) {
+-        s->shdr_num = 0;
++    s->phdr_num = 1; /* Reserve PT_NOTE */
++    if (s->list.num <= UINT32_MAX - 1) {
+         s->phdr_num += s->list.num;
+     } else {
+-        /* sh_info of section 0 holds the real number of phdrs */
+-        s->shdr_num = 1;
+-
+-        /* the type of shdr->sh_info is uint32_t, so we should avoid overflow */
+-        if (s->list.num <= UINT32_MAX - 1) {
+-            s->phdr_num += s->list.num;
+-        } else {
+-            s->phdr_num = UINT32_MAX;
+-        }
++        s->phdr_num = UINT32_MAX;
+     }
+ 
++    /*
++     * Now that the number of section and program headers is known we
++     * can calculate the offsets of the headers and data.
++     */
+     if (dump_is_64bit(s)) {
+         s->shdr_offset = sizeof(Elf64_Ehdr);
+         s->phdr_offset = s->shdr_offset + sizeof(Elf64_Shdr) * s->shdr_num;
+diff --git a/include/sysemu/dump-arch.h b/include/sysemu/dump-arch.h
+index e25b02e990..59bbc9be38 100644
+--- a/include/sysemu/dump-arch.h
++++ b/include/sysemu/dump-arch.h
+@@ -21,6 +21,9 @@ typedef struct ArchDumpInfo {
+     uint32_t page_size;      /* The target's page size. If it's variable and
+                               * unknown, then this should be the maximum. */
+     uint64_t phys_base;      /* The target's physmem base. */
++    void (*arch_sections_add_fn)(DumpState *s);
++    uint64_t (*arch_sections_write_hdr_fn)(DumpState *s, uint8_t *buff);
++    int (*arch_sections_write_fn)(DumpState *s, uint8_t *buff);
+ } ArchDumpInfo;
+ 
+ struct GuestPhysBlockList; /* memory_mapping.h */
+diff --git a/include/sysemu/dump.h b/include/sysemu/dump.h
+index 9ed811b313..38ccac7190 100644
+--- a/include/sysemu/dump.h
++++ b/include/sysemu/dump.h
+@@ -180,6 +180,9 @@ typedef struct DumpState {
+     hwaddr note_offset;
+ 
+     void *elf_section_hdrs;     /* Pointer to section header buffer */
++    void *elf_section_data;     /* Pointer to section data buffer */
++    uint64_t elf_section_data_size; /* Size of section data */
++    GArray *string_table_buf;   /* String table data buffer */
+ 
+     uint8_t *note_buf;          /* buffer for notes */
+     size_t note_buf_offset;     /* the writing place in note_buf */
+-- 
+2.37.3
+

SOURCES/kvm-dump-Add-more-offset-variables.patch

@@ -0,0 +1,138 @@
+From bee31226b87d0b05faae84e88cce3af1b8dabbfd Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Wed, 30 Mar 2022 12:35:59 +0000
+Subject: [PATCH 17/42] dump: Add more offset variables
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [17/41] fbe629e1476e8a0e039f989af6e1f4707075ba01
+
+Offset calculations are easy enough to get wrong. Let's add a few
+variables to make moving around elf headers and data sections easier.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Message-Id: <20220330123603.107120-6-frankja@linux.ibm.com>
+(cherry picked from commit e71d353360bb09a8e784e35d78370c691f6ea185)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c           | 35 +++++++++++++++--------------------
+ include/sysemu/dump.h |  4 ++++
+ 2 files changed, 19 insertions(+), 20 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 5cc2322325..85a402b38c 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -142,13 +142,11 @@ static void write_elf64_header(DumpState *s, Error **errp)
+     elf_header.e_machine = cpu_to_dump16(s, s->dump_info.d_machine);
+     elf_header.e_version = cpu_to_dump32(s, EV_CURRENT);
+     elf_header.e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
+-    elf_header.e_phoff = cpu_to_dump64(s, sizeof(Elf64_Ehdr));
++    elf_header.e_phoff = cpu_to_dump64(s, s->phdr_offset);
+     elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf64_Phdr));
+     elf_header.e_phnum = cpu_to_dump16(s, phnum);
+     if (s->shdr_num) {
+-        uint64_t shoff = sizeof(Elf64_Ehdr) + sizeof(Elf64_Phdr) * s->phdr_num;
+-
+-        elf_header.e_shoff = cpu_to_dump64(s, shoff);
++        elf_header.e_shoff = cpu_to_dump64(s, s->shdr_offset);
+         elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf64_Shdr));
+         elf_header.e_shnum = cpu_to_dump16(s, s->shdr_num);
+     }
+@@ -179,13 +177,11 @@ static void write_elf32_header(DumpState *s, Error **errp)
+     elf_header.e_machine = cpu_to_dump16(s, s->dump_info.d_machine);
+     elf_header.e_version = cpu_to_dump32(s, EV_CURRENT);
+     elf_header.e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
+-    elf_header.e_phoff = cpu_to_dump32(s, sizeof(Elf32_Ehdr));
++    elf_header.e_phoff = cpu_to_dump32(s, s->phdr_offset);
+     elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf32_Phdr));
+     elf_header.e_phnum = cpu_to_dump16(s, phnum);
+     if (s->shdr_num) {
+-        uint32_t shoff = sizeof(Elf32_Ehdr) + sizeof(Elf32_Phdr) * s->phdr_num;
+-
+-        elf_header.e_shoff = cpu_to_dump32(s, shoff);
++        elf_header.e_shoff = cpu_to_dump32(s, s->shdr_offset);
+         elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf32_Shdr));
+         elf_header.e_shnum = cpu_to_dump16(s, s->shdr_num);
+     }
+@@ -248,12 +244,11 @@ static void write_elf32_load(DumpState *s, MemoryMapping *memory_mapping,
+ static void write_elf64_note(DumpState *s, Error **errp)
+ {
+     Elf64_Phdr phdr;
+-    hwaddr begin = s->memory_offset - s->note_size;
+     int ret;
+ 
+     memset(&phdr, 0, sizeof(Elf64_Phdr));
+     phdr.p_type = cpu_to_dump32(s, PT_NOTE);
+-    phdr.p_offset = cpu_to_dump64(s, begin);
++    phdr.p_offset = cpu_to_dump64(s, s->note_offset);
+     phdr.p_paddr = 0;
+     phdr.p_filesz = cpu_to_dump64(s, s->note_size);
+     phdr.p_memsz = cpu_to_dump64(s, s->note_size);
+@@ -313,13 +308,12 @@ static void write_elf64_notes(WriteCoreDumpFunction f, DumpState *s,
+ 
+ static void write_elf32_note(DumpState *s, Error **errp)
+ {
+-    hwaddr begin = s->memory_offset - s->note_size;
+     Elf32_Phdr phdr;
+     int ret;
+ 
+     memset(&phdr, 0, sizeof(Elf32_Phdr));
+     phdr.p_type = cpu_to_dump32(s, PT_NOTE);
+-    phdr.p_offset = cpu_to_dump32(s, begin);
++    phdr.p_offset = cpu_to_dump32(s, s->note_offset);
+     phdr.p_paddr = 0;
+     phdr.p_filesz = cpu_to_dump32(s, s->note_size);
+     phdr.p_memsz = cpu_to_dump32(s, s->note_size);
+@@ -1826,15 +1820,16 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+     }
+ 
+     if (s->dump_info.d_class == ELFCLASS64) {
+-        s->memory_offset = sizeof(Elf64_Ehdr) +
+-                           sizeof(Elf64_Phdr) * s->phdr_num +
+-                           sizeof(Elf64_Shdr) * s->shdr_num +
+-                           s->note_size;
++        s->phdr_offset = sizeof(Elf64_Ehdr);
++        s->shdr_offset = s->phdr_offset + sizeof(Elf64_Phdr) * s->phdr_num;
++        s->note_offset = s->shdr_offset + sizeof(Elf64_Shdr) * s->shdr_num;
++        s->memory_offset = s->note_offset + s->note_size;
+     } else {
+-        s->memory_offset = sizeof(Elf32_Ehdr) +
+-                           sizeof(Elf32_Phdr) * s->phdr_num +
+-                           sizeof(Elf32_Shdr) * s->shdr_num +
+-                           s->note_size;
++
++        s->phdr_offset = sizeof(Elf32_Ehdr);
++        s->shdr_offset = s->phdr_offset + sizeof(Elf32_Phdr) * s->phdr_num;
++        s->note_offset = s->shdr_offset + sizeof(Elf32_Shdr) * s->shdr_num;
++        s->memory_offset = s->note_offset + s->note_size;
+     }
+ 
+     return;
+diff --git a/include/sysemu/dump.h b/include/sysemu/dump.h
+index 19458bffbd..ffc2ea1072 100644
+--- a/include/sysemu/dump.h
++++ b/include/sysemu/dump.h
+@@ -159,6 +159,10 @@ typedef struct DumpState {
+     bool resume;
+     bool detached;
+     ssize_t note_size;
++    hwaddr shdr_offset;
++    hwaddr phdr_offset;
++    hwaddr section_offset;
++    hwaddr note_offset;
+     hwaddr memory_offset;
+     int fd;
+ 
+-- 
+2.37.3
+

SOURCES/kvm-dump-Cleanup-dump_begin-write-functions.patch

@@ -0,0 +1,94 @@
+From cbb653d73e32513ccd46b293a52384eed6a5f84f Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Wed, 30 Mar 2022 12:36:02 +0000
+Subject: [PATCH 20/42] dump: Cleanup dump_begin write functions
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [20/41] 18ea1457a3e54fd368e556d96c3be50c6ad0a6bd
+
+There's no need to have a gigantic if in there let's move the elf
+32/64 bit logic into the section, segment or note code.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220330123603.107120-9-frankja@linux.ibm.com>
+(cherry picked from commit 5ff2e5a3e1e67930e523486e39549a33fcf97227)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 42 +++++++++++-------------------------------
+ 1 file changed, 11 insertions(+), 31 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 823ca32883..88abde355a 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -565,46 +565,26 @@ static void dump_begin(DumpState *s, Error **errp)
+         return;
+     }
+ 
+-    if (dump_is_64bit(s)) {
+-        /* write all PT_LOAD to vmcore */
+-        write_elf_loads(s, errp);
++    /* write all PT_LOAD to vmcore */
++    write_elf_loads(s, errp);
++    if (*errp) {
++        return;
++    }
++
++    /* write section to vmcore */
++    if (s->shdr_num) {
++        write_elf_section(s, 1, errp);
+         if (*errp) {
+             return;
+         }
++    }
+ 
+-        /* write section to vmcore */
+-        if (s->shdr_num) {
+-            write_elf_section(s, 1, errp);
+-            if (*errp) {
+-                return;
+-            }
+-        }
+-
++    if (dump_is_64bit(s)) {
+         /* write notes to vmcore */
+         write_elf64_notes(fd_write_vmcore, s, errp);
+-        if (*errp) {
+-            return;
+-        }
+     } else {
+-        /* write all PT_LOAD to vmcore */
+-        write_elf_loads(s, errp);
+-        if (*errp) {
+-            return;
+-        }
+-
+-        /* write section to vmcore */
+-        if (s->shdr_num) {
+-            write_elf_section(s, 0, errp);
+-            if (*errp) {
+-                return;
+-            }
+-        }
+-
+         /* write notes to vmcore */
+         write_elf32_notes(fd_write_vmcore, s, errp);
+-        if (*errp) {
+-            return;
+-        }
+     }
+ }
+ 
+-- 
+2.37.3
+

SOURCES/kvm-dump-Consolidate-elf-note-function.patch

@@ -0,0 +1,67 @@
+From 0547599cf507930f91943f22d5f917ebacf69484 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Wed, 30 Mar 2022 12:36:03 +0000
+Subject: [PATCH 21/42] dump: Consolidate elf note function
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [21/41] 52298c098c116aea75ad15894731ff412c2c4e73
+
+Just like with the other write functions let's move the 32/64 bit elf
+handling to a function to improve readability.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220330123603.107120-10-frankja@linux.ibm.com>
+(cherry picked from commit c68124738bc29017e4254c898bc40be7be477af7)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 18 +++++++++++-------
+ 1 file changed, 11 insertions(+), 7 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 88abde355a..a451abc590 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -520,6 +520,15 @@ static void write_elf_loads(DumpState *s, Error **errp)
+     }
+ }
+ 
++static void write_elf_notes(DumpState *s, Error **errp)
++{
++    if (dump_is_64bit(s)) {
++        write_elf64_notes(fd_write_vmcore, s, errp);
++    } else {
++        write_elf32_notes(fd_write_vmcore, s, errp);
++    }
++}
++
+ /* write elf header, PT_NOTE and elf note to vmcore. */
+ static void dump_begin(DumpState *s, Error **errp)
+ {
+@@ -579,13 +588,8 @@ static void dump_begin(DumpState *s, Error **errp)
+         }
+     }
+ 
+-    if (dump_is_64bit(s)) {
+-        /* write notes to vmcore */
+-        write_elf64_notes(fd_write_vmcore, s, errp);
+-    } else {
+-        /* write notes to vmcore */
+-        write_elf32_notes(fd_write_vmcore, s, errp);
+-    }
++    /* write notes to vmcore */
++    write_elf_notes(s, errp);
+ }
+ 
+ static int get_next_block(DumpState *s, GuestPhysBlock *block)
+-- 
+2.37.3
+

SOURCES/kvm-dump-Consolidate-phdr-note-writes.patch

@@ -0,0 +1,169 @@
+From f87abe1ef14e80731249ebe9fe1bea569a68e9b4 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Wed, 30 Mar 2022 12:36:01 +0000
+Subject: [PATCH 19/42] dump: Consolidate phdr note writes
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [19/41] 180c4c0ab4941a0bf366dc7f32ee035e03daa6c0
+
+There's no need to have two write functions. Let's rather have two
+functions that set the data for elf 32/64 and then write it in a
+common function.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220330123603.107120-8-frankja@linux.ibm.com>
+(cherry picked from commit bc7d558017e6700f9a05c61b0b638a8994945f0d)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 94 +++++++++++++++++++++++++++--------------------------
+ 1 file changed, 48 insertions(+), 46 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 6394e94023..823ca32883 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -246,24 +246,15 @@ static void write_elf32_load(DumpState *s, MemoryMapping *memory_mapping,
+     }
+ }
+ 
+-static void write_elf64_note(DumpState *s, Error **errp)
++static void write_elf64_phdr_note(DumpState *s, Elf64_Phdr *phdr)
+ {
+-    Elf64_Phdr phdr;
+-    int ret;
+-
+-    memset(&phdr, 0, sizeof(Elf64_Phdr));
+-    phdr.p_type = cpu_to_dump32(s, PT_NOTE);
+-    phdr.p_offset = cpu_to_dump64(s, s->note_offset);
+-    phdr.p_paddr = 0;
+-    phdr.p_filesz = cpu_to_dump64(s, s->note_size);
+-    phdr.p_memsz = cpu_to_dump64(s, s->note_size);
+-    phdr.p_vaddr = 0;
+-
+-    ret = fd_write_vmcore(&phdr, sizeof(Elf64_Phdr), s);
+-    if (ret < 0) {
+-        error_setg_errno(errp, -ret,
+-                         "dump: failed to write program header table");
+-    }
++    memset(phdr, 0, sizeof(*phdr));
++    phdr->p_type = cpu_to_dump32(s, PT_NOTE);
++    phdr->p_offset = cpu_to_dump64(s, s->note_offset);
++    phdr->p_paddr = 0;
++    phdr->p_filesz = cpu_to_dump64(s, s->note_size);
++    phdr->p_memsz = cpu_to_dump64(s, s->note_size);
++    phdr->p_vaddr = 0;
+ }
+ 
+ static inline int cpu_index(CPUState *cpu)
+@@ -311,24 +302,15 @@ static void write_elf64_notes(WriteCoreDumpFunction f, DumpState *s,
+     write_guest_note(f, s, errp);
+ }
+ 
+-static void write_elf32_note(DumpState *s, Error **errp)
++static void write_elf32_phdr_note(DumpState *s, Elf32_Phdr *phdr)
+ {
+-    Elf32_Phdr phdr;
+-    int ret;
+-
+-    memset(&phdr, 0, sizeof(Elf32_Phdr));
+-    phdr.p_type = cpu_to_dump32(s, PT_NOTE);
+-    phdr.p_offset = cpu_to_dump32(s, s->note_offset);
+-    phdr.p_paddr = 0;
+-    phdr.p_filesz = cpu_to_dump32(s, s->note_size);
+-    phdr.p_memsz = cpu_to_dump32(s, s->note_size);
+-    phdr.p_vaddr = 0;
+-
+-    ret = fd_write_vmcore(&phdr, sizeof(Elf32_Phdr), s);
+-    if (ret < 0) {
+-        error_setg_errno(errp, -ret,
+-                         "dump: failed to write program header table");
+-    }
++    memset(phdr, 0, sizeof(*phdr));
++    phdr->p_type = cpu_to_dump32(s, PT_NOTE);
++    phdr->p_offset = cpu_to_dump32(s, s->note_offset);
++    phdr->p_paddr = 0;
++    phdr->p_filesz = cpu_to_dump32(s, s->note_size);
++    phdr->p_memsz = cpu_to_dump32(s, s->note_size);
++    phdr->p_vaddr = 0;
+ }
+ 
+ static void write_elf32_notes(WriteCoreDumpFunction f, DumpState *s,
+@@ -358,6 +340,32 @@ static void write_elf32_notes(WriteCoreDumpFunction f, DumpState *s,
+     write_guest_note(f, s, errp);
+ }
+ 
++static void write_elf_phdr_note(DumpState *s, Error **errp)
++{
++    ERRP_GUARD();
++    Elf32_Phdr phdr32;
++    Elf64_Phdr phdr64;
++    void *phdr;
++    size_t size;
++    int ret;
++
++    if (dump_is_64bit(s)) {
++        write_elf64_phdr_note(s, &phdr64);
++        size = sizeof(phdr64);
++        phdr = &phdr64;
++    } else {
++        write_elf32_phdr_note(s, &phdr32);
++        size = sizeof(phdr32);
++        phdr = &phdr32;
++    }
++
++    ret = fd_write_vmcore(phdr, size, s);
++    if (ret < 0) {
++        error_setg_errno(errp, -ret,
++                         "dump: failed to write program header table");
++    }
++}
++
+ static void write_elf_section(DumpState *s, int type, Error **errp)
+ {
+     Elf32_Shdr shdr32;
+@@ -551,13 +559,13 @@ static void dump_begin(DumpState *s, Error **errp)
+         return;
+     }
+ 
+-    if (dump_is_64bit(s)) {
+-        /* write PT_NOTE to vmcore */
+-        write_elf64_note(s, errp);
+-        if (*errp) {
+-            return;
+-        }
++    /* write PT_NOTE to vmcore */
++    write_elf_phdr_note(s, errp);
++    if (*errp) {
++        return;
++    }
+ 
++    if (dump_is_64bit(s)) {
+         /* write all PT_LOAD to vmcore */
+         write_elf_loads(s, errp);
+         if (*errp) {
+@@ -578,12 +586,6 @@ static void dump_begin(DumpState *s, Error **errp)
+             return;
+         }
+     } else {
+-        /* write PT_NOTE to vmcore */
+-        write_elf32_note(s, errp);
+-        if (*errp) {
+-            return;
+-        }
+-
+         /* write all PT_LOAD to vmcore */
+         write_elf_loads(s, errp);
+         if (*errp) {
+-- 
+2.37.3
+

SOURCES/kvm-dump-Introduce-dump_is_64bit-helper-function.patch

@@ -0,0 +1,118 @@
+From c851676d202b5b76962529f3b6d433936becbd8a Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Wed, 30 Mar 2022 12:36:00 +0000
+Subject: [PATCH 18/42] dump: Introduce dump_is_64bit() helper function
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [18/41] a0fd2d1985c61b8e50d4a7ca26bc0ee6fcaa6196
+
+Checking d_class in dump_info leads to lengthy conditionals so let's
+shorten things a bit by introducing a helper function.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220330123603.107120-7-frankja@linux.ibm.com>
+(cherry picked from commit 05bbaa5040ccb3419e8b93af8040485430e2db42)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 25 +++++++++++++++----------
+ 1 file changed, 15 insertions(+), 10 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 85a402b38c..6394e94023 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -55,6 +55,11 @@ static Error *dump_migration_blocker;
+       DIV_ROUND_UP((name_size), 4) +                    \
+       DIV_ROUND_UP((desc_size), 4)) * 4)
+ 
++static inline bool dump_is_64bit(DumpState *s)
++{
++    return s->dump_info.d_class == ELFCLASS64;
++}
++
+ uint16_t cpu_to_dump16(DumpState *s, uint16_t val)
+ {
+     if (s->dump_info.d_endian == ELFDATA2LSB) {
+@@ -489,7 +494,7 @@ static void write_elf_loads(DumpState *s, Error **errp)
+         get_offset_range(memory_mapping->phys_addr,
+                          memory_mapping->length,
+                          s, &offset, &filesz);
+-        if (s->dump_info.d_class == ELFCLASS64) {
++        if (dump_is_64bit(s)) {
+             write_elf64_load(s, memory_mapping, phdr_index++, offset,
+                              filesz, errp);
+         } else {
+@@ -537,7 +542,7 @@ static void dump_begin(DumpState *s, Error **errp)
+      */
+ 
+     /* write elf header to vmcore */
+-    if (s->dump_info.d_class == ELFCLASS64) {
++    if (dump_is_64bit(s)) {
+         write_elf64_header(s, errp);
+     } else {
+         write_elf32_header(s, errp);
+@@ -546,7 +551,7 @@ static void dump_begin(DumpState *s, Error **errp)
+         return;
+     }
+ 
+-    if (s->dump_info.d_class == ELFCLASS64) {
++    if (dump_is_64bit(s)) {
+         /* write PT_NOTE to vmcore */
+         write_elf64_note(s, errp);
+         if (*errp) {
+@@ -757,7 +762,7 @@ static void get_note_sizes(DumpState *s, const void *note,
+     uint64_t name_sz;
+     uint64_t desc_sz;
+ 
+-    if (s->dump_info.d_class == ELFCLASS64) {
++    if (dump_is_64bit(s)) {
+         const Elf64_Nhdr *hdr = note;
+         note_head_sz = sizeof(Elf64_Nhdr);
+         name_sz = tswap64(hdr->n_namesz);
+@@ -1017,10 +1022,10 @@ out:
+ 
+ static void write_dump_header(DumpState *s, Error **errp)
+ {
+-    if (s->dump_info.d_class == ELFCLASS32) {
+-        create_header32(s, errp);
+-    } else {
++    if (dump_is_64bit(s)) {
+         create_header64(s, errp);
++    } else {
++        create_header32(s, errp);
+     }
+ }
+ 
+@@ -1715,8 +1720,8 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+         uint32_t size;
+         uint16_t format;
+ 
+-        note_head_size = s->dump_info.d_class == ELFCLASS32 ?
+-            sizeof(Elf32_Nhdr) : sizeof(Elf64_Nhdr);
++        note_head_size = dump_is_64bit(s) ?
++            sizeof(Elf64_Nhdr) : sizeof(Elf32_Nhdr);
+ 
+         format = le16_to_cpu(vmci->vmcoreinfo.guest_format);
+         size = le32_to_cpu(vmci->vmcoreinfo.size);
+@@ -1819,7 +1824,7 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+         }
+     }
+ 
+-    if (s->dump_info.d_class == ELFCLASS64) {
++    if (dump_is_64bit(s)) {
+         s->phdr_offset = sizeof(Elf64_Ehdr);
+         s->shdr_offset = s->phdr_offset + sizeof(Elf64_Phdr) * s->phdr_num;
+         s->note_offset = s->shdr_offset + sizeof(Elf64_Shdr) * s->shdr_num;
+-- 
+2.37.3
+

SOURCES/kvm-dump-Introduce-shdr_num-to-decrease-complexity.patch

@@ -0,0 +1,136 @@
+From 255722667a4fa4d522bb0b7e0825cbbe635abb8d Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Wed, 30 Mar 2022 12:35:57 +0000
+Subject: [PATCH 15/42] dump: Introduce shdr_num to decrease complexity
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [15/41] b0215ea5d381ef7f6abfe3f3bafea51ce933da56
+
+Let's move from a boolean to a int variable which will later enable us
+to store the number of sections that are in the dump file.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220330123603.107120-4-frankja@linux.ibm.com>
+(cherry picked from commit 862a395858e5a302ed5921487777acdc95a3a31b)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c           | 24 ++++++++++++------------
+ include/sysemu/dump.h |  2 +-
+ 2 files changed, 13 insertions(+), 13 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 7236b167cc..972e28b089 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -145,12 +145,12 @@ static void write_elf64_header(DumpState *s, Error **errp)
+     elf_header.e_phoff = cpu_to_dump64(s, sizeof(Elf64_Ehdr));
+     elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf64_Phdr));
+     elf_header.e_phnum = cpu_to_dump16(s, phnum);
+-    if (s->have_section) {
++    if (s->shdr_num) {
+         uint64_t shoff = sizeof(Elf64_Ehdr) + sizeof(Elf64_Phdr) * s->phdr_num;
+ 
+         elf_header.e_shoff = cpu_to_dump64(s, shoff);
+         elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf64_Shdr));
+-        elf_header.e_shnum = cpu_to_dump16(s, 1);
++        elf_header.e_shnum = cpu_to_dump16(s, s->shdr_num);
+     }
+ 
+     ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
+@@ -182,12 +182,12 @@ static void write_elf32_header(DumpState *s, Error **errp)
+     elf_header.e_phoff = cpu_to_dump32(s, sizeof(Elf32_Ehdr));
+     elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf32_Phdr));
+     elf_header.e_phnum = cpu_to_dump16(s, phnum);
+-    if (s->have_section) {
++    if (s->shdr_num) {
+         uint32_t shoff = sizeof(Elf32_Ehdr) + sizeof(Elf32_Phdr) * s->phdr_num;
+ 
+         elf_header.e_shoff = cpu_to_dump32(s, shoff);
+         elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf32_Shdr));
+-        elf_header.e_shnum = cpu_to_dump16(s, 1);
++        elf_header.e_shnum = cpu_to_dump16(s, s->shdr_num);
+     }
+ 
+     ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
+@@ -566,7 +566,7 @@ static void dump_begin(DumpState *s, Error **errp)
+         }
+ 
+         /* write section to vmcore */
+-        if (s->have_section) {
++        if (s->shdr_num) {
+             write_elf_section(s, 1, errp);
+             if (*errp) {
+                 return;
+@@ -592,7 +592,7 @@ static void dump_begin(DumpState *s, Error **errp)
+         }
+ 
+         /* write section to vmcore */
+-        if (s->have_section) {
++        if (s->shdr_num) {
+             write_elf_section(s, 0, errp);
+             if (*errp) {
+                 return;
+@@ -1811,11 +1811,11 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+      */
+     s->phdr_num = 1; /* PT_NOTE */
+     if (s->list.num < UINT16_MAX - 2) {
++        s->shdr_num = 0;
+         s->phdr_num += s->list.num;
+-        s->have_section = false;
+     } else {
+         /* sh_info of section 0 holds the real number of phdrs */
+-        s->have_section = true;
++        s->shdr_num = 1;
+ 
+         /* the type of shdr->sh_info is uint32_t, so we should avoid overflow */
+         if (s->list.num <= UINT32_MAX - 1) {
+@@ -1826,19 +1826,19 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+     }
+ 
+     if (s->dump_info.d_class == ELFCLASS64) {
+-        if (s->have_section) {
++        if (s->shdr_num) {
+             s->memory_offset = sizeof(Elf64_Ehdr) +
+                                sizeof(Elf64_Phdr) * s->phdr_num +
+-                               sizeof(Elf64_Shdr) + s->note_size;
++                               sizeof(Elf64_Shdr) * s->shdr_num + s->note_size;
+         } else {
+             s->memory_offset = sizeof(Elf64_Ehdr) +
+                                sizeof(Elf64_Phdr) * s->phdr_num + s->note_size;
+         }
+     } else {
+-        if (s->have_section) {
++        if (s->shdr_num) {
+             s->memory_offset = sizeof(Elf32_Ehdr) +
+                                sizeof(Elf32_Phdr) * s->phdr_num +
+-                               sizeof(Elf32_Shdr) + s->note_size;
++                               sizeof(Elf32_Shdr) * s->shdr_num + s->note_size;
+         } else {
+             s->memory_offset = sizeof(Elf32_Ehdr) +
+                                sizeof(Elf32_Phdr) * s->phdr_num + s->note_size;
+diff --git a/include/sysemu/dump.h b/include/sysemu/dump.h
+index b463fc9c02..19458bffbd 100644
+--- a/include/sysemu/dump.h
++++ b/include/sysemu/dump.h
+@@ -155,7 +155,7 @@ typedef struct DumpState {
+     ArchDumpInfo dump_info;
+     MemoryMappingList list;
+     uint32_t phdr_num;
+-    bool have_section;
++    uint32_t shdr_num;
+     bool resume;
+     bool detached;
+     ssize_t note_size;
+-- 
+2.37.3
+

SOURCES/kvm-dump-Refactor-dump_iterate-and-introduce-dump_filter.patch

@@ -0,0 +1,142 @@
+From a18ba2fbaf132724e81be92da42b36d8f365e66c Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Thu, 11 Aug 2022 12:10:56 +0000
+Subject: [PATCH 24/42] dump: Refactor dump_iterate and introduce
+ dump_filter_memblock_*()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [24/41] 74ef470f24d9d98093c4d63730a99474587033fd
+
+The iteration over the memblocks in dump_iterate() is hard to
+understand so it's about time to clean it up. Instead of manually
+grabbing the next memblock we can use QTAILQ_FOREACH to iterate over
+all memblocks.
+
+Additionally we move the calculation of the offset and length out by
+introducing and using the dump_filter_memblock_*() functions. These
+functions will later be used to cleanup other parts of dump.c.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220811121111.9878-4-frankja@linux.ibm.com>
+(cherry picked from commit 1e8113032f5b1efc5da66382470ce4809c76f8f2)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 74 ++++++++++++++++++++++++++++++-----------------------
+ 1 file changed, 42 insertions(+), 32 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index fa787f379f..d981e843dd 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -592,31 +592,43 @@ static void dump_begin(DumpState *s, Error **errp)
+     write_elf_notes(s, errp);
+ }
+ 
+-static int get_next_block(DumpState *s, GuestPhysBlock *block)
++static int64_t dump_filtered_memblock_size(GuestPhysBlock *block,
++                                           int64_t filter_area_start,
++                                           int64_t filter_area_length)
+ {
+-    while (1) {
+-        block = QTAILQ_NEXT(block, next);
+-        if (!block) {
+-            /* no more block */
+-            return 1;
+-        }
++    int64_t size, left, right;
+ 
+-        s->start = 0;
+-        s->next_block = block;
+-        if (s->has_filter) {
+-            if (block->target_start >= s->begin + s->length ||
+-                block->target_end <= s->begin) {
+-                /* This block is out of the range */
+-                continue;
+-            }
++    /* No filter, return full size */
++    if (!filter_area_length) {
++        return block->target_end - block->target_start;
++    }
+ 
+-            if (s->begin > block->target_start) {
+-                s->start = s->begin - block->target_start;
+-            }
++    /* calculate the overlapped region. */
++    left = MAX(filter_area_start, block->target_start);
++    right = MIN(filter_area_start + filter_area_length, block->target_end);
++    size = right - left;
++    size = size > 0 ? size : 0;
++
++    return size;
++}
++
++static int64_t dump_filtered_memblock_start(GuestPhysBlock *block,
++                                            int64_t filter_area_start,
++                                            int64_t filter_area_length)
++{
++    if (filter_area_length) {
++        /* return -1 if the block is not within filter area */
++        if (block->target_start >= filter_area_start + filter_area_length ||
++            block->target_end <= filter_area_start) {
++            return -1;
+         }
+ 
+-        return 0;
++        if (filter_area_start > block->target_start) {
++            return filter_area_start - block->target_start;
++        }
+     }
++
++    return 0;
+ }
+ 
+ /* write all memory to vmcore */
+@@ -624,24 +636,22 @@ static void dump_iterate(DumpState *s, Error **errp)
+ {
+     ERRP_GUARD();
+     GuestPhysBlock *block;
+-    int64_t size;
+-
+-    do {
+-        block = s->next_block;
++    int64_t memblock_size, memblock_start;
+ 
+-        size = block->target_end - block->target_start;
+-        if (s->has_filter) {
+-            size -= s->start;
+-            if (s->begin + s->length < block->target_end) {
+-                size -= block->target_end - (s->begin + s->length);
+-            }
++    QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
++        memblock_start = dump_filtered_memblock_start(block, s->begin, s->length);
++        if (memblock_start == -1) {
++            continue;
+         }
+-        write_memory(s, block, s->start, size, errp);
++
++        memblock_size = dump_filtered_memblock_size(block, s->begin, s->length);
++
++        /* Write the memory to file */
++        write_memory(s, block, memblock_start, memblock_size, errp);
+         if (*errp) {
+             return;
+         }
+-
+-    } while (!get_next_block(s, block));
++    }
+ }
+ 
+ static void create_vmcore(DumpState *s, Error **errp)
+-- 
+2.37.3
+

SOURCES/kvm-dump-Reintroduce-memory_offset-and-section_offset.patch

@@ -0,0 +1,45 @@
+From 6932fe3afbec443bbf6acff5b707536254e1bc37 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Mon, 17 Oct 2022 08:38:16 +0000
+Subject: [PATCH 35/42] dump: Reintroduce memory_offset and section_offset
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [35/41] e60c0d066aeeedb42e724712bc3aa7b7591c6c79
+
+section_offset will later be used to store the offset to the section
+data which will be stored last. For now memory_offset is only needed
+to make section_offset look nicer.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20221017083822.43118-5-frankja@linux.ibm.com>
+(cherry picked from commit 13fd417ddc81a1685c6a8f4e1c80bbfe7150f164)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 2 ++
+ 1 file changed, 2 insertions(+)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index d17537d4e9..7a42401790 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -1885,6 +1885,8 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+         s->phdr_offset = s->shdr_offset + sizeof(Elf32_Shdr) * s->shdr_num;
+         s->note_offset = s->phdr_offset + sizeof(Elf32_Phdr) * s->phdr_num;
+     }
++    s->memory_offset = s->note_offset + s->note_size;
++    s->section_offset = s->memory_offset + s->total_size;
+ 
+     return;
+ 
+-- 
+2.37.3
+

SOURCES/kvm-dump-Remove-the-section-if-when-calculating-the-memo.patch

@@ -0,0 +1,70 @@
+From a8eeab6936a2bd27b33b63aed7e2ef96034f7772 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Wed, 30 Mar 2022 12:35:58 +0000
+Subject: [PATCH 16/42] dump: Remove the section if when calculating the memory
+ offset
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [16/41] ff214d2c23b9cb16fd49d22d976829267df43133
+
+When s->shdr_num is 0 we'll add 0 bytes of section headers which is
+equivalent to not adding section headers but with the multiplication
+we can remove a if/else.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220330123603.107120-5-frankja@linux.ibm.com>
+(cherry picked from commit 344107e07bd81546474a54ab83800158ca953059)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 24 ++++++++----------------
+ 1 file changed, 8 insertions(+), 16 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 972e28b089..5cc2322325 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -1826,23 +1826,15 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+     }
+ 
+     if (s->dump_info.d_class == ELFCLASS64) {
+-        if (s->shdr_num) {
+-            s->memory_offset = sizeof(Elf64_Ehdr) +
+-                               sizeof(Elf64_Phdr) * s->phdr_num +
+-                               sizeof(Elf64_Shdr) * s->shdr_num + s->note_size;
+-        } else {
+-            s->memory_offset = sizeof(Elf64_Ehdr) +
+-                               sizeof(Elf64_Phdr) * s->phdr_num + s->note_size;
+-        }
++        s->memory_offset = sizeof(Elf64_Ehdr) +
++                           sizeof(Elf64_Phdr) * s->phdr_num +
++                           sizeof(Elf64_Shdr) * s->shdr_num +
++                           s->note_size;
+     } else {
+-        if (s->shdr_num) {
+-            s->memory_offset = sizeof(Elf32_Ehdr) +
+-                               sizeof(Elf32_Phdr) * s->phdr_num +
+-                               sizeof(Elf32_Shdr) * s->shdr_num + s->note_size;
+-        } else {
+-            s->memory_offset = sizeof(Elf32_Ehdr) +
+-                               sizeof(Elf32_Phdr) * s->phdr_num + s->note_size;
+-        }
++        s->memory_offset = sizeof(Elf32_Ehdr) +
++                           sizeof(Elf32_Phdr) * s->phdr_num +
++                           sizeof(Elf32_Shdr) * s->shdr_num +
++                           s->note_size;
+     }
+ 
+     return;
+-- 
+2.37.3
+

SOURCES/kvm-dump-Remove-the-sh_info-variable.patch

@@ -0,0 +1,176 @@
+From eb763bec53d6b9aea7a6b60b0cf8c5d8b5f1b35c Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Thu, 7 Apr 2022 09:48:24 +0000
+Subject: [PATCH 14/42] dump: Remove the sh_info variable
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [14/41] 24af12b78c8f5a02cf85df2f6b1d64249f9499c9
+
+There's no need to have phdr_num and sh_info at the same time. We can
+make phdr_num 32 bit and set PN_XNUM when we write the header if
+phdr_num >= PN_XNUM.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220407094824.5074-1-frankja@linux.ibm.com>
+(cherry picked from commit 046bc4160bc780eaacc2d702a2589f1a7a01188d)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c           | 44 +++++++++++++++++++++++--------------------
+ include/sysemu/dump.h |  3 +--
+ 2 files changed, 25 insertions(+), 22 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 9876123f2e..7236b167cc 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -124,6 +124,12 @@ static int fd_write_vmcore(const void *buf, size_t size, void *opaque)
+ 
+ static void write_elf64_header(DumpState *s, Error **errp)
+ {
++    /*
++     * phnum in the elf header is 16 bit, if we have more segments we
++     * set phnum to PN_XNUM and write the real number of segments to a
++     * special section.
++     */
++    uint16_t phnum = MIN(s->phdr_num, PN_XNUM);
+     Elf64_Ehdr elf_header;
+     int ret;
+ 
+@@ -138,9 +144,9 @@ static void write_elf64_header(DumpState *s, Error **errp)
+     elf_header.e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
+     elf_header.e_phoff = cpu_to_dump64(s, sizeof(Elf64_Ehdr));
+     elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf64_Phdr));
+-    elf_header.e_phnum = cpu_to_dump16(s, s->phdr_num);
++    elf_header.e_phnum = cpu_to_dump16(s, phnum);
+     if (s->have_section) {
+-        uint64_t shoff = sizeof(Elf64_Ehdr) + sizeof(Elf64_Phdr) * s->sh_info;
++        uint64_t shoff = sizeof(Elf64_Ehdr) + sizeof(Elf64_Phdr) * s->phdr_num;
+ 
+         elf_header.e_shoff = cpu_to_dump64(s, shoff);
+         elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf64_Shdr));
+@@ -155,6 +161,12 @@ static void write_elf64_header(DumpState *s, Error **errp)
+ 
+ static void write_elf32_header(DumpState *s, Error **errp)
+ {
++    /*
++     * phnum in the elf header is 16 bit, if we have more segments we
++     * set phnum to PN_XNUM and write the real number of segments to a
++     * special section.
++     */
++    uint16_t phnum = MIN(s->phdr_num, PN_XNUM);
+     Elf32_Ehdr elf_header;
+     int ret;
+ 
+@@ -169,9 +181,9 @@ static void write_elf32_header(DumpState *s, Error **errp)
+     elf_header.e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
+     elf_header.e_phoff = cpu_to_dump32(s, sizeof(Elf32_Ehdr));
+     elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf32_Phdr));
+-    elf_header.e_phnum = cpu_to_dump16(s, s->phdr_num);
++    elf_header.e_phnum = cpu_to_dump16(s, phnum);
+     if (s->have_section) {
+-        uint32_t shoff = sizeof(Elf32_Ehdr) + sizeof(Elf32_Phdr) * s->sh_info;
++        uint32_t shoff = sizeof(Elf32_Ehdr) + sizeof(Elf32_Phdr) * s->phdr_num;
+ 
+         elf_header.e_shoff = cpu_to_dump32(s, shoff);
+         elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf32_Shdr));
+@@ -358,12 +370,12 @@ static void write_elf_section(DumpState *s, int type, Error **errp)
+     if (type == 0) {
+         shdr_size = sizeof(Elf32_Shdr);
+         memset(&shdr32, 0, shdr_size);
+-        shdr32.sh_info = cpu_to_dump32(s, s->sh_info);
++        shdr32.sh_info = cpu_to_dump32(s, s->phdr_num);
+         shdr = &shdr32;
+     } else {
+         shdr_size = sizeof(Elf64_Shdr);
+         memset(&shdr64, 0, shdr_size);
+-        shdr64.sh_info = cpu_to_dump32(s, s->sh_info);
++        shdr64.sh_info = cpu_to_dump32(s, s->phdr_num);
+         shdr = &shdr64;
+     }
+ 
+@@ -478,13 +490,6 @@ static void write_elf_loads(DumpState *s, Error **errp)
+     hwaddr offset, filesz;
+     MemoryMapping *memory_mapping;
+     uint32_t phdr_index = 1;
+-    uint32_t max_index;
+-
+-    if (s->have_section) {
+-        max_index = s->sh_info;
+-    } else {
+-        max_index = s->phdr_num;
+-    }
+ 
+     QTAILQ_FOREACH(memory_mapping, &s->list.head, next) {
+         get_offset_range(memory_mapping->phys_addr,
+@@ -502,7 +507,7 @@ static void write_elf_loads(DumpState *s, Error **errp)
+             return;
+         }
+ 
+-        if (phdr_index >= max_index) {
++        if (phdr_index >= s->phdr_num) {
+             break;
+         }
+     }
+@@ -1809,22 +1814,21 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+         s->phdr_num += s->list.num;
+         s->have_section = false;
+     } else {
++        /* sh_info of section 0 holds the real number of phdrs */
+         s->have_section = true;
+-        s->phdr_num = PN_XNUM;
+-        s->sh_info = 1; /* PT_NOTE */
+ 
+         /* the type of shdr->sh_info is uint32_t, so we should avoid overflow */
+         if (s->list.num <= UINT32_MAX - 1) {
+-            s->sh_info += s->list.num;
++            s->phdr_num += s->list.num;
+         } else {
+-            s->sh_info = UINT32_MAX;
++            s->phdr_num = UINT32_MAX;
+         }
+     }
+ 
+     if (s->dump_info.d_class == ELFCLASS64) {
+         if (s->have_section) {
+             s->memory_offset = sizeof(Elf64_Ehdr) +
+-                               sizeof(Elf64_Phdr) * s->sh_info +
++                               sizeof(Elf64_Phdr) * s->phdr_num +
+                                sizeof(Elf64_Shdr) + s->note_size;
+         } else {
+             s->memory_offset = sizeof(Elf64_Ehdr) +
+@@ -1833,7 +1837,7 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+     } else {
+         if (s->have_section) {
+             s->memory_offset = sizeof(Elf32_Ehdr) +
+-                               sizeof(Elf32_Phdr) * s->sh_info +
++                               sizeof(Elf32_Phdr) * s->phdr_num +
+                                sizeof(Elf32_Shdr) + s->note_size;
+         } else {
+             s->memory_offset = sizeof(Elf32_Ehdr) +
+diff --git a/include/sysemu/dump.h b/include/sysemu/dump.h
+index 250143cb5a..b463fc9c02 100644
+--- a/include/sysemu/dump.h
++++ b/include/sysemu/dump.h
+@@ -154,8 +154,7 @@ typedef struct DumpState {
+     GuestPhysBlockList guest_phys_blocks;
+     ArchDumpInfo dump_info;
+     MemoryMappingList list;
+-    uint16_t phdr_num;
+-    uint32_t sh_info;
++    uint32_t phdr_num;
+     bool have_section;
+     bool resume;
+     bool detached;
+-- 
+2.37.3
+

SOURCES/kvm-dump-Rename-write_elf-_phdr_note-to-prepare_elf-_phd.patch

@@ -0,0 +1,69 @@
+From 18fef7f02801d51207d67b8f8ec5f0d828889c78 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Thu, 11 Aug 2022 12:11:01 +0000
+Subject: [PATCH 29/42] dump: Rename write_elf*_phdr_note to
+ prepare_elf*_phdr_note
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [29/41] 876cea6f6e51be8df2763f56d0daef99d11fdd49
+
+The functions in question do not actually write to the file descriptor
+they set up a buffer which is later written to the fd.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220811121111.9878-9-frankja@linux.ibm.com>
+(cherry picked from commit 2341a94d3a0a8a93a5a977e642da1807b8edaab8)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 8d5226f861..c2c1341ad7 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -261,7 +261,7 @@ static void write_elf32_load(DumpState *s, MemoryMapping *memory_mapping,
+     }
+ }
+ 
+-static void write_elf64_phdr_note(DumpState *s, Elf64_Phdr *phdr)
++static void prepare_elf64_phdr_note(DumpState *s, Elf64_Phdr *phdr)
+ {
+     memset(phdr, 0, sizeof(*phdr));
+     phdr->p_type = cpu_to_dump32(s, PT_NOTE);
+@@ -317,7 +317,7 @@ static void write_elf64_notes(WriteCoreDumpFunction f, DumpState *s,
+     write_guest_note(f, s, errp);
+ }
+ 
+-static void write_elf32_phdr_note(DumpState *s, Elf32_Phdr *phdr)
++static void prepare_elf32_phdr_note(DumpState *s, Elf32_Phdr *phdr)
+ {
+     memset(phdr, 0, sizeof(*phdr));
+     phdr->p_type = cpu_to_dump32(s, PT_NOTE);
+@@ -365,11 +365,11 @@ static void write_elf_phdr_note(DumpState *s, Error **errp)
+     int ret;
+ 
+     if (dump_is_64bit(s)) {
+-        write_elf64_phdr_note(s, &phdr64);
++        prepare_elf64_phdr_note(s, &phdr64);
+         size = sizeof(phdr64);
+         phdr = &phdr64;
+     } else {
+-        write_elf32_phdr_note(s, &phdr32);
++        prepare_elf32_phdr_note(s, &phdr32);
+         size = sizeof(phdr32);
+         phdr = &phdr32;
+     }
+-- 
+2.37.3
+

SOURCES/kvm-dump-Rename-write_elf_loads-to-write_elf_phdr_loads.patch

@@ -0,0 +1,57 @@
+From 04d4947a22fe3192384ff486d0a979d799ded98e Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Thu, 11 Aug 2022 12:10:55 +0000
+Subject: [PATCH 23/42] dump: Rename write_elf_loads to write_elf_phdr_loads
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [23/41] 18e3ef70b97c525b7c43cf12143204bdb1060e4f
+
+Let's make it a bit clearer that we write the program headers of the
+PT_LOAD type.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Reviewed-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
+Reviewed-by: Steffen Eiden <seiden@ibm.linux.com>
+Message-Id: <20220811121111.9878-3-frankja@linux.ibm.com>
+(cherry picked from commit afae6056ea79e2d89fd90867de3a01732eae724f)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 6 +++---
+ 1 file changed, 3 insertions(+), 3 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index a451abc590..fa787f379f 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -491,7 +491,7 @@ static void get_offset_range(hwaddr phys_addr,
+     }
+ }
+ 
+-static void write_elf_loads(DumpState *s, Error **errp)
++static void write_elf_phdr_loads(DumpState *s, Error **errp)
+ {
+     ERRP_GUARD();
+     hwaddr offset, filesz;
+@@ -574,8 +574,8 @@ static void dump_begin(DumpState *s, Error **errp)
+         return;
+     }
+ 
+-    /* write all PT_LOAD to vmcore */
+-    write_elf_loads(s, errp);
++    /* write all PT_LOADs to vmcore */
++    write_elf_phdr_loads(s, errp);
+     if (*errp) {
+         return;
+     }
+-- 
+2.37.3
+

SOURCES/kvm-dump-Reorder-struct-DumpState.patch

@@ -0,0 +1,68 @@
+From 7e8d6290099b33f88621b45e62652a97704c9573 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Mon, 17 Oct 2022 08:38:15 +0000
+Subject: [PATCH 34/42] dump: Reorder struct DumpState
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [34/41] 8d44e5e8c86ea5b33644eba141046cd657d0071e
+
+Let's move ELF related members into one block and guest memory related
+ones into another to improve readability.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20221017083822.43118-4-frankja@linux.ibm.com>
+(cherry picked from commit 8384b73c46fd474847d7e74d121318e344edc3c4)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ include/sysemu/dump.h | 16 +++++++++-------
+ 1 file changed, 9 insertions(+), 7 deletions(-)
+
+diff --git a/include/sysemu/dump.h b/include/sysemu/dump.h
+index 9995f65dc8..9ed811b313 100644
+--- a/include/sysemu/dump.h
++++ b/include/sysemu/dump.h
+@@ -154,15 +154,8 @@ typedef struct DumpState {
+     GuestPhysBlockList guest_phys_blocks;
+     ArchDumpInfo dump_info;
+     MemoryMappingList list;
+-    uint32_t phdr_num;
+-    uint32_t shdr_num;
+     bool resume;
+     bool detached;
+-    ssize_t note_size;
+-    hwaddr shdr_offset;
+-    hwaddr phdr_offset;
+-    hwaddr section_offset;
+-    hwaddr note_offset;
+     hwaddr memory_offset;
+     int fd;
+ 
+@@ -177,6 +170,15 @@ typedef struct DumpState {
+     int64_t filter_area_begin;  /* Start address of partial guest memory area */
+     int64_t filter_area_length; /* Length of partial guest memory area */
+ 
++    /* Elf dump related data */
++    uint32_t phdr_num;
++    uint32_t shdr_num;
++    ssize_t note_size;
++    hwaddr shdr_offset;
++    hwaddr phdr_offset;
++    hwaddr section_offset;
++    hwaddr note_offset;
++
+     void *elf_section_hdrs;     /* Pointer to section header buffer */
+ 
+     uint8_t *note_buf;          /* buffer for notes */
+-- 
+2.37.3
+

SOURCES/kvm-dump-Replace-opaque-DumpState-pointer-with-a-typed-o.patch

@@ -0,0 +1,467 @@
+From 8f674e0e12e4b88fc035948612a0b0949e0ad892 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Thu, 11 Aug 2022 12:10:54 +0000
+Subject: [PATCH 22/42] dump: Replace opaque DumpState pointer with a typed one
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [22/41] 5f071d7ef441ae6f5da70eb56018c4657deee3d7
+
+It's always better to convey the type of a pointer if at all
+possible. So let's add the DumpState typedef to typedefs.h and move
+the dump note functions from the opaque pointers to DumpState
+pointers.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+CC: Peter Maydell <peter.maydell@linaro.org>
+CC: Cédric Le Goater <clg@kaod.org>
+CC: Daniel Henrique Barboza <danielhb413@gmail.com>
+CC: David Gibson <david@gibson.dropbear.id.au>
+CC: Greg Kurz <groug@kaod.org>
+CC: Palmer Dabbelt <palmer@dabbelt.com>
+CC: Alistair Francis <alistair.francis@wdc.com>
+CC: Bin Meng <bin.meng@windriver.com>
+CC: Cornelia Huck <cohuck@redhat.com>
+CC: Thomas Huth <thuth@redhat.com>
+CC: Richard Henderson <richard.henderson@linaro.org>
+CC: David Hildenbrand <david@redhat.com>
+Acked-by: Daniel Henrique Barboza <danielhb413@gmail.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220811121111.9878-2-frankja@linux.ibm.com>
+(cherry picked from commit 1af0006ab959864dfa2f59e9136c5fb93000b61f)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ include/hw/core/sysemu-cpu-ops.h |  8 ++++----
+ include/qemu/typedefs.h          |  1 +
+ target/arm/arch_dump.c           |  6 ++----
+ target/arm/cpu.h                 |  4 ++--
+ target/i386/arch_dump.c          | 30 +++++++++++++++---------------
+ target/i386/cpu.h                |  8 ++++----
+ target/ppc/arch_dump.c           | 18 +++++++++---------
+ target/ppc/cpu.h                 |  4 ++--
+ target/riscv/arch_dump.c         |  6 ++----
+ target/riscv/cpu.h               |  4 ++--
+ target/s390x/arch_dump.c         | 10 +++++-----
+ target/s390x/s390x-internal.h    |  2 +-
+ 12 files changed, 49 insertions(+), 52 deletions(-)
+
+diff --git a/include/hw/core/sysemu-cpu-ops.h b/include/hw/core/sysemu-cpu-ops.h
+index a9ba39e5f2..ee169b872c 100644
+--- a/include/hw/core/sysemu-cpu-ops.h
++++ b/include/hw/core/sysemu-cpu-ops.h
+@@ -53,25 +53,25 @@ typedef struct SysemuCPUOps {
+      * 32-bit VM coredump.
+      */
+     int (*write_elf32_note)(WriteCoreDumpFunction f, CPUState *cpu,
+-                            int cpuid, void *opaque);
++                            int cpuid, DumpState *s);
+     /**
+      * @write_elf64_note: Callback for writing a CPU-specific ELF note to a
+      * 64-bit VM coredump.
+      */
+     int (*write_elf64_note)(WriteCoreDumpFunction f, CPUState *cpu,
+-                            int cpuid, void *opaque);
++                            int cpuid, DumpState *s);
+     /**
+      * @write_elf32_qemunote: Callback for writing a CPU- and QEMU-specific ELF
+      * note to a 32-bit VM coredump.
+      */
+     int (*write_elf32_qemunote)(WriteCoreDumpFunction f, CPUState *cpu,
+-                                void *opaque);
++                                DumpState *s);
+     /**
+      * @write_elf64_qemunote: Callback for writing a CPU- and QEMU-specific ELF
+      * note to a 64-bit VM coredump.
+      */
+     int (*write_elf64_qemunote)(WriteCoreDumpFunction f, CPUState *cpu,
+-                                void *opaque);
++                                DumpState *s);
+     /**
+      * @virtio_is_big_endian: Callback to return %true if a CPU which supports
+      * runtime configurable endianness is currently big-endian.
+diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h
+index ee60eb3de4..ac9d031be6 100644
+--- a/include/qemu/typedefs.h
++++ b/include/qemu/typedefs.h
+@@ -125,6 +125,7 @@ typedef struct VirtIODevice VirtIODevice;
+ typedef struct Visitor Visitor;
+ typedef struct VMChangeStateEntry VMChangeStateEntry;
+ typedef struct VMStateDescription VMStateDescription;
++typedef struct DumpState DumpState;
+ 
+ /*
+  * Pointer types
+diff --git a/target/arm/arch_dump.c b/target/arm/arch_dump.c
+index 0184845310..3a824e0aa6 100644
+--- a/target/arm/arch_dump.c
++++ b/target/arm/arch_dump.c
+@@ -232,12 +232,11 @@ static int aarch64_write_elf64_sve(WriteCoreDumpFunction f,
+ #endif
+ 
+ int arm_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+-                             int cpuid, void *opaque)
++                             int cpuid, DumpState *s)
+ {
+     struct aarch64_note note;
+     ARMCPU *cpu = ARM_CPU(cs);
+     CPUARMState *env = &cpu->env;
+-    DumpState *s = opaque;
+     uint64_t pstate, sp;
+     int ret, i;
+ 
+@@ -360,12 +359,11 @@ static int arm_write_elf32_vfp(WriteCoreDumpFunction f, CPUARMState *env,
+ }
+ 
+ int arm_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
+-                             int cpuid, void *opaque)
++                             int cpuid, DumpState *s)
+ {
+     struct arm_note note;
+     ARMCPU *cpu = ARM_CPU(cs);
+     CPUARMState *env = &cpu->env;
+-    DumpState *s = opaque;
+     int ret, i;
+     bool fpvalid = cpu_isar_feature(aa32_vfp_simd, cpu);
+ 
+diff --git a/target/arm/cpu.h b/target/arm/cpu.h
+index e33f37b70a..8d2f496ef9 100644
+--- a/target/arm/cpu.h
++++ b/target/arm/cpu.h
+@@ -1065,9 +1065,9 @@ int arm_gen_dynamic_svereg_xml(CPUState *cpu, int base_reg);
+ const char *arm_gdb_get_dynamic_xml(CPUState *cpu, const char *xmlname);
+ 
+ int arm_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+-                             int cpuid, void *opaque);
++                             int cpuid, DumpState *s);
+ int arm_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
+-                             int cpuid, void *opaque);
++                             int cpuid, DumpState *s);
+ 
+ #ifdef TARGET_AARCH64
+ int aarch64_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg);
+diff --git a/target/i386/arch_dump.c b/target/i386/arch_dump.c
+index 004141fc04..c290910a04 100644
+--- a/target/i386/arch_dump.c
++++ b/target/i386/arch_dump.c
+@@ -42,7 +42,7 @@ typedef struct {
+ 
+ static int x86_64_write_elf64_note(WriteCoreDumpFunction f,
+                                    CPUX86State *env, int id,
+-                                   void *opaque)
++                                   DumpState *s)
+ {
+     x86_64_user_regs_struct regs;
+     Elf64_Nhdr *note;
+@@ -94,7 +94,7 @@ static int x86_64_write_elf64_note(WriteCoreDumpFunction f,
+     buf += descsz - sizeof(x86_64_user_regs_struct)-sizeof(target_ulong);
+     memcpy(buf, &regs, sizeof(x86_64_user_regs_struct));
+ 
+-    ret = f(note, note_size, opaque);
++    ret = f(note, note_size, s);
+     g_free(note);
+     if (ret < 0) {
+         return -1;
+@@ -148,7 +148,7 @@ static void x86_fill_elf_prstatus(x86_elf_prstatus *prstatus, CPUX86State *env,
+ }
+ 
+ static int x86_write_elf64_note(WriteCoreDumpFunction f, CPUX86State *env,
+-                                int id, void *opaque)
++                                int id, DumpState *s)
+ {
+     x86_elf_prstatus prstatus;
+     Elf64_Nhdr *note;
+@@ -170,7 +170,7 @@ static int x86_write_elf64_note(WriteCoreDumpFunction f, CPUX86State *env,
+     buf += ROUND_UP(name_size, 4);
+     memcpy(buf, &prstatus, sizeof(prstatus));
+ 
+-    ret = f(note, note_size, opaque);
++    ret = f(note, note_size, s);
+     g_free(note);
+     if (ret < 0) {
+         return -1;
+@@ -180,7 +180,7 @@ static int x86_write_elf64_note(WriteCoreDumpFunction f, CPUX86State *env,
+ }
+ 
+ int x86_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+-                             int cpuid, void *opaque)
++                             int cpuid, DumpState *s)
+ {
+     X86CPU *cpu = X86_CPU(cs);
+     int ret;
+@@ -189,10 +189,10 @@ int x86_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+     bool lma = !!(first_x86_cpu->env.hflags & HF_LMA_MASK);
+ 
+     if (lma) {
+-        ret = x86_64_write_elf64_note(f, &cpu->env, cpuid, opaque);
++        ret = x86_64_write_elf64_note(f, &cpu->env, cpuid, s);
+     } else {
+ #endif
+-        ret = x86_write_elf64_note(f, &cpu->env, cpuid, opaque);
++        ret = x86_write_elf64_note(f, &cpu->env, cpuid, s);
+ #ifdef TARGET_X86_64
+     }
+ #endif
+@@ -201,7 +201,7 @@ int x86_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+ }
+ 
+ int x86_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
+-                             int cpuid, void *opaque)
++                             int cpuid, DumpState *s)
+ {
+     X86CPU *cpu = X86_CPU(cs);
+     x86_elf_prstatus prstatus;
+@@ -224,7 +224,7 @@ int x86_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
+     buf += ROUND_UP(name_size, 4);
+     memcpy(buf, &prstatus, sizeof(prstatus));
+ 
+-    ret = f(note, note_size, opaque);
++    ret = f(note, note_size, s);
+     g_free(note);
+     if (ret < 0) {
+         return -1;
+@@ -329,7 +329,7 @@ static void qemu_get_cpustate(QEMUCPUState *s, CPUX86State *env)
+ 
+ static inline int cpu_write_qemu_note(WriteCoreDumpFunction f,
+                                       CPUX86State *env,
+-                                      void *opaque,
++                                      DumpState *s,
+                                       int type)
+ {
+     QEMUCPUState state;
+@@ -369,7 +369,7 @@ static inline int cpu_write_qemu_note(WriteCoreDumpFunction f,
+     buf += ROUND_UP(name_size, 4);
+     memcpy(buf, &state, sizeof(state));
+ 
+-    ret = f(note, note_size, opaque);
++    ret = f(note, note_size, s);
+     g_free(note);
+     if (ret < 0) {
+         return -1;
+@@ -379,19 +379,19 @@ static inline int cpu_write_qemu_note(WriteCoreDumpFunction f,
+ }
+ 
+ int x86_cpu_write_elf64_qemunote(WriteCoreDumpFunction f, CPUState *cs,
+-                                 void *opaque)
++                                 DumpState *s)
+ {
+     X86CPU *cpu = X86_CPU(cs);
+ 
+-    return cpu_write_qemu_note(f, &cpu->env, opaque, 1);
++    return cpu_write_qemu_note(f, &cpu->env, s, 1);
+ }
+ 
+ int x86_cpu_write_elf32_qemunote(WriteCoreDumpFunction f, CPUState *cs,
+-                                 void *opaque)
++                                 DumpState *s)
+ {
+     X86CPU *cpu = X86_CPU(cs);
+ 
+-    return cpu_write_qemu_note(f, &cpu->env, opaque, 0);
++    return cpu_write_qemu_note(f, &cpu->env, s, 0);
+ }
+ 
+ int cpu_get_dump_info(ArchDumpInfo *info,
+diff --git a/target/i386/cpu.h b/target/i386/cpu.h
+index 006b735fe4..5d2ddd81b9 100644
+--- a/target/i386/cpu.h
++++ b/target/i386/cpu.h
+@@ -1887,13 +1887,13 @@ extern const VMStateDescription vmstate_x86_cpu;
+ int x86_cpu_pending_interrupt(CPUState *cs, int interrupt_request);
+ 
+ int x86_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cpu,
+-                             int cpuid, void *opaque);
++                             int cpuid, DumpState *s);
+ int x86_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cpu,
+-                             int cpuid, void *opaque);
++                             int cpuid, DumpState *s);
+ int x86_cpu_write_elf64_qemunote(WriteCoreDumpFunction f, CPUState *cpu,
+-                                 void *opaque);
++                                 DumpState *s);
+ int x86_cpu_write_elf32_qemunote(WriteCoreDumpFunction f, CPUState *cpu,
+-                                 void *opaque);
++                                 DumpState *s);
+ 
+ void x86_cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list,
+                                 Error **errp);
+diff --git a/target/ppc/arch_dump.c b/target/ppc/arch_dump.c
+index bb392f6d88..e9f512bcd4 100644
+--- a/target/ppc/arch_dump.c
++++ b/target/ppc/arch_dump.c
+@@ -270,23 +270,23 @@ ssize_t cpu_get_note_size(int class, int machine, int nr_cpus)
+ static int ppc_write_all_elf_notes(const char *note_name,
+                                    WriteCoreDumpFunction f,
+                                    PowerPCCPU *cpu, int id,
+-                                   void *opaque)
++                                   DumpState *s)
+ {
+-    NoteFuncArg arg = { .state = opaque };
++    NoteFuncArg arg = { .state = s };
+     int ret = -1;
+     int note_size;
+     const NoteFuncDesc *nf;
+ 
+     for (nf = note_func; nf->note_contents_func; nf++) {
+-        arg.note.hdr.n_namesz = cpu_to_dump32(opaque, sizeof(arg.note.name));
+-        arg.note.hdr.n_descsz = cpu_to_dump32(opaque, nf->contents_size);
++        arg.note.hdr.n_namesz = cpu_to_dump32(s, sizeof(arg.note.name));
++        arg.note.hdr.n_descsz = cpu_to_dump32(s, nf->contents_size);
+         strncpy(arg.note.name, note_name, sizeof(arg.note.name));
+ 
+         (*nf->note_contents_func)(&arg, cpu);
+ 
+         note_size =
+             sizeof(arg.note) - sizeof(arg.note.contents) + nf->contents_size;
+-        ret = f(&arg.note, note_size, opaque);
++        ret = f(&arg.note, note_size, s);
+         if (ret < 0) {
+             return -1;
+         }
+@@ -295,15 +295,15 @@ static int ppc_write_all_elf_notes(const char *note_name,
+ }
+ 
+ int ppc64_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+-                               int cpuid, void *opaque)
++                               int cpuid, DumpState *s)
+ {
+     PowerPCCPU *cpu = POWERPC_CPU(cs);
+-    return ppc_write_all_elf_notes("CORE", f, cpu, cpuid, opaque);
++    return ppc_write_all_elf_notes("CORE", f, cpu, cpuid, s);
+ }
+ 
+ int ppc32_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
+-                               int cpuid, void *opaque)
++                               int cpuid, DumpState *s)
+ {
+     PowerPCCPU *cpu = POWERPC_CPU(cs);
+-    return ppc_write_all_elf_notes("CORE", f, cpu, cpuid, opaque);
++    return ppc_write_all_elf_notes("CORE", f, cpu, cpuid, s);
+ }
+diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
+index 23e8b76c85..f5fb284706 100644
+--- a/target/ppc/cpu.h
++++ b/target/ppc/cpu.h
+@@ -1289,9 +1289,9 @@ void ppc_gdb_gen_spr_xml(PowerPCCPU *cpu);
+ const char *ppc_gdb_get_dynamic_xml(CPUState *cs, const char *xml_name);
+ #endif
+ int ppc64_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+-                               int cpuid, void *opaque);
++                               int cpuid, DumpState *s);
+ int ppc32_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
+-                               int cpuid, void *opaque);
++                               int cpuid, DumpState *s);
+ #ifndef CONFIG_USER_ONLY
+ void ppc_cpu_do_interrupt(CPUState *cpu);
+ bool ppc_cpu_exec_interrupt(CPUState *cpu, int int_req);
+diff --git a/target/riscv/arch_dump.c b/target/riscv/arch_dump.c
+index 709f621d82..736a232956 100644
+--- a/target/riscv/arch_dump.c
++++ b/target/riscv/arch_dump.c
+@@ -64,12 +64,11 @@ static void riscv64_note_init(struct riscv64_note *note, DumpState *s,
+ }
+ 
+ int riscv_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+-                               int cpuid, void *opaque)
++                               int cpuid, DumpState *s)
+ {
+     struct riscv64_note note;
+     RISCVCPU *cpu = RISCV_CPU(cs);
+     CPURISCVState *env = &cpu->env;
+-    DumpState *s = opaque;
+     int ret, i = 0;
+     const char name[] = "CORE";
+ 
+@@ -134,12 +133,11 @@ static void riscv32_note_init(struct riscv32_note *note, DumpState *s,
+ }
+ 
+ int riscv_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
+-                               int cpuid, void *opaque)
++                               int cpuid, DumpState *s)
+ {
+     struct riscv32_note note;
+     RISCVCPU *cpu = RISCV_CPU(cs);
+     CPURISCVState *env = &cpu->env;
+-    DumpState *s = opaque;
+     int ret, i;
+     const char name[] = "CORE";
+ 
+diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
+index 0760c0af93..4cce524b2c 100644
+--- a/target/riscv/cpu.h
++++ b/target/riscv/cpu.h
+@@ -344,9 +344,9 @@ extern const char * const riscv_fpr_regnames[];
+ const char *riscv_cpu_get_trap_name(target_ulong cause, bool async);
+ void riscv_cpu_do_interrupt(CPUState *cpu);
+ int riscv_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+-                               int cpuid, void *opaque);
++                               int cpuid, DumpState *s);
+ int riscv_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
+-                               int cpuid, void *opaque);
++                               int cpuid, DumpState *s);
+ int riscv_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg);
+ int riscv_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg);
+ bool riscv_cpu_fp_enabled(CPURISCVState *env);
+diff --git a/target/s390x/arch_dump.c b/target/s390x/arch_dump.c
+index 08daf93ae1..f60a14920d 100644
+--- a/target/s390x/arch_dump.c
++++ b/target/s390x/arch_dump.c
+@@ -204,7 +204,7 @@ static const NoteFuncDesc note_linux[] = {
+ static int s390x_write_elf64_notes(const char *note_name,
+                                        WriteCoreDumpFunction f,
+                                        S390CPU *cpu, int id,
+-                                       void *opaque,
++                                       DumpState *s,
+                                        const NoteFuncDesc *funcs)
+ {
+     Note note;
+@@ -222,7 +222,7 @@ static int s390x_write_elf64_notes(const char *note_name,
+         (*nf->note_contents_func)(&note, cpu, id);
+ 
+         note_size = sizeof(note) - sizeof(note.contents) + nf->contents_size;
+-        ret = f(&note, note_size, opaque);
++        ret = f(&note, note_size, s);
+ 
+         if (ret < 0) {
+             return -1;
+@@ -235,16 +235,16 @@ static int s390x_write_elf64_notes(const char *note_name,
+ 
+ 
+ int s390_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+-                              int cpuid, void *opaque)
++                              int cpuid, DumpState *s)
+ {
+     S390CPU *cpu = S390_CPU(cs);
+     int r;
+ 
+-    r = s390x_write_elf64_notes("CORE", f, cpu, cpuid, opaque, note_core);
++    r = s390x_write_elf64_notes("CORE", f, cpu, cpuid, s, note_core);
+     if (r) {
+         return r;
+     }
+-    return s390x_write_elf64_notes("LINUX", f, cpu, cpuid, opaque, note_linux);
++    return s390x_write_elf64_notes("LINUX", f, cpu, cpuid, s, note_linux);
+ }
+ 
+ int cpu_get_dump_info(ArchDumpInfo *info,
+diff --git a/target/s390x/s390x-internal.h b/target/s390x/s390x-internal.h
+index 1a178aed41..02cf6c3f43 100644
+--- a/target/s390x/s390x-internal.h
++++ b/target/s390x/s390x-internal.h
+@@ -228,7 +228,7 @@ static inline hwaddr decode_basedisp_s(CPUS390XState *env, uint32_t ipb,
+ 
+ /* arch_dump.c */
+ int s390_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
+-                              int cpuid, void *opaque);
++                              int cpuid, DumpState *s);
+ 
+ 
+ /* cc_helper.c */
+-- 
+2.37.3
+

SOURCES/kvm-dump-Rework-dump_calculate_size-function.patch

@@ -0,0 +1,73 @@
+From 1f7cb73592a1922b3a981eb3232098281e07679f Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Thu, 11 Aug 2022 12:10:59 +0000
+Subject: [PATCH 27/42] dump: Rework dump_calculate_size function
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [27/41] eaa05c39109b57a119752ad3df66f4c2ace2cbe4
+
+dump_calculate_size() sums up all the sizes of the guest memory
+blocks. Since we already have a function that calculates the size of a
+single memory block (dump_get_memblock_size()) we can simply iterate
+over the blocks and use the function instead of calculating the size
+ourselves.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Reviewed-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
+Message-Id: <20220811121111.9878-7-frankja@linux.ibm.com>
+(cherry picked from commit c370d5300f9ac1f90f8158082d22262b904fe30e)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 22 ++++++++--------------
+ 1 file changed, 8 insertions(+), 14 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index f6fe13e258..902a85ef8e 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -1557,25 +1557,19 @@ bool dump_in_progress(void)
+     return (qatomic_read(&state->status) == DUMP_STATUS_ACTIVE);
+ }
+ 
+-/* calculate total size of memory to be dumped (taking filter into
+- * acoount.) */
++/*
++ * calculate total size of memory to be dumped (taking filter into
++ * account.)
++ */
+ static int64_t dump_calculate_size(DumpState *s)
+ {
+     GuestPhysBlock *block;
+-    int64_t size = 0, total = 0, left = 0, right = 0;
++    int64_t total = 0;
+ 
+     QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
+-        if (dump_has_filter(s)) {
+-            /* calculate the overlapped region. */
+-            left = MAX(s->filter_area_begin, block->target_start);
+-            right = MIN(s->filter_area_begin + s->filter_area_length, block->target_end);
+-            size = right - left;
+-            size = size > 0 ? size : 0;
+-        } else {
+-            /* count the whole region in */
+-            size = (block->target_end - block->target_start);
+-        }
+-        total += size;
++        total += dump_filtered_memblock_size(block,
++                                             s->filter_area_begin,
++                                             s->filter_area_length);
+     }
+ 
+     return total;
+-- 
+2.37.3
+

SOURCES/kvm-dump-Rework-filter-area-variables.patch

@@ -0,0 +1,187 @@
+From 411f5354b809f6b783946e58d7655135814fb809 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Thu, 11 Aug 2022 12:10:58 +0000
+Subject: [PATCH 26/42] dump: Rework filter area variables
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [26/41] f10a5523dfd2724f7a8637fca3ed68ba6df659a5
+
+While the DumpState begin and length variables directly mirror the API
+variable names they are not very descriptive. So let's add a
+"filter_area_" prefix and make has_filter a function checking length > 0.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220811121111.9878-6-frankja@linux.ibm.com>
+(cherry picked from commit dddf725f70bfe7f5adb41fa31dbd06e767271bda)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c           | 53 +++++++++++++++++++++++++------------------
+ include/sysemu/dump.h | 13 ++++++++---
+ 2 files changed, 41 insertions(+), 25 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index e6aa037f59..f6fe13e258 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -60,6 +60,11 @@ static inline bool dump_is_64bit(DumpState *s)
+     return s->dump_info.d_class == ELFCLASS64;
+ }
+ 
++static inline bool dump_has_filter(DumpState *s)
++{
++    return s->filter_area_length > 0;
++}
++
+ uint16_t cpu_to_dump16(DumpState *s, uint16_t val)
+ {
+     if (s->dump_info.d_endian == ELFDATA2LSB) {
+@@ -444,29 +449,30 @@ static void get_offset_range(hwaddr phys_addr,
+     *p_offset = -1;
+     *p_filesz = 0;
+ 
+-    if (s->has_filter) {
+-        if (phys_addr < s->begin || phys_addr >= s->begin + s->length) {
++    if (dump_has_filter(s)) {
++        if (phys_addr < s->filter_area_begin ||
++            phys_addr >= s->filter_area_begin + s->filter_area_length) {
+             return;
+         }
+     }
+ 
+     QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
+-        if (s->has_filter) {
+-            if (block->target_start >= s->begin + s->length ||
+-                block->target_end <= s->begin) {
++        if (dump_has_filter(s)) {
++            if (block->target_start >= s->filter_area_begin + s->filter_area_length ||
++                block->target_end <= s->filter_area_begin) {
+                 /* This block is out of the range */
+                 continue;
+             }
+ 
+-            if (s->begin <= block->target_start) {
++            if (s->filter_area_begin <= block->target_start) {
+                 start = block->target_start;
+             } else {
+-                start = s->begin;
++                start = s->filter_area_begin;
+             }
+ 
+             size_in_block = block->target_end - start;
+-            if (s->begin + s->length < block->target_end) {
+-                size_in_block -= block->target_end - (s->begin + s->length);
++            if (s->filter_area_begin + s->filter_area_length < block->target_end) {
++                size_in_block -= block->target_end - (s->filter_area_begin + s->filter_area_length);
+             }
+         } else {
+             start = block->target_start;
+@@ -639,12 +645,12 @@ static void dump_iterate(DumpState *s, Error **errp)
+     int64_t memblock_size, memblock_start;
+ 
+     QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
+-        memblock_start = dump_filtered_memblock_start(block, s->begin, s->length);
++        memblock_start = dump_filtered_memblock_start(block, s->filter_area_begin, s->filter_area_length);
+         if (memblock_start == -1) {
+             continue;
+         }
+ 
+-        memblock_size = dump_filtered_memblock_size(block, s->begin, s->length);
++        memblock_size = dump_filtered_memblock_size(block, s->filter_area_begin, s->filter_area_length);
+ 
+         /* Write the memory to file */
+         write_memory(s, block, memblock_start, memblock_size, errp);
+@@ -1513,14 +1519,14 @@ static int validate_start_block(DumpState *s)
+ {
+     GuestPhysBlock *block;
+ 
+-    if (!s->has_filter) {
++    if (!dump_has_filter(s)) {
+         return 0;
+     }
+ 
+     QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
+         /* This block is out of the range */
+-        if (block->target_start >= s->begin + s->length ||
+-            block->target_end <= s->begin) {
++        if (block->target_start >= s->filter_area_begin + s->filter_area_length ||
++            block->target_end <= s->filter_area_begin) {
+             continue;
+         }
+         return 0;
+@@ -1559,10 +1565,10 @@ static int64_t dump_calculate_size(DumpState *s)
+     int64_t size = 0, total = 0, left = 0, right = 0;
+ 
+     QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
+-        if (s->has_filter) {
++        if (dump_has_filter(s)) {
+             /* calculate the overlapped region. */
+-            left = MAX(s->begin, block->target_start);
+-            right = MIN(s->begin + s->length, block->target_end);
++            left = MAX(s->filter_area_begin, block->target_start);
++            right = MIN(s->filter_area_begin + s->filter_area_length, block->target_end);
+             size = right - left;
+             size = size > 0 ? size : 0;
+         } else {
+@@ -1652,9 +1658,12 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+     }
+ 
+     s->fd = fd;
+-    s->has_filter = has_filter;
+-    s->begin = begin;
+-    s->length = length;
++    if (has_filter && !length) {
++        error_setg(errp, QERR_INVALID_PARAMETER, "length");
++        goto cleanup;
++    }
++    s->filter_area_begin = begin;
++    s->filter_area_length = length;
+ 
+     memory_mapping_list_init(&s->list);
+ 
+@@ -1787,8 +1796,8 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+         return;
+     }
+ 
+-    if (s->has_filter) {
+-        memory_mapping_filter(&s->list, s->begin, s->length);
++    if (dump_has_filter(s)) {
++        memory_mapping_filter(&s->list, s->filter_area_begin, s->filter_area_length);
+     }
+ 
+     /*
+diff --git a/include/sysemu/dump.h b/include/sysemu/dump.h
+index 7fce1d4af6..b62513d87d 100644
+--- a/include/sysemu/dump.h
++++ b/include/sysemu/dump.h
+@@ -166,9 +166,16 @@ typedef struct DumpState {
+     hwaddr memory_offset;
+     int fd;
+ 
+-    bool has_filter;
+-    int64_t begin;
+-    int64_t length;
++    /*
++     * Dump filter area variables
++     *
++     * A filtered dump only contains the guest memory designated by
++     * the start address and length variables defined below.
++     *
++     * If length is 0, no filtering is applied.
++     */
++    int64_t filter_area_begin;  /* Start address of partial guest memory area */
++    int64_t filter_area_length; /* Length of partial guest memory area */
+ 
+     uint8_t *note_buf;          /* buffer for notes */
+     size_t note_buf_offset;     /* the writing place in note_buf */
+-- 
+2.37.3
+

SOURCES/kvm-dump-Rework-get_start_block.patch

@@ -0,0 +1,102 @@
+From b56c362132baef40cc25d910c1e0d217d83cfe44 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Thu, 11 Aug 2022 12:10:57 +0000
+Subject: [PATCH 25/42] dump: Rework get_start_block
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [25/41] c93842a1aaeadcc11e91c194452fcd05d163b3ca
+
+get_start_block() returns the start address of the first memory block
+or -1.
+
+With the GuestPhysBlock iterator conversion we don't need to set the
+start address and can therefore remove that code and the "start"
+DumpState struct member. The only functionality left is the validation
+of the start block so it only makes sense to re-name the function to
+validate_start_block()
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Reviewed-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
+Message-Id: <20220811121111.9878-5-frankja@linux.ibm.com>
+(cherry picked from commit 0c2994ac9009577b967529ce18e269da5b280351)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c           | 20 ++++++--------------
+ include/sysemu/dump.h |  2 --
+ 2 files changed, 6 insertions(+), 16 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index d981e843dd..e6aa037f59 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -1509,30 +1509,22 @@ static void create_kdump_vmcore(DumpState *s, Error **errp)
+     }
+ }
+ 
+-static ram_addr_t get_start_block(DumpState *s)
++static int validate_start_block(DumpState *s)
+ {
+     GuestPhysBlock *block;
+ 
+     if (!s->has_filter) {
+-        s->next_block = QTAILQ_FIRST(&s->guest_phys_blocks.head);
+         return 0;
+     }
+ 
+     QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
++        /* This block is out of the range */
+         if (block->target_start >= s->begin + s->length ||
+             block->target_end <= s->begin) {
+-            /* This block is out of the range */
+             continue;
+         }
+-
+-        s->next_block = block;
+-        if (s->begin > block->target_start) {
+-            s->start = s->begin - block->target_start;
+-        } else {
+-            s->start = 0;
+-        }
+-        return s->start;
+-    }
++        return 0;
++   }
+ 
+     return -1;
+ }
+@@ -1679,8 +1671,8 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+         goto cleanup;
+     }
+ 
+-    s->start = get_start_block(s);
+-    if (s->start == -1) {
++    /* Is the filter filtering everything? */
++    if (validate_start_block(s) == -1) {
+         error_setg(errp, QERR_INVALID_PARAMETER, "begin");
+         goto cleanup;
+     }
+diff --git a/include/sysemu/dump.h b/include/sysemu/dump.h
+index ffc2ea1072..7fce1d4af6 100644
+--- a/include/sysemu/dump.h
++++ b/include/sysemu/dump.h
+@@ -166,8 +166,6 @@ typedef struct DumpState {
+     hwaddr memory_offset;
+     int fd;
+ 
+-    GuestPhysBlock *next_block;
+-    ram_addr_t start;
+     bool has_filter;
+     int64_t begin;
+     int64_t length;
+-- 
+2.37.3
+

SOURCES/kvm-dump-Split-elf-header-functions-into-prepare-and-wri.patch

@@ -0,0 +1,173 @@
+From d1e147a3133d4d31d4b0c02c05916366fadd9c30 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Thu, 11 Aug 2022 12:11:00 +0000
+Subject: [PATCH 28/42] dump: Split elf header functions into prepare and write
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [28/41] f70a13ad443835e7f46b7c5e176e372d370ac797
+
+Let's split the write from the modification of the elf header so we
+can consolidate the write of the data in one function.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220811121111.9878-8-frankja@linux.ibm.com>
+(cherry picked from commit 670e76998a61ca171200fcded3865b294a2d1243)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 100 ++++++++++++++++++++++++++++------------------------
+ 1 file changed, 53 insertions(+), 47 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 902a85ef8e..8d5226f861 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -132,7 +132,7 @@ static int fd_write_vmcore(const void *buf, size_t size, void *opaque)
+     return 0;
+ }
+ 
+-static void write_elf64_header(DumpState *s, Error **errp)
++static void prepare_elf64_header(DumpState *s, Elf64_Ehdr *elf_header)
+ {
+     /*
+      * phnum in the elf header is 16 bit, if we have more segments we
+@@ -140,34 +140,27 @@ static void write_elf64_header(DumpState *s, Error **errp)
+      * special section.
+      */
+     uint16_t phnum = MIN(s->phdr_num, PN_XNUM);
+-    Elf64_Ehdr elf_header;
+-    int ret;
+ 
+-    memset(&elf_header, 0, sizeof(Elf64_Ehdr));
+-    memcpy(&elf_header, ELFMAG, SELFMAG);
+-    elf_header.e_ident[EI_CLASS] = ELFCLASS64;
+-    elf_header.e_ident[EI_DATA] = s->dump_info.d_endian;
+-    elf_header.e_ident[EI_VERSION] = EV_CURRENT;
+-    elf_header.e_type = cpu_to_dump16(s, ET_CORE);
+-    elf_header.e_machine = cpu_to_dump16(s, s->dump_info.d_machine);
+-    elf_header.e_version = cpu_to_dump32(s, EV_CURRENT);
+-    elf_header.e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
+-    elf_header.e_phoff = cpu_to_dump64(s, s->phdr_offset);
+-    elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf64_Phdr));
+-    elf_header.e_phnum = cpu_to_dump16(s, phnum);
++    memset(elf_header, 0, sizeof(Elf64_Ehdr));
++    memcpy(elf_header, ELFMAG, SELFMAG);
++    elf_header->e_ident[EI_CLASS] = ELFCLASS64;
++    elf_header->e_ident[EI_DATA] = s->dump_info.d_endian;
++    elf_header->e_ident[EI_VERSION] = EV_CURRENT;
++    elf_header->e_type = cpu_to_dump16(s, ET_CORE);
++    elf_header->e_machine = cpu_to_dump16(s, s->dump_info.d_machine);
++    elf_header->e_version = cpu_to_dump32(s, EV_CURRENT);
++    elf_header->e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
++    elf_header->e_phoff = cpu_to_dump64(s, s->phdr_offset);
++    elf_header->e_phentsize = cpu_to_dump16(s, sizeof(Elf64_Phdr));
++    elf_header->e_phnum = cpu_to_dump16(s, phnum);
+     if (s->shdr_num) {
+-        elf_header.e_shoff = cpu_to_dump64(s, s->shdr_offset);
+-        elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf64_Shdr));
+-        elf_header.e_shnum = cpu_to_dump16(s, s->shdr_num);
+-    }
+-
+-    ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
+-    if (ret < 0) {
+-        error_setg_errno(errp, -ret, "dump: failed to write elf header");
++        elf_header->e_shoff = cpu_to_dump64(s, s->shdr_offset);
++        elf_header->e_shentsize = cpu_to_dump16(s, sizeof(Elf64_Shdr));
++        elf_header->e_shnum = cpu_to_dump16(s, s->shdr_num);
+     }
+ }
+ 
+-static void write_elf32_header(DumpState *s, Error **errp)
++static void prepare_elf32_header(DumpState *s, Elf32_Ehdr *elf_header)
+ {
+     /*
+      * phnum in the elf header is 16 bit, if we have more segments we
+@@ -175,28 +168,45 @@ static void write_elf32_header(DumpState *s, Error **errp)
+      * special section.
+      */
+     uint16_t phnum = MIN(s->phdr_num, PN_XNUM);
+-    Elf32_Ehdr elf_header;
+-    int ret;
+ 
+-    memset(&elf_header, 0, sizeof(Elf32_Ehdr));
+-    memcpy(&elf_header, ELFMAG, SELFMAG);
+-    elf_header.e_ident[EI_CLASS] = ELFCLASS32;
+-    elf_header.e_ident[EI_DATA] = s->dump_info.d_endian;
+-    elf_header.e_ident[EI_VERSION] = EV_CURRENT;
+-    elf_header.e_type = cpu_to_dump16(s, ET_CORE);
+-    elf_header.e_machine = cpu_to_dump16(s, s->dump_info.d_machine);
+-    elf_header.e_version = cpu_to_dump32(s, EV_CURRENT);
+-    elf_header.e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
+-    elf_header.e_phoff = cpu_to_dump32(s, s->phdr_offset);
+-    elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf32_Phdr));
+-    elf_header.e_phnum = cpu_to_dump16(s, phnum);
++    memset(elf_header, 0, sizeof(Elf32_Ehdr));
++    memcpy(elf_header, ELFMAG, SELFMAG);
++    elf_header->e_ident[EI_CLASS] = ELFCLASS32;
++    elf_header->e_ident[EI_DATA] = s->dump_info.d_endian;
++    elf_header->e_ident[EI_VERSION] = EV_CURRENT;
++    elf_header->e_type = cpu_to_dump16(s, ET_CORE);
++    elf_header->e_machine = cpu_to_dump16(s, s->dump_info.d_machine);
++    elf_header->e_version = cpu_to_dump32(s, EV_CURRENT);
++    elf_header->e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
++    elf_header->e_phoff = cpu_to_dump32(s, s->phdr_offset);
++    elf_header->e_phentsize = cpu_to_dump16(s, sizeof(Elf32_Phdr));
++    elf_header->e_phnum = cpu_to_dump16(s, phnum);
+     if (s->shdr_num) {
+-        elf_header.e_shoff = cpu_to_dump32(s, s->shdr_offset);
+-        elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf32_Shdr));
+-        elf_header.e_shnum = cpu_to_dump16(s, s->shdr_num);
++        elf_header->e_shoff = cpu_to_dump32(s, s->shdr_offset);
++        elf_header->e_shentsize = cpu_to_dump16(s, sizeof(Elf32_Shdr));
++        elf_header->e_shnum = cpu_to_dump16(s, s->shdr_num);
+     }
++}
+ 
+-    ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
++static void write_elf_header(DumpState *s, Error **errp)
++{
++    Elf32_Ehdr elf32_header;
++    Elf64_Ehdr elf64_header;
++    size_t header_size;
++    void *header_ptr;
++    int ret;
++
++    if (dump_is_64bit(s)) {
++        prepare_elf64_header(s, &elf64_header);
++        header_size = sizeof(elf64_header);
++        header_ptr = &elf64_header;
++    } else {
++        prepare_elf32_header(s, &elf32_header);
++        header_size = sizeof(elf32_header);
++        header_ptr = &elf32_header;
++    }
++
++    ret = fd_write_vmcore(header_ptr, header_size, s);
+     if (ret < 0) {
+         error_setg_errno(errp, -ret, "dump: failed to write elf header");
+     }
+@@ -565,11 +575,7 @@ static void dump_begin(DumpState *s, Error **errp)
+      */
+ 
+     /* write elf header to vmcore */
+-    if (dump_is_64bit(s)) {
+-        write_elf64_header(s, errp);
+-    } else {
+-        write_elf32_header(s, errp);
+-    }
++    write_elf_header(s, errp);
+     if (*errp) {
+         return;
+     }
+-- 
+2.37.3
+

SOURCES/kvm-dump-Use-ERRP_GUARD.patch

@@ -0,0 +1,420 @@
+From 4ca61efe246d62d420eb332655c0c8ead4cc762b Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Wed, 30 Mar 2022 12:35:55 +0000
+Subject: [PATCH 13/42] dump: Use ERRP_GUARD()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [13/41] f735cd1dab0230000cfadd878765fdf4647b239c
+
+Let's move to the new way of handling errors before changing the dump
+code. This patch has mostly been generated by the coccinelle script
+scripts/coccinelle/errp-guard.cocci.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20220330123603.107120-2-frankja@linux.ibm.com>
+(cherry picked from commit 86a518bba4f4d7c9016fc5b104fe1e58b00ad756)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 144 ++++++++++++++++++++++------------------------------
+ 1 file changed, 61 insertions(+), 83 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 662d0a62cd..9876123f2e 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -390,23 +390,21 @@ static void write_data(DumpState *s, void *buf, int length, Error **errp)
+ static void write_memory(DumpState *s, GuestPhysBlock *block, ram_addr_t start,
+                          int64_t size, Error **errp)
+ {
++    ERRP_GUARD();
+     int64_t i;
+-    Error *local_err = NULL;
+ 
+     for (i = 0; i < size / s->dump_info.page_size; i++) {
+         write_data(s, block->host_addr + start + i * s->dump_info.page_size,
+-                   s->dump_info.page_size, &local_err);
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++                   s->dump_info.page_size, errp);
++        if (*errp) {
+             return;
+         }
+     }
+ 
+     if ((size % s->dump_info.page_size) != 0) {
+         write_data(s, block->host_addr + start + i * s->dump_info.page_size,
+-                   size % s->dump_info.page_size, &local_err);
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++                   size % s->dump_info.page_size, errp);
++        if (*errp) {
+             return;
+         }
+     }
+@@ -476,11 +474,11 @@ static void get_offset_range(hwaddr phys_addr,
+ 
+ static void write_elf_loads(DumpState *s, Error **errp)
+ {
++    ERRP_GUARD();
+     hwaddr offset, filesz;
+     MemoryMapping *memory_mapping;
+     uint32_t phdr_index = 1;
+     uint32_t max_index;
+-    Error *local_err = NULL;
+ 
+     if (s->have_section) {
+         max_index = s->sh_info;
+@@ -494,14 +492,13 @@ static void write_elf_loads(DumpState *s, Error **errp)
+                          s, &offset, &filesz);
+         if (s->dump_info.d_class == ELFCLASS64) {
+             write_elf64_load(s, memory_mapping, phdr_index++, offset,
+-                             filesz, &local_err);
++                             filesz, errp);
+         } else {
+             write_elf32_load(s, memory_mapping, phdr_index++, offset,
+-                             filesz, &local_err);
++                             filesz, errp);
+         }
+ 
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++        if (*errp) {
+             return;
+         }
+ 
+@@ -514,7 +511,7 @@ static void write_elf_loads(DumpState *s, Error **errp)
+ /* write elf header, PT_NOTE and elf note to vmcore. */
+ static void dump_begin(DumpState *s, Error **errp)
+ {
+-    Error *local_err = NULL;
++    ERRP_GUARD();
+ 
+     /*
+      * the vmcore's format is:
+@@ -542,73 +539,64 @@ static void dump_begin(DumpState *s, Error **errp)
+ 
+     /* write elf header to vmcore */
+     if (s->dump_info.d_class == ELFCLASS64) {
+-        write_elf64_header(s, &local_err);
++        write_elf64_header(s, errp);
+     } else {
+-        write_elf32_header(s, &local_err);
++        write_elf32_header(s, errp);
+     }
+-    if (local_err) {
+-        error_propagate(errp, local_err);
++    if (*errp) {
+         return;
+     }
+ 
+     if (s->dump_info.d_class == ELFCLASS64) {
+         /* write PT_NOTE to vmcore */
+-        write_elf64_note(s, &local_err);
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++        write_elf64_note(s, errp);
++        if (*errp) {
+             return;
+         }
+ 
+         /* write all PT_LOAD to vmcore */
+-        write_elf_loads(s, &local_err);
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++        write_elf_loads(s, errp);
++        if (*errp) {
+             return;
+         }
+ 
+         /* write section to vmcore */
+         if (s->have_section) {
+-            write_elf_section(s, 1, &local_err);
+-            if (local_err) {
+-                error_propagate(errp, local_err);
++            write_elf_section(s, 1, errp);
++            if (*errp) {
+                 return;
+             }
+         }
+ 
+         /* write notes to vmcore */
+-        write_elf64_notes(fd_write_vmcore, s, &local_err);
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++        write_elf64_notes(fd_write_vmcore, s, errp);
++        if (*errp) {
+             return;
+         }
+     } else {
+         /* write PT_NOTE to vmcore */
+-        write_elf32_note(s, &local_err);
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++        write_elf32_note(s, errp);
++        if (*errp) {
+             return;
+         }
+ 
+         /* write all PT_LOAD to vmcore */
+-        write_elf_loads(s, &local_err);
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++        write_elf_loads(s, errp);
++        if (*errp) {
+             return;
+         }
+ 
+         /* write section to vmcore */
+         if (s->have_section) {
+-            write_elf_section(s, 0, &local_err);
+-            if (local_err) {
+-                error_propagate(errp, local_err);
++            write_elf_section(s, 0, errp);
++            if (*errp) {
+                 return;
+             }
+         }
+ 
+         /* write notes to vmcore */
+-        write_elf32_notes(fd_write_vmcore, s, &local_err);
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++        write_elf32_notes(fd_write_vmcore, s, errp);
++        if (*errp) {
+             return;
+         }
+     }
+@@ -644,9 +632,9 @@ static int get_next_block(DumpState *s, GuestPhysBlock *block)
+ /* write all memory to vmcore */
+ static void dump_iterate(DumpState *s, Error **errp)
+ {
++    ERRP_GUARD();
+     GuestPhysBlock *block;
+     int64_t size;
+-    Error *local_err = NULL;
+ 
+     do {
+         block = s->next_block;
+@@ -658,9 +646,8 @@ static void dump_iterate(DumpState *s, Error **errp)
+                 size -= block->target_end - (s->begin + s->length);
+             }
+         }
+-        write_memory(s, block, s->start, size, &local_err);
+-        if (local_err) {
+-            error_propagate(errp, local_err);
++        write_memory(s, block, s->start, size, errp);
++        if (*errp) {
+             return;
+         }
+ 
+@@ -669,11 +656,10 @@ static void dump_iterate(DumpState *s, Error **errp)
+ 
+ static void create_vmcore(DumpState *s, Error **errp)
+ {
+-    Error *local_err = NULL;
++    ERRP_GUARD();
+ 
+-    dump_begin(s, &local_err);
+-    if (local_err) {
+-        error_propagate(errp, local_err);
++    dump_begin(s, errp);
++    if (*errp) {
+         return;
+     }
+ 
+@@ -810,6 +796,7 @@ static bool note_name_equal(DumpState *s,
+ /* write common header, sub header and elf note to vmcore */
+ static void create_header32(DumpState *s, Error **errp)
+ {
++    ERRP_GUARD();
+     DiskDumpHeader32 *dh = NULL;
+     KdumpSubHeader32 *kh = NULL;
+     size_t size;
+@@ -818,7 +805,6 @@ static void create_header32(DumpState *s, Error **errp)
+     uint32_t bitmap_blocks;
+     uint32_t status = 0;
+     uint64_t offset_note;
+-    Error *local_err = NULL;
+ 
+     /* write common header, the version of kdump-compressed format is 6th */
+     size = sizeof(DiskDumpHeader32);
+@@ -894,9 +880,8 @@ static void create_header32(DumpState *s, Error **errp)
+     s->note_buf_offset = 0;
+ 
+     /* use s->note_buf to store notes temporarily */
+-    write_elf32_notes(buf_write_note, s, &local_err);
+-    if (local_err) {
+-        error_propagate(errp, local_err);
++    write_elf32_notes(buf_write_note, s, errp);
++    if (*errp) {
+         goto out;
+     }
+     if (write_buffer(s->fd, offset_note, s->note_buf,
+@@ -922,6 +907,7 @@ out:
+ /* write common header, sub header and elf note to vmcore */
+ static void create_header64(DumpState *s, Error **errp)
+ {
++    ERRP_GUARD();
+     DiskDumpHeader64 *dh = NULL;
+     KdumpSubHeader64 *kh = NULL;
+     size_t size;
+@@ -930,7 +916,6 @@ static void create_header64(DumpState *s, Error **errp)
+     uint32_t bitmap_blocks;
+     uint32_t status = 0;
+     uint64_t offset_note;
+-    Error *local_err = NULL;
+ 
+     /* write common header, the version of kdump-compressed format is 6th */
+     size = sizeof(DiskDumpHeader64);
+@@ -1006,9 +991,8 @@ static void create_header64(DumpState *s, Error **errp)
+     s->note_buf_offset = 0;
+ 
+     /* use s->note_buf to store notes temporarily */
+-    write_elf64_notes(buf_write_note, s, &local_err);
+-    if (local_err) {
+-        error_propagate(errp, local_err);
++    write_elf64_notes(buf_write_note, s, errp);
++    if (*errp) {
+         goto out;
+     }
+ 
+@@ -1472,8 +1456,8 @@ out:
+ 
+ static void create_kdump_vmcore(DumpState *s, Error **errp)
+ {
++    ERRP_GUARD();
+     int ret;
+-    Error *local_err = NULL;
+ 
+     /*
+      * the kdump-compressed format is:
+@@ -1503,21 +1487,18 @@ static void create_kdump_vmcore(DumpState *s, Error **errp)
+         return;
+     }
+ 
+-    write_dump_header(s, &local_err);
+-    if (local_err) {
+-        error_propagate(errp, local_err);
++    write_dump_header(s, errp);
++    if (*errp) {
+         return;
+     }
+ 
+-    write_dump_bitmap(s, &local_err);
+-    if (local_err) {
+-        error_propagate(errp, local_err);
++    write_dump_bitmap(s, errp);
++    if (*errp) {
+         return;
+     }
+ 
+-    write_dump_pages(s, &local_err);
+-    if (local_err) {
+-        error_propagate(errp, local_err);
++    write_dump_pages(s, errp);
++    if (*errp) {
+         return;
+     }
+ 
+@@ -1647,10 +1628,10 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+                       DumpGuestMemoryFormat format, bool paging, bool has_filter,
+                       int64_t begin, int64_t length, Error **errp)
+ {
++    ERRP_GUARD();
+     VMCoreInfoState *vmci = vmcoreinfo_find();
+     CPUState *cpu;
+     int nr_cpus;
+-    Error *err = NULL;
+     int ret;
+ 
+     s->has_format = has_format;
+@@ -1769,9 +1750,8 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+ 
+     /* get memory mapping */
+     if (paging) {
+-        qemu_get_guest_memory_mapping(&s->list, &s->guest_phys_blocks, &err);
+-        if (err != NULL) {
+-            error_propagate(errp, err);
++        qemu_get_guest_memory_mapping(&s->list, &s->guest_phys_blocks, errp);
++        if (*errp) {
+             goto cleanup;
+         }
+     } else {
+@@ -1870,33 +1850,32 @@ cleanup:
+ /* this operation might be time consuming. */
+ static void dump_process(DumpState *s, Error **errp)
+ {
+-    Error *local_err = NULL;
++    ERRP_GUARD();
+     DumpQueryResult *result = NULL;
+ 
+     if (s->has_format && s->format == DUMP_GUEST_MEMORY_FORMAT_WIN_DMP) {
+ #ifdef TARGET_X86_64
+-        create_win_dump(s, &local_err);
++        create_win_dump(s, errp);
+ #endif
+     } else if (s->has_format && s->format != DUMP_GUEST_MEMORY_FORMAT_ELF) {
+-        create_kdump_vmcore(s, &local_err);
++        create_kdump_vmcore(s, errp);
+     } else {
+-        create_vmcore(s, &local_err);
++        create_vmcore(s, errp);
+     }
+ 
+     /* make sure status is written after written_size updates */
+     smp_wmb();
+     qatomic_set(&s->status,
+-               (local_err ? DUMP_STATUS_FAILED : DUMP_STATUS_COMPLETED));
++               (*errp ? DUMP_STATUS_FAILED : DUMP_STATUS_COMPLETED));
+ 
+     /* send DUMP_COMPLETED message (unconditionally) */
+     result = qmp_query_dump(NULL);
+     /* should never fail */
+     assert(result);
+-    qapi_event_send_dump_completed(result, !!local_err, (local_err ?
+-                                   error_get_pretty(local_err) : NULL));
++    qapi_event_send_dump_completed(result, !!*errp, (*errp ?
++                                                     error_get_pretty(*errp) : NULL));
+     qapi_free_DumpQueryResult(result);
+ 
+-    error_propagate(errp, local_err);
+     dump_cleanup(s);
+ }
+ 
+@@ -1925,10 +1904,10 @@ void qmp_dump_guest_memory(bool paging, const char *file,
+                            int64_t length, bool has_format,
+                            DumpGuestMemoryFormat format, Error **errp)
+ {
++    ERRP_GUARD();
+     const char *p;
+     int fd = -1;
+     DumpState *s;
+-    Error *local_err = NULL;
+     bool detach_p = false;
+ 
+     if (runstate_check(RUN_STATE_INMIGRATE)) {
+@@ -2028,9 +2007,8 @@ void qmp_dump_guest_memory(bool paging, const char *file,
+     dump_state_prepare(s);
+ 
+     dump_init(s, fd, has_format, format, paging, has_begin,
+-              begin, length, &local_err);
+-    if (local_err) {
+-        error_propagate(errp, local_err);
++              begin, length, errp);
++    if (*errp) {
+         qatomic_set(&s->status, DUMP_STATUS_FAILED);
+         return;
+     }
+-- 
+2.37.3
+

SOURCES/kvm-dump-Use-a-buffer-for-ELF-section-data-and-headers.patch

@@ -0,0 +1,150 @@
+From a918c7305ec7c68e8bc37b449f71e75d84124cd0 Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Mon, 17 Oct 2022 08:38:13 +0000
+Subject: [PATCH 32/42] dump: Use a buffer for ELF section data and headers
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [32/41] e1a03e202e67764581e486f37e13e479200e5846
+
+Currently we're writing the NULL section header if we overflow the
+physical header number in the ELF header. But in the future we'll add
+custom section headers AND section data.
+
+To facilitate this we need to rearange section handling a bit. As with
+the other ELF headers we split the code into a prepare and a write
+step.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20221017083822.43118-2-frankja@linux.ibm.com>
+(cherry picked from commit e41ed29bcee5cb16715317bcf290f6b5c196eb0a)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c           | 75 +++++++++++++++++++++++++++++--------------
+ include/sysemu/dump.h |  2 ++
+ 2 files changed, 53 insertions(+), 24 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 88177fa886..4142b4cc0c 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -381,31 +381,60 @@ static void write_elf_phdr_note(DumpState *s, Error **errp)
+     }
+ }
+ 
+-static void write_elf_section(DumpState *s, int type, Error **errp)
++static void prepare_elf_section_hdr_zero(DumpState *s)
+ {
+-    Elf32_Shdr shdr32;
+-    Elf64_Shdr shdr64;
+-    int shdr_size;
+-    void *shdr;
+-    int ret;
++    if (dump_is_64bit(s)) {
++        Elf64_Shdr *shdr64 = s->elf_section_hdrs;
+ 
+-    if (type == 0) {
+-        shdr_size = sizeof(Elf32_Shdr);
+-        memset(&shdr32, 0, shdr_size);
+-        shdr32.sh_info = cpu_to_dump32(s, s->phdr_num);
+-        shdr = &shdr32;
++        shdr64->sh_info = cpu_to_dump32(s, s->phdr_num);
+     } else {
+-        shdr_size = sizeof(Elf64_Shdr);
+-        memset(&shdr64, 0, shdr_size);
+-        shdr64.sh_info = cpu_to_dump32(s, s->phdr_num);
+-        shdr = &shdr64;
++        Elf32_Shdr *shdr32 = s->elf_section_hdrs;
++
++        shdr32->sh_info = cpu_to_dump32(s, s->phdr_num);
++    }
++}
++
++static void prepare_elf_section_hdrs(DumpState *s)
++{
++    size_t len, sizeof_shdr;
++
++    /*
++     * Section ordering:
++     * - HDR zero
++     */
++    sizeof_shdr = dump_is_64bit(s) ? sizeof(Elf64_Shdr) : sizeof(Elf32_Shdr);
++    len = sizeof_shdr * s->shdr_num;
++    s->elf_section_hdrs = g_malloc0(len);
++
++    /*
++     * The first section header is ALWAYS a special initial section
++     * header.
++     *
++     * The header should be 0 with one exception being that if
++     * phdr_num is PN_XNUM then the sh_info field contains the real
++     * number of segment entries.
++     *
++     * As we zero allocate the buffer we will only need to modify
++     * sh_info for the PN_XNUM case.
++     */
++    if (s->phdr_num >= PN_XNUM) {
++        prepare_elf_section_hdr_zero(s);
+     }
++}
+ 
+-    ret = fd_write_vmcore(shdr, shdr_size, s);
++static void write_elf_section_headers(DumpState *s, Error **errp)
++{
++    size_t sizeof_shdr = dump_is_64bit(s) ? sizeof(Elf64_Shdr) : sizeof(Elf32_Shdr);
++    int ret;
++
++    prepare_elf_section_hdrs(s);
++
++    ret = fd_write_vmcore(s->elf_section_hdrs, s->shdr_num * sizeof_shdr, s);
+     if (ret < 0) {
+-        error_setg_errno(errp, -ret,
+-                         "dump: failed to write section header table");
++        error_setg_errno(errp, -ret, "dump: failed to write section headers");
+     }
++
++    g_free(s->elf_section_hdrs);
+ }
+ 
+ static void write_data(DumpState *s, void *buf, int length, Error **errp)
+@@ -592,12 +621,10 @@ static void dump_begin(DumpState *s, Error **errp)
+         return;
+     }
+ 
+-    /* write section to vmcore */
+-    if (s->shdr_num) {
+-        write_elf_section(s, 1, errp);
+-        if (*errp) {
+-            return;
+-        }
++    /* write section headers to vmcore */
++    write_elf_section_headers(s, errp);
++    if (*errp) {
++        return;
+     }
+ 
+     /* write notes to vmcore */
+diff --git a/include/sysemu/dump.h b/include/sysemu/dump.h
+index b62513d87d..9995f65dc8 100644
+--- a/include/sysemu/dump.h
++++ b/include/sysemu/dump.h
+@@ -177,6 +177,8 @@ typedef struct DumpState {
+     int64_t filter_area_begin;  /* Start address of partial guest memory area */
+     int64_t filter_area_length; /* Length of partial guest memory area */
+ 
++    void *elf_section_hdrs;     /* Pointer to section header buffer */
++
+     uint8_t *note_buf;          /* buffer for notes */
+     size_t note_buf_offset;     /* the writing place in note_buf */
+     uint32_t nr_cpus;           /* number of guest's cpu */
+-- 
+2.37.3
+

SOURCES/kvm-dump-Write-ELF-section-headers-right-after-ELF-heade.patch

@@ -0,0 +1,104 @@
+From 987ede93fa4e3d058acddc19874e467faa116ede Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Mon, 17 Oct 2022 08:38:14 +0000
+Subject: [PATCH 33/42] dump: Write ELF section headers right after ELF header
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [33/41] e956040753533ac376e9763145192de1e216027d
+
+Let's start bundling the writes of the headers and of the data so we
+have a clear ordering between them. Since the ELF header uses offsets
+to the headers we can freely order them.
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Message-Id: <20221017083822.43118-3-frankja@linux.ibm.com>
+(cherry picked from commit cb415fd61e48d52f81dcf38956e3f913651cff1c)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 31 ++++++++++++++-----------------
+ 1 file changed, 14 insertions(+), 17 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 4142b4cc0c..d17537d4e9 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -584,6 +584,8 @@ static void dump_begin(DumpState *s, Error **errp)
+      *   --------------
+      *   |  elf header |
+      *   --------------
++     *   |  sctn_hdr   |
++     *   --------------
+      *   |  PT_NOTE    |
+      *   --------------
+      *   |  PT_LOAD    |
+@@ -592,8 +594,6 @@ static void dump_begin(DumpState *s, Error **errp)
+      *   --------------
+      *   |  PT_LOAD    |
+      *   --------------
+-     *   |  sec_hdr    |
+-     *   --------------
+      *   |  elf note   |
+      *   --------------
+      *   |  memory     |
+@@ -609,20 +609,20 @@ static void dump_begin(DumpState *s, Error **errp)
+         return;
+     }
+ 
+-    /* write PT_NOTE to vmcore */
+-    write_elf_phdr_note(s, errp);
++    /* write section headers to vmcore */
++    write_elf_section_headers(s, errp);
+     if (*errp) {
+         return;
+     }
+ 
+-    /* write all PT_LOADs to vmcore */
+-    write_elf_phdr_loads(s, errp);
++    /* write PT_NOTE to vmcore */
++    write_elf_phdr_note(s, errp);
+     if (*errp) {
+         return;
+     }
+ 
+-    /* write section headers to vmcore */
+-    write_elf_section_headers(s, errp);
++    /* write all PT_LOADs to vmcore */
++    write_elf_phdr_loads(s, errp);
+     if (*errp) {
+         return;
+     }
+@@ -1877,16 +1877,13 @@ static void dump_init(DumpState *s, int fd, bool has_format,
+     }
+ 
+     if (dump_is_64bit(s)) {
+-        s->phdr_offset = sizeof(Elf64_Ehdr);
+-        s->shdr_offset = s->phdr_offset + sizeof(Elf64_Phdr) * s->phdr_num;
+-        s->note_offset = s->shdr_offset + sizeof(Elf64_Shdr) * s->shdr_num;
+-        s->memory_offset = s->note_offset + s->note_size;
++        s->shdr_offset = sizeof(Elf64_Ehdr);
++        s->phdr_offset = s->shdr_offset + sizeof(Elf64_Shdr) * s->shdr_num;
++        s->note_offset = s->phdr_offset + sizeof(Elf64_Phdr) * s->phdr_num;
+     } else {
+-
+-        s->phdr_offset = sizeof(Elf32_Ehdr);
+-        s->shdr_offset = s->phdr_offset + sizeof(Elf32_Phdr) * s->phdr_num;
+-        s->note_offset = s->shdr_offset + sizeof(Elf32_Shdr) * s->shdr_num;
+-        s->memory_offset = s->note_offset + s->note_size;
++        s->shdr_offset = sizeof(Elf32_Ehdr);
++        s->phdr_offset = s->shdr_offset + sizeof(Elf32_Shdr) * s->shdr_num;
++        s->note_offset = s->phdr_offset + sizeof(Elf32_Phdr) * s->phdr_num;
+     }
+ 
+     return;
+-- 
+2.37.3
+

SOURCES/kvm-dump-fix-kdump-to-work-over-non-aligned-blocks.patch

@@ -0,0 +1,173 @@
+From deaf4e0f5e90d227b7b9f3e5d1dff7fd0bc0206a Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?= <marcandre.lureau@redhat.com>
+Date: Mon, 5 Sep 2022 16:06:21 +0400
+Subject: [PATCH 31/42] dump: fix kdump to work over non-aligned blocks
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [31/41] b307bdce4a4791fc30160fa2a1678bd238f2432e
+
+Rewrite get_next_page() to work over non-aligned blocks. When it
+encounters non aligned addresses, it will try to fill a page provided by
+the caller.
+
+This solves a kdump crash with "tpm-crb-cmd" RAM memory region,
+qemu-kvm: ../dump/dump.c:1162: _Bool get_next_page(GuestPhysBlock **,
+uint64_t *, uint8_t **, DumpState *): Assertion `(block->target_start &
+~target_page_mask) == 0' failed.
+
+because:
+guest_phys_block_add_section: target_start=00000000fed40080 target_end=00000000fed41000: added (count: 4)
+
+Fixes:
+https://bugzilla.redhat.com/show_bug.cgi?id=2120480
+
+Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Acked-by: David Hildenbrand <david@redhat.com>
+(cherry picked from commit 94d788408d2d5a6474c99b2c9cf06913b9db7c58)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 79 +++++++++++++++++++++++++++++++++++++----------------
+ 1 file changed, 56 insertions(+), 23 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index 1c49232390..88177fa886 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -1117,50 +1117,81 @@ static uint64_t dump_pfn_to_paddr(DumpState *s, uint64_t pfn)
+ }
+ 
+ /*
+- * exam every page and return the page frame number and the address of the page.
+- * bufptr can be NULL. note: the blocks here is supposed to reflect guest-phys
+- * blocks, so block->target_start and block->target_end should be interal
+- * multiples of the target page size.
++ * Return the page frame number and the page content in *bufptr. bufptr can be
++ * NULL. If not NULL, *bufptr must contains a target page size of pre-allocated
++ * memory. This is not necessarily the memory returned.
+  */
+ static bool get_next_page(GuestPhysBlock **blockptr, uint64_t *pfnptr,
+                           uint8_t **bufptr, DumpState *s)
+ {
+     GuestPhysBlock *block = *blockptr;
+-    hwaddr addr, target_page_mask = ~((hwaddr)s->dump_info.page_size - 1);
+-    uint8_t *buf;
++    uint32_t page_size = s->dump_info.page_size;
++    uint8_t *buf = NULL, *hbuf;
++    hwaddr addr;
+ 
+     /* block == NULL means the start of the iteration */
+     if (!block) {
+         block = QTAILQ_FIRST(&s->guest_phys_blocks.head);
+         *blockptr = block;
+         addr = block->target_start;
++        *pfnptr = dump_paddr_to_pfn(s, addr);
+     } else {
+-        addr = dump_pfn_to_paddr(s, *pfnptr + 1);
++        *pfnptr += 1;
++        addr = dump_pfn_to_paddr(s, *pfnptr);
+     }
+     assert(block != NULL);
+ 
+-    if ((addr >= block->target_start) &&
+-        (addr + s->dump_info.page_size <= block->target_end)) {
+-        buf = block->host_addr + (addr - block->target_start);
+-    } else {
+-        /* the next page is in the next block */
+-        block = QTAILQ_NEXT(block, next);
+-        *blockptr = block;
+-        if (!block) {
+-            return false;
++    while (1) {
++        if (addr >= block->target_start && addr < block->target_end) {
++            size_t n = MIN(block->target_end - addr, page_size - addr % page_size);
++            hbuf = block->host_addr + (addr - block->target_start);
++            if (!buf) {
++                if (n == page_size) {
++                    /* this is a whole target page, go for it */
++                    assert(addr % page_size == 0);
++                    buf = hbuf;
++                    break;
++                } else if (bufptr) {
++                    assert(*bufptr);
++                    buf = *bufptr;
++                    memset(buf, 0, page_size);
++                } else {
++                    return true;
++                }
++            }
++
++            memcpy(buf + addr % page_size, hbuf, n);
++            addr += n;
++            if (addr % page_size == 0) {
++                /* we filled up the page */
++                break;
++            }
++        } else {
++            /* the next page is in the next block */
++            *blockptr = block = QTAILQ_NEXT(block, next);
++            if (!block) {
++                break;
++            }
++
++            addr = block->target_start;
++            /* are we still in the same page? */
++            if (dump_paddr_to_pfn(s, addr) != *pfnptr) {
++                if (buf) {
++                    /* no, but we already filled something earlier, return it */
++                    break;
++                } else {
++                    /* else continue from there */
++                    *pfnptr = dump_paddr_to_pfn(s, addr);
++                }
++            }
+         }
+-        addr = block->target_start;
+-        buf = block->host_addr;
+     }
+ 
+-    assert((block->target_start & ~target_page_mask) == 0);
+-    assert((block->target_end & ~target_page_mask) == 0);
+-    *pfnptr = dump_paddr_to_pfn(s, addr);
+     if (bufptr) {
+         *bufptr = buf;
+     }
+ 
+-    return true;
++    return buf != NULL;
+ }
+ 
+ static void write_dump_bitmap(DumpState *s, Error **errp)
+@@ -1306,6 +1337,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
+     uint8_t *buf;
+     GuestPhysBlock *block_iter = NULL;
+     uint64_t pfn_iter;
++    g_autofree uint8_t *page = NULL;
+ 
+     /* get offset of page_desc and page_data in dump file */
+     offset_desc = s->offset_page;
+@@ -1341,12 +1373,13 @@ static void write_dump_pages(DumpState *s, Error **errp)
+     }
+ 
+     offset_data += s->dump_info.page_size;
++    page = g_malloc(s->dump_info.page_size);
+ 
+     /*
+      * dump memory to vmcore page by page. zero page will all be resided in the
+      * first page of page section
+      */
+-    while (get_next_page(&block_iter, &pfn_iter, &buf, s)) {
++    for (buf = page; get_next_page(&block_iter, &pfn_iter, &buf, s); buf = page) {
+         /* check zero page */
+         if (is_zero_page(buf, s->dump_info.page_size)) {
+             ret = write_cache(&page_desc, &pd_zero, sizeof(PageDescriptor),
+-- 
+2.37.3
+

SOURCES/kvm-dump-simplify-a-bit-kdump-get_next_page.patch

@@ -0,0 +1,75 @@
+From bb55fde4d8ca587e2ef52ce58a0c22e4d66a08dc Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?= <marcandre.lureau@redhat.com>
+Date: Thu, 25 Aug 2022 12:40:12 +0400
+Subject: [PATCH 30/42] dump: simplify a bit kdump get_next_page()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [30/41] 417ac19fa96036e0242f40121ac6e87a9f3f70ba
+
+This should be functionally equivalent, but slightly easier to read,
+with simplified paths and checks at the end of the function.
+
+The following patch is a major rewrite to get rid of the assert().
+
+Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+Reviewed-by: David Hildenbrand <david@redhat.com>
+(cherry picked from commit 08df343874fcddd260021a04ce3c5a34f2c48164)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ dump/dump.c | 21 ++++++++-------------
+ 1 file changed, 8 insertions(+), 13 deletions(-)
+
+diff --git a/dump/dump.c b/dump/dump.c
+index c2c1341ad7..1c49232390 100644
+--- a/dump/dump.c
++++ b/dump/dump.c
+@@ -1133,17 +1133,11 @@ static bool get_next_page(GuestPhysBlock **blockptr, uint64_t *pfnptr,
+     if (!block) {
+         block = QTAILQ_FIRST(&s->guest_phys_blocks.head);
+         *blockptr = block;
+-        assert((block->target_start & ~target_page_mask) == 0);
+-        assert((block->target_end & ~target_page_mask) == 0);
+-        *pfnptr = dump_paddr_to_pfn(s, block->target_start);
+-        if (bufptr) {
+-            *bufptr = block->host_addr;
+-        }
+-        return true;
++        addr = block->target_start;
++    } else {
++        addr = dump_pfn_to_paddr(s, *pfnptr + 1);
+     }
+-
+-    *pfnptr = *pfnptr + 1;
+-    addr = dump_pfn_to_paddr(s, *pfnptr);
++    assert(block != NULL);
+ 
+     if ((addr >= block->target_start) &&
+         (addr + s->dump_info.page_size <= block->target_end)) {
+@@ -1155,12 +1149,13 @@ static bool get_next_page(GuestPhysBlock **blockptr, uint64_t *pfnptr,
+         if (!block) {
+             return false;
+         }
+-        assert((block->target_start & ~target_page_mask) == 0);
+-        assert((block->target_end & ~target_page_mask) == 0);
+-        *pfnptr = dump_paddr_to_pfn(s, block->target_start);
++        addr = block->target_start;
+         buf = block->host_addr;
+     }
+ 
++    assert((block->target_start & ~target_page_mask) == 0);
++    assert((block->target_end & ~target_page_mask) == 0);
++    *pfnptr = dump_paddr_to_pfn(s, addr);
+     if (bufptr) {
+         *bufptr = buf;
+     }
+-- 
+2.37.3
+

SOURCES/kvm-edu-add-smp_mb__after_rmw.patch

@@ -0,0 +1,61 @@
+From 7693449b235bbab6d32a1b87fa1d0e101c786f3b Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Thu, 9 Mar 2023 08:11:14 -0500
+Subject: [PATCH 05/13] edu: add smp_mb__after_rmw()
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw()
+RH-Bugzilla: 2168472
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Eric Auger <eric.auger@redhat.com>
+RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Commit: [5/10] 300901290e08b253b1278eedc39cd07c1e202b96
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472
+
+commit 2482aeea4195ad84cf3d4e5b15b28ec5b420ed5a
+Author: Paolo Bonzini <pbonzini@redhat.com>
+Date:   Thu Mar 2 11:16:13 2023 +0100
+
+    edu: add smp_mb__after_rmw()
+
+    Ensure ordering between clearing the COMPUTING flag and checking
+    IRQFACT, and between setting the IRQFACT flag and checking
+    COMPUTING.  This ensures that no wakeups are lost.
+
+    Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+    Reviewed-by: David Hildenbrand <david@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ hw/misc/edu.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+diff --git a/hw/misc/edu.c b/hw/misc/edu.c
+index e935c418d4..a1f8bc77e7 100644
+--- a/hw/misc/edu.c
++++ b/hw/misc/edu.c
+@@ -267,6 +267,8 @@ static void edu_mmio_write(void *opaque, hwaddr addr, uint64_t val,
+     case 0x20:
+         if (val & EDU_STATUS_IRQFACT) {
+             qatomic_or(&edu->status, EDU_STATUS_IRQFACT);
++            /* Order check of the COMPUTING flag after setting IRQFACT.  */
++            smp_mb__after_rmw();
+         } else {
+             qatomic_and(&edu->status, ~EDU_STATUS_IRQFACT);
+         }
+@@ -349,6 +351,9 @@ static void *edu_fact_thread(void *opaque)
+         qemu_mutex_unlock(&edu->thr_mutex);
+         qatomic_and(&edu->status, ~EDU_STATUS_COMPUTING);
+ 
++        /* Clear COMPUTING flag before checking IRQFACT.  */
++        smp_mb__after_rmw();
++
+         if (qatomic_read(&edu->status) & EDU_STATUS_IRQFACT) {
+             qemu_mutex_lock_iothread();
+             edu_raise_irq(edu, FACT_IRQ);
+-- 
+2.37.3
+

SOURCES/kvm-glib-compat-Introduce-g_memdup2-wrapper.patch

@@ -0,0 +1,105 @@
+From 939c75ab92ac608893cad0e46f55527950518a57 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Tue, 5 Mar 2024 11:36:15 -0500
+Subject: [PATCH 1/3] glib-compat: Introduce g_memdup2() wrapper
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 353: ui/clipboard: mark type as not available when there is no data
+RH-Jira: RHEL-19628
+RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+RH-Acked-by: Gerd Hoffmann <None>
+RH-Commit: [1/2] f401c63303ef558bfcbb36e4c8fcc8bf2b1c3eb4 (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+JIRA: https://issues.redhat.com/browse/RHEL-19628
+CVE: CVE-2023-6683
+Upstream: Merged
+
+commit 2c674fada72079583a3f2cc1790b16a0259c4fa0
+Author: Philippe Mathieu-Daudé <philmd@linaro.org>
+Date:   Fri Sep 3 19:44:44 2021 +0200
+
+    glib-compat: Introduce g_memdup2() wrapper
+    When experimenting raising GLIB_VERSION_MIN_REQUIRED to 2.68
+    (Fedora 34 provides GLib 2.68.1) we get:
+
+      hw/virtio/virtio-crypto.c:245:24: error: 'g_memdup' is deprecated: Use 'g_memdup2' instead [-Werror,-Wdeprecated-declarations]
+      ...
+
+    g_memdup() has been updated by g_memdup2() to fix eventual security
+    issues (size argument is 32-bit and could be truncated / wrapping).
+    GLib recommends to copy their static inline version of g_memdup2():
+    https://discourse.gnome.org/t/port-your-module-from-g-memdup-to-g-memdup2-now/5538
+
+    Our glib-compat.h provides a comment explaining how to deal with
+    these deprecated declarations (see commit e71e8cc0355
+    "glib: enforce the minimum required version and warn about old APIs").
+
+    Following this comment suggestion, implement the g_memdup2_qemu()
+    wrapper to g_memdup2(), and use the safer equivalent inlined when
+    we are using pre-2.68 GLib.
+
+    Reported-by: Eric Blake <eblake@redhat.com>
+    Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
+    Reviewed-by: Eric Blake <eblake@redhat.com>
+    Message-Id: <20210903174510.751630-3-philmd@redhat.com>
+    Signed-off-by: Laurent Vivier <laurent@vivier.eu>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ include/glib-compat.h | 37 +++++++++++++++++++++++++++++++++++++
+ 1 file changed, 37 insertions(+)
+
+diff --git a/include/glib-compat.h b/include/glib-compat.h
+index 9e95c888f5..8d01a8c01f 100644
+--- a/include/glib-compat.h
++++ b/include/glib-compat.h
+@@ -68,6 +68,43 @@
+  * without generating warnings.
+  */
+ 
++/*
++ * g_memdup2_qemu:
++ * @mem: (nullable): the memory to copy.
++ * @byte_size: the number of bytes to copy.
++ *
++ * Allocates @byte_size bytes of memory, and copies @byte_size bytes into it
++ * from @mem. If @mem is %NULL it returns %NULL.
++ *
++ * This replaces g_memdup(), which was prone to integer overflows when
++ * converting the argument from a #gsize to a #guint.
++ *
++ * This static inline version is a backport of the new public API from
++ * GLib 2.68, kept internal to GLib for backport to older stable releases.
++ * See https://gitlab.gnome.org/GNOME/glib/-/issues/2319.
++ *
++ * Returns: (nullable): a pointer to the newly-allocated copy of the memory,
++ *          or %NULL if @mem is %NULL.
++ */
++static inline gpointer g_memdup2_qemu(gconstpointer mem, gsize byte_size)
++{
++#if GLIB_CHECK_VERSION(2, 68, 0)
++    return g_memdup2(mem, byte_size);
++#else
++    gpointer new_mem;
++
++    if (mem && byte_size != 0) {
++        new_mem = g_malloc(byte_size);
++        memcpy(new_mem, mem, byte_size);
++    } else {
++        new_mem = NULL;
++    }
++
++    return new_mem;
++#endif
++}
++#define g_memdup2(m, s) g_memdup2_qemu(m, s)
++
+ #if defined(G_OS_UNIX)
+ /*
+  * Note: The fallback implementation is not MT-safe, and it returns a copy of
+-- 
+2.41.0
+

SOURCES/kvm-hw-acpi-Add-ospm_status-hook-implementation-for-acpi.patch

@@ -0,0 +1,81 @@
+From edead46187b1e55ad5e238332780aef19f1bc214 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Wed, 9 Nov 2022 18:41:18 -0500
+Subject: [PATCH 1/2] hw/acpi: Add ospm_status hook implementation for acpi-ged
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 228: qemu-kvm: backport some aarch64 fixes
+RH-Bugzilla: 2132609
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
+RH-Acked-by: Eric Auger <eric.auger@redhat.com>
+RH-Acked-by: Gavin Shan <gshan@redhat.com>
+RH-Commit: [1/2] 99730b1a27666ca745dc28d90751c938d43f1682 (jmaloy/qemu-kvm)
+
+BZ: https://bugzilla.redhat.com/show_bug.cgi?id=2132609
+Upstream: Merged
+
+commit d4424bebceaa8ffbc23060ce45e52a9bb817e3c9
+Author: Keqian Zhu <zhukeqian1@huawei.com>
+Date:   Tue Aug 16 17:49:57 2022 +0800
+
+    hw/acpi: Add ospm_status hook implementation for acpi-ged
+
+    Setup an ARM virtual machine of machine virt and execute qmp "query-acpi-ospm-status"
+    causes segmentation fault with following dumpstack:
+     #1  0x0000aaaaab64235c in qmp_query_acpi_ospm_status (errp=errp@entry=0xfffffffff030) at ../monitor/qmp-cmds.c:312
+     #2  0x0000aaaaabfc4e20 in qmp_marshal_query_acpi_ospm_status (args=<optimized out>, ret=0xffffea4ffe90, errp=0xffffea4ffe88) at qapi/qapi-commands-acpi.c:63
+     #3  0x0000aaaaabff8ba0 in do_qmp_dispatch_bh (opaque=0xffffea4ffe98) at ../qapi/qmp-dispatch.c:128
+     #4  0x0000aaaaac02e594 in aio_bh_call (bh=0xffffe0004d80) at ../util/async.c:150
+     #5  aio_bh_poll (ctx=ctx@entry=0xaaaaad0f6040) at ../util/async.c:178
+     #6  0x0000aaaaac00bd40 in aio_dispatch (ctx=ctx@entry=0xaaaaad0f6040) at ../util/aio-posix.c:421
+     #7  0x0000aaaaac02e010 in aio_ctx_dispatch (source=0xaaaaad0f6040, callback=<optimized out>, user_data=<optimized out>) at ../util/async.c:320
+     #8  0x0000fffff76f6884 in g_main_context_dispatch () at /usr/lib64/libglib-2.0.so.0
+     #9  0x0000aaaaac0452d4 in glib_pollfds_poll () at ../util/main-loop.c:297
+     #10 os_host_main_loop_wait (timeout=0) at ../util/main-loop.c:320
+     #11 main_loop_wait (nonblocking=nonblocking@entry=0) at ../util/main-loop.c:596
+     #12 0x0000aaaaab5c9e50 in qemu_main_loop () at ../softmmu/runstate.c:734
+     #13 0x0000aaaaab185370 in qemu_main (argc=argc@entry=47, argv=argv@entry=0xfffffffff518, envp=envp@entry=0x0) at ../softmmu/main.c:38
+     #14 0x0000aaaaab16f99c in main (argc=47, argv=0xfffffffff518) at ../softmmu/main.c:47
+
+    Fixes: ebb62075021a ("hw/acpi: Add ACPI Generic Event Device Support")
+    Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com>
+    Reviewed-by: Igor Mammedov <imammedo@redhat.com>
+    Message-id: 20220816094957.31700-1-zhukeqian1@huawei.com
+    Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+
+(cherry picked from commit d4424bebceaa8ffbc23060ce45e52a9bb817e3c9)
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/acpi/generic_event_device.c | 8 ++++++++
+ 1 file changed, 8 insertions(+)
+
+diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
+index e28457a7d1..a3d31631fe 100644
+--- a/hw/acpi/generic_event_device.c
++++ b/hw/acpi/generic_event_device.c
+@@ -267,6 +267,13 @@ static void acpi_ged_unplug_cb(HotplugHandler *hotplug_dev,
+     }
+ }
+ 
++static void acpi_ged_ospm_status(AcpiDeviceIf *adev, ACPIOSTInfoList ***list)
++{
++    AcpiGedState *s = ACPI_GED(adev);
++
++    acpi_memory_ospm_status(&s->memhp_state, list);
++}
++
+ static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
+ {
+     AcpiGedState *s = ACPI_GED(adev);
+@@ -409,6 +416,7 @@ static void acpi_ged_class_init(ObjectClass *class, void *data)
+     hc->unplug_request = acpi_ged_unplug_request_cb;
+     hc->unplug = acpi_ged_unplug_cb;
+ 
++    adevc->ospm_status = acpi_ged_ospm_status;
+     adevc->send_event = acpi_ged_send_event;
+ }
+ 
+-- 
+2.37.3
+

SOURCES/kvm-hw-arm-virt-Do-not-load-efi-virtio.rom-for-all-virti.patch

@@ -0,0 +1,119 @@
+From 4f6f881de10e31cac4636d5fde4b7ed4c8affadb Mon Sep 17 00:00:00 2001
+From: Eric Auger <eric.auger@redhat.com>
+Date: Thu, 4 Jan 2024 12:02:31 +0100
+Subject: [PATCH 3/3] hw/arm/virt: Do not load efi-virtio.rom for all
+ virtio-net-pci variants
+
+RH-Author: Eric Auger <eric.auger@redhat.com>
+RH-MergeRequest: 344: hw/arm/virt: Do not load efi-virtio.rom for any virtio-net-pci variants
+RH-Jira: RHEL-14870
+RH-Acked-by: Gerd Hoffmann <None>
+RH-Acked-by: Sebastian Ott <None>
+RH-Commit: [1/1] ffeaa78ad0a1cff5b49009dfb32d25e5cadc0e05
+
+Upstream: RHEL-only
+Brew: http://brewweb.engineering.redhat.com/brew/taskinfo?taskID=5785640
+
+Currently arm_rhel_compat just sets the romfile to "" for
+virtio-net-pci and not for transitional and non transitional
+variants. However, on aarch64 RHEL, efi-virtio.rom is not
+shipped so transitional and non-transitional variants cannot
+be used and the following error is obeserved:
+
+"Could not open option rom 'efi-virtio.rom': No such file or directory"
+
+In practice, we do not need any rom file for those virtio-net-pci
+variants either because edk2 already brings the full functionality.
+
+So let's change the applied compat to cover all the variants. While
+at it also change the way arm_rhel_compat is applied. Instead of
+applying it from the latest _virt_options(), which is error prone
+when upgrading the machine type, let's apply it before calling
+*virt_options in the non abstract machine class. That way the setting
+will apply to any machine type without any need to add it in any
+future machine types.
+
+We don't really care keeping non void romfiles for transitional and
+non transitional devices on previous machine types because this
+was not working anyway.
+
+Signed-off-by: Eric Auger <eric.auger@redhat.com>
+---
+ hw/arm/virt.c | 42 ++++++++++++++++++++++++++++--------------
+ 1 file changed, 28 insertions(+), 14 deletions(-)
+
+diff --git a/hw/arm/virt.c b/hw/arm/virt.c
+index dbf0a6d62f..46c72a9611 100644
+--- a/hw/arm/virt.c
++++ b/hw/arm/virt.c
+@@ -108,11 +108,39 @@
+     DEFINE_VIRT_MACHINE_LATEST(major, minor, false)
+ #endif /* disabled for RHEL */
+ 
++/*
++ * This variable is for changes to properties that are RHEL specific,
++ * different to the current upstream and to be applied to the latest
++ * machine type. They may be overriden by older machine compats.
++ *
++ * virtio-net-pci variant romfiles are not needed because edk2 does
++ * fully support the pxe boot. Besides virtio romfiles are not shipped
++ * on rhel/aarch64.
++ */
++GlobalProperty arm_rhel_compat[] = {
++    {"virtio-net-pci", "romfile", "" },
++    {"virtio-net-pci-transitional", "romfile", "" },
++    {"virtio-net-pci-non-transitional", "romfile", "" },
++};
++const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
++
++/*
++ * This cannot be called from the rhel_virt_class_init() because
++ * TYPE_RHEL_MACHINE is abstract and mc->compat_props g_ptr_array_new()
++ * only is called on virt-rhelm.n.s non abstract class init.
++ */
++static void arm_rhel_compat_set(MachineClass *mc)
++{
++    compat_props_add(mc->compat_props, arm_rhel_compat,
++                     arm_rhel_compat_len);
++}
++
+ #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);                           \
++        arm_rhel_compat_set(mc);                                        \
+         rhel##m##n##s##_virt_options(mc);                               \
+         mc->desc = "RHEL " # m "." # n "." # s " ARM Virtual Machine";  \
+         if (latest) {                                                   \
+@@ -136,19 +164,6 @@
+ #define DEFINE_RHEL_MACHINE(major, minor, subminor)             \
+     DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, false)
+ 
+-/* This variable is for changes to properties that are RHEL specific,
+- * different to the current upstream and to be applied to the latest
+- * machine type.
+- */
+-GlobalProperty arm_rhel_compat[] = {
+-    {
+-        .driver   = "virtio-net-pci",
+-        .property = "romfile",
+-        .value    = "",
+-    },
+-};
+-const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
+-
+ /* Number of external interrupt lines to configure the GIC with */
+ #define NUM_IRQS 256
+ 
+@@ -3240,7 +3255,6 @@ type_init(rhel_machine_init);
+ 
+ static void rhel860_virt_options(MachineClass *mc)
+ {
+-    compat_props_add(mc->compat_props, arm_rhel_compat, arm_rhel_compat_len);
+ }
+ DEFINE_RHEL_MACHINE_AS_LATEST(8, 6, 0)
+ 
+-- 
+2.41.0
+

SOURCES/kvm-hw-display-qxl-Assert-memory-slot-fits-in-preallocat.patch

@@ -0,0 +1,52 @@
+From 100f33ff8a1d55986e43b99ba8726abc29ee8d26 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Mon, 5 Dec 2022 15:32:55 -0500
+Subject: [PATCH 5/5] hw/display/qxl: Assert memory slot fits in preallocated
+ MemoryRegion
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 240: hw/display/qxl: Have qxl_log_command Return early if no log_cmd handler
+RH-Bugzilla: 2148545
+RH-Acked-by: Gerd Hoffmann <kraxel@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+RH-Commit: [5/5] f809ce48e7989dd6547b7c8bf1a5efc3fdcacbac (jmaloy/jons-qemu-kvm)
+
+BZ: https://bugzilla.redhat.com/show_bug.cgi?id=2148545
+CVE: CVE-2022-4144
+Upstream: Merged
+
+commit 86fdb0582c653a9824183679403a85f588260d62
+Author: Philippe Mathieu-Daudé <philmd@linaro.org>
+Date:   Mon Nov 28 21:27:41 2022 +0100
+
+    hw/display/qxl: Assert memory slot fits in preallocated MemoryRegion
+
+    Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+    Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Message-Id: <20221128202741.4945-6-philmd@linaro.org>
+
+(cherry picked from commit 86fdb0582c653a9824183679403a85f588260d62)
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/display/qxl.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/hw/display/qxl.c b/hw/display/qxl.c
+index 2a4b2d4158..bcd9e8716a 100644
+--- a/hw/display/qxl.c
++++ b/hw/display/qxl.c
+@@ -1372,6 +1372,7 @@ static int qxl_add_memslot(PCIQXLDevice *d, uint32_t slot_id, uint64_t delta,
+         qxl_set_guest_bug(d, "%s: pci_region = %d", __func__, pci_region);
+         return 1;
+     }
++    assert(guest_end - pci_start <= memory_region_size(mr));
+ 
+     virt_start = (intptr_t)memory_region_get_ram_ptr(mr);
+     memslot.slot_id = slot_id;
+-- 
+2.37.3
+

SOURCES/kvm-hw-display-qxl-Avoid-buffer-overrun-in-qxl_phys2virt.patch

@@ -0,0 +1,130 @@
+From 4e1bfbe3a0a113fe3cf39336a9d7da4e8c2a21ea Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Mon, 5 Dec 2022 15:32:55 -0500
+Subject: [PATCH 4/5] hw/display/qxl: Avoid buffer overrun in qxl_phys2virt
+ (CVE-2022-4144)
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 240: hw/display/qxl: Have qxl_log_command Return early if no log_cmd handler
+RH-Bugzilla: 2148545
+RH-Acked-by: Gerd Hoffmann <kraxel@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+RH-Commit: [4/5] afe53f8d9b31c6fd8211fe172173151f3255e67c (jmaloy/jons-qemu-kvm)
+
+BZ: https://bugzilla.redhat.com/show_bug.cgi?id=2148545
+CVE: CVE-2022-4144
+Upstream: Merged
+
+commit 6dbbf055148c6f1b7d8a3251a65bd6f3d1e1f622
+Author: Philippe Mathieu-Daudé <philmd@linaro.org>
+Date:   Mon Nov 28 21:27:40 2022 +0100
+
+    hw/display/qxl: Avoid buffer overrun in qxl_phys2virt (CVE-2022-4144)
+
+    Have qxl_get_check_slot_offset() return false if the requested
+    buffer size does not fit within the slot memory region.
+
+    Similarly qxl_phys2virt() now returns NULL in such case, and
+    qxl_dirty_one_surface() aborts.
+
+    This avoids buffer overrun in the host pointer returned by
+    memory_region_get_ram_ptr().
+
+    Fixes: CVE-2022-4144 (out-of-bounds read)
+    Reported-by: Wenxu Yin (@awxylitol)
+    Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1336
+    Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+    Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Message-Id: <20221128202741.4945-5-philmd@linaro.org>
+
+(cherry picked from commit 6dbbf055148c6f1b7d8a3251a65bd6f3d1e1f622)
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/display/qxl.c | 27 +++++++++++++++++++++++----
+ hw/display/qxl.h |  2 +-
+ 2 files changed, 24 insertions(+), 5 deletions(-)
+
+diff --git a/hw/display/qxl.c b/hw/display/qxl.c
+index aa9065183e..2a4b2d4158 100644
+--- a/hw/display/qxl.c
++++ b/hw/display/qxl.c
+@@ -1412,11 +1412,13 @@ static void qxl_reset_surfaces(PCIQXLDevice *d)
+ 
+ /* can be also called from spice server thread context */
+ static bool qxl_get_check_slot_offset(PCIQXLDevice *qxl, QXLPHYSICAL pqxl,
+-                                      uint32_t *s, uint64_t *o)
++                                      uint32_t *s, uint64_t *o,
++                                      size_t size_requested)
+ {
+     uint64_t phys   = le64_to_cpu(pqxl);
+     uint32_t slot   = (phys >> (64 -  8)) & 0xff;
+     uint64_t offset = phys & 0xffffffffffff;
++    uint64_t size_available;
+ 
+     if (slot >= NUM_MEMSLOTS) {
+         qxl_set_guest_bug(qxl, "slot too large %d >= %d", slot,
+@@ -1440,6 +1442,23 @@ static bool qxl_get_check_slot_offset(PCIQXLDevice *qxl, QXLPHYSICAL pqxl,
+                           slot, offset, qxl->guest_slots[slot].size);
+         return false;
+     }
++    size_available = memory_region_size(qxl->guest_slots[slot].mr);
++    if (qxl->guest_slots[slot].offset + offset >= size_available) {
++        qxl_set_guest_bug(qxl,
++                          "slot %d offset %"PRIu64" > region size %"PRIu64"\n",
++                          slot, qxl->guest_slots[slot].offset + offset,
++                          size_available);
++        return false;
++    }
++    size_available -= qxl->guest_slots[slot].offset + offset;
++    if (size_requested > size_available) {
++        qxl_set_guest_bug(qxl,
++                          "slot %d offset %"PRIu64" size %zu: "
++                          "overrun by %"PRIu64" bytes\n",
++                          slot, offset, size_requested,
++                          size_requested - size_available);
++        return false;
++    }
+ 
+     *s = slot;
+     *o = offset;
+@@ -1459,7 +1478,7 @@ void *qxl_phys2virt(PCIQXLDevice *qxl, QXLPHYSICAL pqxl, int group_id,
+         offset = le64_to_cpu(pqxl) & 0xffffffffffff;
+         return (void *)(intptr_t)offset;
+     case MEMSLOT_GROUP_GUEST:
+-        if (!qxl_get_check_slot_offset(qxl, pqxl, &slot, &offset)) {
++        if (!qxl_get_check_slot_offset(qxl, pqxl, &slot, &offset, size)) {
+             return NULL;
+         }
+         ptr = memory_region_get_ram_ptr(qxl->guest_slots[slot].mr);
+@@ -1925,9 +1944,9 @@ static void qxl_dirty_one_surface(PCIQXLDevice *qxl, QXLPHYSICAL pqxl,
+     uint32_t slot;
+     bool rc;
+ 
+-    rc = qxl_get_check_slot_offset(qxl, pqxl, &slot, &offset);
+-    assert(rc == true);
+     size = (uint64_t)height * abs(stride);
++    rc = qxl_get_check_slot_offset(qxl, pqxl, &slot, &offset, size);
++    assert(rc == true);
+     trace_qxl_surfaces_dirty(qxl->id, offset, size);
+     qxl_set_dirty(qxl->guest_slots[slot].mr,
+                   qxl->guest_slots[slot].offset + offset,
+diff --git a/hw/display/qxl.h b/hw/display/qxl.h
+index c784315daa..89ca832cf9 100644
+--- a/hw/display/qxl.h
++++ b/hw/display/qxl.h
+@@ -157,7 +157,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(PCIQXLDevice, PCI_QXL)
+  *
+  * Returns a host pointer to a buffer placed at offset @phys within the
+  * active slot @group_id of the PCI VGA RAM memory region associated with
+- * the @qxl device. If the slot is inactive, or the offset is out
++ * the @qxl device. If the slot is inactive, or the offset + size are out
+  * of the memory region, returns NULL.
+  *
+  * Use with care; by the time this function returns, the returned pointer is
+-- 
+2.37.3
+

SOURCES/kvm-hw-display-qxl-Document-qxl_phys2virt.patch

@@ -0,0 +1,70 @@
+From 068c531fb968ec04509b85f524d0745e6acf5449 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Mon, 5 Dec 2022 15:32:55 -0500
+Subject: [PATCH 2/5] hw/display/qxl: Document qxl_phys2virt()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 240: hw/display/qxl: Have qxl_log_command Return early if no log_cmd handler
+RH-Bugzilla: 2148545
+RH-Acked-by: Gerd Hoffmann <kraxel@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+RH-Commit: [2/5] f84c0b379022c527fc2508a242443d86454944c0 (jmaloy/jons-qemu-kvm)
+
+BZ: https://bugzilla.redhat.com/show_bug.cgi?id=2148545
+CVE: CVE-2022-4144
+Upstream: Merged
+
+commit b1901de83a9456cde26fc755f71ca2b7b3ef50fc
+Author: Philippe Mathieu-Daudé <philmd@linaro.org>
+Date:   Mon Nov 28 21:27:38 2022 +0100
+
+    hw/display/qxl: Document qxl_phys2virt()
+
+    Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+    Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+    Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Message-Id: <20221128202741.4945-3-philmd@linaro.org>
+
+(cherry picked from commit b1901de83a9456cde26fc755f71ca2b7b3ef50fc)
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/display/qxl.h | 19 +++++++++++++++++++
+ 1 file changed, 19 insertions(+)
+
+diff --git a/hw/display/qxl.h b/hw/display/qxl.h
+index 30d21f4d0b..c938f88a2f 100644
+--- a/hw/display/qxl.h
++++ b/hw/display/qxl.h
+@@ -147,6 +147,25 @@ OBJECT_DECLARE_SIMPLE_TYPE(PCIQXLDevice, PCI_QXL)
+ #define QXL_DEFAULT_REVISION (QXL_REVISION_STABLE_V12 + 1)
+ 
+ /* qxl.c */
++/**
++ * qxl_phys2virt: Get a pointer within a PCI VRAM memory region.
++ *
++ * @qxl: QXL device
++ * @phys: physical offset of buffer within the VRAM
++ * @group_id: memory slot group
++ *
++ * Returns a host pointer to a buffer placed at offset @phys within the
++ * active slot @group_id of the PCI VGA RAM memory region associated with
++ * the @qxl device. If the slot is inactive, or the offset is out
++ * of the memory region, returns NULL.
++ *
++ * Use with care; by the time this function returns, the returned pointer is
++ * not protected by RCU anymore.  If the caller is not within an RCU critical
++ * section and does not hold the iothread lock, it must have other means of
++ * protecting the pointer, such as a reference to the region that includes
++ * the incoming ram_addr_t.
++ *
++ */
+ void *qxl_phys2virt(PCIQXLDevice *qxl, QXLPHYSICAL phys, int group_id);
+ void qxl_set_guest_bug(PCIQXLDevice *qxl, const char *msg, ...)
+     GCC_FMT_ATTR(2, 3);
+-- 
+2.37.3
+

SOURCES/kvm-hw-display-qxl-Have-qxl_log_command-Return-early-if-.patch

@@ -0,0 +1,74 @@
+From 5ec8d909d40fa04ef2c3572e01509a1866786070 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Mon, 5 Dec 2022 15:32:55 -0500
+Subject: [PATCH 1/5] hw/display/qxl: Have qxl_log_command Return early if no
+ log_cmd handler
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 240: hw/display/qxl: Have qxl_log_command Return early if no log_cmd handler
+RH-Bugzilla: 2148545
+RH-Acked-by: Gerd Hoffmann <kraxel@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+RH-Commit: [1/5] 33d94f40c46cccbc32d108d1035365917bf90356 (jmaloy/jons-qemu-kvm)
+
+BZ: https://bugzilla.redhat.com/show_bug.cgi?id=2148545
+CVE: CVE-2022-4144
+Upstream: Merged
+
+commit 61c34fc194b776ecadc39fb26b061331107e5599
+Author: Philippe Mathieu-Daudé <philmd@linaro.org>
+Date:   Mon Nov 28 21:27:37 2022 +0100
+
+    hw/display/qxl: Have qxl_log_command Return early if no log_cmd handler
+
+    Only 3 command types are logged: no need to call qxl_phys2virt()
+    for the other types. Using different cases will help to pass
+    different structure sizes to qxl_phys2virt() in a pair of commits.
+
+    Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+    Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+    Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Message-Id: <20221128202741.4945-2-philmd@linaro.org>
+
+(cherry picked from commit 61c34fc194b776ecadc39fb26b061331107e5599)
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/display/qxl-logger.c | 11 +++++++++++
+ 1 file changed, 11 insertions(+)
+
+diff --git a/hw/display/qxl-logger.c b/hw/display/qxl-logger.c
+index 68bfa47568..1bcf803db6 100644
+--- a/hw/display/qxl-logger.c
++++ b/hw/display/qxl-logger.c
+@@ -247,6 +247,16 @@ int qxl_log_command(PCIQXLDevice *qxl, const char *ring, QXLCommandExt *ext)
+             qxl_name(qxl_type, ext->cmd.type),
+             compat ? "(compat)" : "");
+ 
++    switch (ext->cmd.type) {
++    case QXL_CMD_DRAW:
++        break;
++    case QXL_CMD_SURFACE:
++        break;
++    case QXL_CMD_CURSOR:
++        break;
++    default:
++        goto out;
++    }
+     data = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id);
+     if (!data) {
+         return 1;
+@@ -269,6 +279,7 @@ int qxl_log_command(PCIQXLDevice *qxl, const char *ring, QXLCommandExt *ext)
+         qxl_log_cmd_cursor(qxl, data, ext->group_id);
+         break;
+     }
++out:
+     fprintf(stderr, "\n");
+     return 0;
+ }
+-- 
+2.37.3
+

SOURCES/kvm-hw-display-qxl-Pass-requested-buffer-size-to-qxl_phy.patch

@@ -0,0 +1,234 @@
+From 0e6bd3911c4971f575aac7e9cd726467b52fe544 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Mon, 5 Dec 2022 15:32:55 -0500
+Subject: [PATCH 3/5] hw/display/qxl: Pass requested buffer size to
+ qxl_phys2virt()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 240: hw/display/qxl: Have qxl_log_command Return early if no log_cmd handler
+RH-Bugzilla: 2148545
+RH-Acked-by: Gerd Hoffmann <kraxel@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Marc-André Lureau <marcandre.lureau@redhat.com>
+RH-Commit: [3/5] 8e362d67fe7fef9eb457cfb15d75b298fed725c3 (jmaloy/jons-qemu-kvm)
+
+BZ: https://bugzilla.redhat.com/show_bug.cgi?id=2148545
+CVE: CVE-2022-4144
+Upstream: Merged
+
+commit 8efec0ef8bbc1e75a7ebf6e325a35806ece9b39f
+Author: Philippe Mathieu-Daudé <philmd@linaro.org>
+Date:   Mon Nov 28 21:27:39 2022 +0100
+
+    hw/display/qxl: Pass requested buffer size to qxl_phys2virt()
+
+    Currently qxl_phys2virt() doesn't check for buffer overrun.
+    In order to do so in the next commit, pass the buffer size
+    as argument.
+
+    For QXLCursor in qxl_render_cursor() -> qxl_cursor() we
+    verify the size of the chunked data ahead, checking we can
+    access 'sizeof(QXLCursor) + chunk->data_size' bytes.
+    Since in the SPICE_CURSOR_TYPE_MONO case the cursor is
+    assumed to fit in one chunk, no change are required.
+    In SPICE_CURSOR_TYPE_ALPHA the ahead read is handled in
+    qxl_unpack_chunks().
+
+    Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+    Acked-by: Gerd Hoffmann <kraxel@redhat.com>
+    Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Message-Id: <20221128202741.4945-4-philmd@linaro.org>
+
+(cherry picked from commit 8efec0ef8bbc1e75a7ebf6e325a35806ece9b39f)
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/display/qxl-logger.c | 11 ++++++++---
+ hw/display/qxl-render.c | 20 ++++++++++++++++----
+ hw/display/qxl.c        | 14 +++++++++-----
+ hw/display/qxl.h        |  4 +++-
+ 4 files changed, 36 insertions(+), 13 deletions(-)
+
+diff --git a/hw/display/qxl-logger.c b/hw/display/qxl-logger.c
+index 1bcf803db6..35c38f6252 100644
+--- a/hw/display/qxl-logger.c
++++ b/hw/display/qxl-logger.c
+@@ -106,7 +106,7 @@ static int qxl_log_image(PCIQXLDevice *qxl, QXLPHYSICAL addr, int group_id)
+     QXLImage *image;
+     QXLImageDescriptor *desc;
+ 
+-    image = qxl_phys2virt(qxl, addr, group_id);
++    image = qxl_phys2virt(qxl, addr, group_id, sizeof(QXLImage));
+     if (!image) {
+         return 1;
+     }
+@@ -214,7 +214,8 @@ int qxl_log_cmd_cursor(PCIQXLDevice *qxl, QXLCursorCmd *cmd, int group_id)
+                 cmd->u.set.position.y,
+                 cmd->u.set.visible ? "yes" : "no",
+                 cmd->u.set.shape);
+-        cursor = qxl_phys2virt(qxl, cmd->u.set.shape, group_id);
++        cursor = qxl_phys2virt(qxl, cmd->u.set.shape, group_id,
++                               sizeof(QXLCursor));
+         if (!cursor) {
+             return 1;
+         }
+@@ -236,6 +237,7 @@ int qxl_log_command(PCIQXLDevice *qxl, const char *ring, QXLCommandExt *ext)
+ {
+     bool compat = ext->flags & QXL_COMMAND_FLAG_COMPAT;
+     void *data;
++    size_t datasz;
+     int ret;
+ 
+     if (!qxl->cmdlog) {
+@@ -249,15 +251,18 @@ int qxl_log_command(PCIQXLDevice *qxl, const char *ring, QXLCommandExt *ext)
+ 
+     switch (ext->cmd.type) {
+     case QXL_CMD_DRAW:
++        datasz = compat ? sizeof(QXLCompatDrawable) : sizeof(QXLDrawable);
+         break;
+     case QXL_CMD_SURFACE:
++        datasz = sizeof(QXLSurfaceCmd);
+         break;
+     case QXL_CMD_CURSOR:
++        datasz = sizeof(QXLCursorCmd);
+         break;
+     default:
+         goto out;
+     }
+-    data = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id);
++    data = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id, datasz);
+     if (!data) {
+         return 1;
+     }
+diff --git a/hw/display/qxl-render.c b/hw/display/qxl-render.c
+index ca217004bf..fcfd40c3ac 100644
+--- a/hw/display/qxl-render.c
++++ b/hw/display/qxl-render.c
+@@ -107,7 +107,9 @@ static void qxl_render_update_area_unlocked(PCIQXLDevice *qxl)
+         qxl->guest_primary.resized = 0;
+         qxl->guest_primary.data = qxl_phys2virt(qxl,
+                                                 qxl->guest_primary.surface.mem,
+-                                                MEMSLOT_GROUP_GUEST);
++                                                MEMSLOT_GROUP_GUEST,
++                                                qxl->guest_primary.abs_stride
++                                                * height);
+         if (!qxl->guest_primary.data) {
+             goto end;
+         }
+@@ -228,7 +230,8 @@ static void qxl_unpack_chunks(void *dest, size_t size, PCIQXLDevice *qxl,
+         if (offset == size) {
+             return;
+         }
+-        chunk = qxl_phys2virt(qxl, chunk->next_chunk, group_id);
++        chunk = qxl_phys2virt(qxl, chunk->next_chunk, group_id,
++                              sizeof(QXLDataChunk) + chunk->data_size);
+         if (!chunk) {
+             return;
+         }
+@@ -295,7 +298,8 @@ fail:
+ /* called from spice server thread context only */
+ int qxl_render_cursor(PCIQXLDevice *qxl, QXLCommandExt *ext)
+ {
+-    QXLCursorCmd *cmd = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id);
++    QXLCursorCmd *cmd = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id,
++                                      sizeof(QXLCursorCmd));
+     QXLCursor *cursor;
+     QEMUCursor *c;
+ 
+@@ -314,7 +318,15 @@ int qxl_render_cursor(PCIQXLDevice *qxl, QXLCommandExt *ext)
+     }
+     switch (cmd->type) {
+     case QXL_CURSOR_SET:
+-        cursor = qxl_phys2virt(qxl, cmd->u.set.shape, ext->group_id);
++        /* First read the QXLCursor to get QXLDataChunk::data_size ... */
++        cursor = qxl_phys2virt(qxl, cmd->u.set.shape, ext->group_id,
++                               sizeof(QXLCursor));
++        if (!cursor) {
++            return 1;
++        }
++        /* Then read including the chunked data following QXLCursor. */
++        cursor = qxl_phys2virt(qxl, cmd->u.set.shape, ext->group_id,
++                               sizeof(QXLCursor) + cursor->chunk.data_size);
+         if (!cursor) {
+             return 1;
+         }
+diff --git a/hw/display/qxl.c b/hw/display/qxl.c
+index 29c80b4289..aa9065183e 100644
+--- a/hw/display/qxl.c
++++ b/hw/display/qxl.c
+@@ -274,7 +274,8 @@ static void qxl_spice_monitors_config_async(PCIQXLDevice *qxl, int replay)
+                                           QXL_IO_MONITORS_CONFIG_ASYNC));
+     }
+ 
+-    cfg = qxl_phys2virt(qxl, qxl->guest_monitors_config, MEMSLOT_GROUP_GUEST);
++    cfg = qxl_phys2virt(qxl, qxl->guest_monitors_config, MEMSLOT_GROUP_GUEST,
++                        sizeof(QXLMonitorsConfig));
+     if (cfg != NULL && cfg->count == 1) {
+         qxl->guest_primary.resized = 1;
+         qxl->guest_head0_width  = cfg->heads[0].width;
+@@ -459,7 +460,8 @@ static int qxl_track_command(PCIQXLDevice *qxl, struct QXLCommandExt *ext)
+     switch (le32_to_cpu(ext->cmd.type)) {
+     case QXL_CMD_SURFACE:
+     {
+-        QXLSurfaceCmd *cmd = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id);
++        QXLSurfaceCmd *cmd = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id,
++                                           sizeof(QXLSurfaceCmd));
+ 
+         if (!cmd) {
+             return 1;
+@@ -494,7 +496,8 @@ static int qxl_track_command(PCIQXLDevice *qxl, struct QXLCommandExt *ext)
+     }
+     case QXL_CMD_CURSOR:
+     {
+-        QXLCursorCmd *cmd = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id);
++        QXLCursorCmd *cmd = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id,
++                                          sizeof(QXLCursorCmd));
+ 
+         if (!cmd) {
+             return 1;
+@@ -1444,7 +1447,8 @@ static bool qxl_get_check_slot_offset(PCIQXLDevice *qxl, QXLPHYSICAL pqxl,
+ }
+ 
+ /* can be also called from spice server thread context */
+-void *qxl_phys2virt(PCIQXLDevice *qxl, QXLPHYSICAL pqxl, int group_id)
++void *qxl_phys2virt(PCIQXLDevice *qxl, QXLPHYSICAL pqxl, int group_id,
++                    size_t size)
+ {
+     uint64_t offset;
+     uint32_t slot;
+@@ -1952,7 +1956,7 @@ static void qxl_dirty_surfaces(PCIQXLDevice *qxl)
+         }
+ 
+         cmd = qxl_phys2virt(qxl, qxl->guest_surfaces.cmds[i],
+-                            MEMSLOT_GROUP_GUEST);
++                            MEMSLOT_GROUP_GUEST, sizeof(QXLSurfaceCmd));
+         assert(cmd);
+         assert(cmd->type == QXL_SURFACE_CMD_CREATE);
+         qxl_dirty_one_surface(qxl, cmd->u.surface_create.data,
+diff --git a/hw/display/qxl.h b/hw/display/qxl.h
+index c938f88a2f..c784315daa 100644
+--- a/hw/display/qxl.h
++++ b/hw/display/qxl.h
+@@ -153,6 +153,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(PCIQXLDevice, PCI_QXL)
+  * @qxl: QXL device
+  * @phys: physical offset of buffer within the VRAM
+  * @group_id: memory slot group
++ * @size: size of the buffer
+  *
+  * Returns a host pointer to a buffer placed at offset @phys within the
+  * active slot @group_id of the PCI VGA RAM memory region associated with
+@@ -166,7 +167,8 @@ OBJECT_DECLARE_SIMPLE_TYPE(PCIQXLDevice, PCI_QXL)
+  * the incoming ram_addr_t.
+  *
+  */
+-void *qxl_phys2virt(PCIQXLDevice *qxl, QXLPHYSICAL phys, int group_id);
++void *qxl_phys2virt(PCIQXLDevice *qxl, QXLPHYSICAL phys, int group_id,
++                    size_t size);
+ void qxl_set_guest_bug(PCIQXLDevice *qxl, const char *msg, ...)
+     GCC_FMT_ATTR(2, 3);
+ 
+-- 
+2.37.3
+

SOURCES/kvm-hw-ide-reset-cancel-async-DMA-operation-before-reset.patch

@@ -0,0 +1,128 @@
+From 2308abf0c5da2fe35a0721318c31d22e077663c2 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Fri, 24 Nov 2023 12:17:11 -0500
+Subject: [PATCH 1/2] hw/ide: reset: cancel async DMA operation before
+ resetting state
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 335: hw/ide: reset: cancel async DMA operation before resetting state
+RH-Jira: RHEL-15437
+RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
+RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+RH-Commit: [1/2] b0f5f7f888559a210f1c6b3c545e337dbbc9cf22 (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+JIRA: https://issues.redhat.com/browse/RHEL-15437
+CVE: CVE-2023-5088
+Upstream: Merged
+
+commit 7d7512019fc40c577e2bdd61f114f31a9eb84a8e
+Author: Fiona Ebner <f.ebner@proxmox.com>
+Date:   Wed Sep 6 15:09:21 2023 +0200
+
+    hw/ide: reset: cancel async DMA operation before resetting state
+
+    If there is a pending DMA operation during ide_bus_reset(), the fact
+    that the IDEState is already reset before the operation is canceled
+    can be problematic. In particular, ide_dma_cb() might be called and
+    then use the reset IDEState which contains the signature after the
+    reset. When used to construct the IO operation this leads to
+    ide_get_sector() returning 0 and nsector being 1. This is particularly
+    bad, because a write command will thus destroy the first sector which
+    often contains a partition table or similar.
+
+    Traces showing the unsolicited write happening with IDEState
+    0x5595af6949d0 being used after reset:
+
+    > ahci_port_write ahci(0x5595af6923f0)[0]: port write [reg:PxSCTL] @ 0x2c: 0x00000300
+    > ahci_reset_port ahci(0x5595af6923f0)[0]: reset port
+    > ide_reset IDEstate 0x5595af6949d0
+    > ide_reset IDEstate 0x5595af694da8
+    > ide_bus_reset_aio aio_cancel
+    > dma_aio_cancel dbs=0x7f64600089a0
+    > dma_blk_cb dbs=0x7f64600089a0 ret=0
+    > dma_complete dbs=0x7f64600089a0 ret=0 cb=0x5595acd40b30
+    > ahci_populate_sglist ahci(0x5595af6923f0)[0]
+    > ahci_dma_prepare_buf ahci(0x5595af6923f0)[0]: prepare buf limit=512 prepared=512
+    > ide_dma_cb IDEState 0x5595af6949d0; sector_num=0 n=1 cmd=DMA WRITE
+    > dma_blk_io dbs=0x7f6420802010 bs=0x5595ae2c6c30 offset=0 to_dev=1
+    > dma_blk_cb dbs=0x7f6420802010 ret=0
+
+    > (gdb) p *qiov
+    > $11 = {iov = 0x7f647c76d840, niov = 1, {{nalloc = 1, local_iov = {iov_base = 0x0,
+    >       iov_len = 512}}, {__pad = "\001\000\000\000\000\000\000\000\000\000\000",
+    >       size = 512}}}
+    > (gdb) bt
+    > #0  blk_aio_pwritev (blk=0x5595ae2c6c30, offset=0, qiov=0x7f6420802070, flags=0,
+    >     cb=0x5595ace6f0b0 <dma_blk_cb>, opaque=0x7f6420802010)
+    >     at ../block/block-backend.c:1682
+    > #1  0x00005595ace6f185 in dma_blk_cb (opaque=0x7f6420802010, ret=<optimized out>)
+    >     at ../softmmu/dma-helpers.c:179
+    > #2  0x00005595ace6f778 in dma_blk_io (ctx=0x5595ae0609f0,
+    >     sg=sg@entry=0x5595af694d00, offset=offset@entry=0, align=align@entry=512,
+    >     io_func=io_func@entry=0x5595ace6ee30 <dma_blk_write_io_func>,
+    >     io_func_opaque=io_func_opaque@entry=0x5595ae2c6c30,
+    >     cb=0x5595acd40b30 <ide_dma_cb>, opaque=0x5595af6949d0,
+    >     dir=DMA_DIRECTION_TO_DEVICE) at ../softmmu/dma-helpers.c:244
+    > #3  0x00005595ace6f90a in dma_blk_write (blk=0x5595ae2c6c30,
+    >     sg=sg@entry=0x5595af694d00, offset=offset@entry=0, align=align@entry=512,
+    >     cb=cb@entry=0x5595acd40b30 <ide_dma_cb>, opaque=opaque@entry=0x5595af6949d0)
+    >     at ../softmmu/dma-helpers.c:280
+    > #4  0x00005595acd40e18 in ide_dma_cb (opaque=0x5595af6949d0, ret=<optimized out>)
+    >     at ../hw/ide/core.c:953
+    > #5  0x00005595ace6f319 in dma_complete (ret=0, dbs=0x7f64600089a0)
+    >     at ../softmmu/dma-helpers.c:107
+    > #6  dma_blk_cb (opaque=0x7f64600089a0, ret=0) at ../softmmu/dma-helpers.c:127
+    > #7  0x00005595ad12227d in blk_aio_complete (acb=0x7f6460005b10)
+    >     at ../block/block-backend.c:1527
+    > #8  blk_aio_complete (acb=0x7f6460005b10) at ../block/block-backend.c:1524
+    > #9  blk_aio_write_entry (opaque=0x7f6460005b10) at ../block/block-backend.c:1594
+    > #10 0x00005595ad258cfb in coroutine_trampoline (i0=<optimized out>,
+    >     i1=<optimized out>) at ../util/coroutine-ucontext.c:177
+
+    Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
+    Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+    Tested-by: simon.rowe@nutanix.com
+    Message-ID: <20230906130922.142845-1-f.ebner@proxmox.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/ide/core.c | 14 +++++++-------
+ 1 file changed, 7 insertions(+), 7 deletions(-)
+
+diff --git a/hw/ide/core.c b/hw/ide/core.c
+index 05a32d0a99..fd50c123e8 100644
+--- a/hw/ide/core.c
++++ b/hw/ide/core.c
+@@ -2456,19 +2456,19 @@ static void ide_dummy_transfer_stop(IDEState *s)
+ 
+ void ide_bus_reset(IDEBus *bus)
+ {
+-    bus->unit = 0;
+-    bus->cmd = 0;
+-    ide_reset(&bus->ifs[0]);
+-    ide_reset(&bus->ifs[1]);
+-    ide_clear_hob(bus);
+-
+-    /* pending async DMA */
++    /* pending async DMA - needs the IDEState before it is reset */
+     if (bus->dma->aiocb) {
+         trace_ide_bus_reset_aio();
+         blk_aio_cancel(bus->dma->aiocb);
+         bus->dma->aiocb = NULL;
+     }
+ 
++    bus->unit = 0;
++    bus->cmd = 0;
++    ide_reset(&bus->ifs[0]);
++    ide_reset(&bus->ifs[1]);
++    ide_clear_hob(bus);
++
+     /* reset dma provider too */
+     if (bus->dma->ops->reset) {
+         bus->dma->ops->reset(bus->dma);
+-- 
+2.41.0
+

SOURCES/kvm-hw-replace-most-qemu_bh_new-calls-with-qemu_bh_new_g.patch

@@ -0,0 +1,449 @@
+From 146cfb23b76b898f08690ffc14aab16d22a41404 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Tue, 9 May 2023 10:29:03 -0400
+Subject: [PATCH 04/15] hw: replace most qemu_bh_new calls with
+ qemu_bh_new_guarded
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [4/12] 00c51d30246b3aa529f6043e35ee471660aa1fce (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+Conflicts: In hw/nvme/ctrl.c there are no calls to qemu_bh_new() at the two locations
+           the replacement is done in the upstream commit. Instead, timer_new_ns() is
+           used. We leave these functions unaltered.
+
+commit f63192b0544af5d3e4d5edfd85ab520fcf671377
+Author: Alexander Bulekov <alxndr@bu.edu>
+Date:   Thu Apr 27 17:10:09 2023 -0400
+
+    hw: replace most qemu_bh_new calls with qemu_bh_new_guarded
+
+    This protects devices from bh->mmio reentrancy issues.
+
+    Thanks: Thomas Huth <thuth@redhat.com> for diagnosing OS X test failure.
+    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
+    Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
+    Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
+    Reviewed-by: Paul Durrant <paul@xen.org>
+    Reviewed-by: Thomas Huth <thuth@redhat.com>
+    Message-Id: <20230427211013.2994127-5-alxndr@bu.edu>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/9pfs/xen-9p-backend.c        | 5 ++++-
+ hw/block/dataplane/virtio-blk.c | 3 ++-
+ hw/block/dataplane/xen-block.c  | 5 +++--
+ hw/char/virtio-serial-bus.c     | 3 ++-
+ hw/display/qxl.c                | 9 ++++++---
+ hw/display/virtio-gpu.c         | 6 ++++--
+ hw/ide/ahci.c                   | 3 ++-
+ hw/ide/ahci_internal.h          | 1 +
+ hw/ide/core.c                   | 4 +++-
+ hw/misc/imx_rngc.c              | 6 ++++--
+ hw/misc/macio/mac_dbdma.c       | 2 +-
+ hw/net/virtio-net.c             | 3 ++-
+ hw/scsi/mptsas.c                | 3 ++-
+ hw/scsi/scsi-bus.c              | 3 ++-
+ hw/scsi/vmw_pvscsi.c            | 3 ++-
+ hw/usb/dev-uas.c                | 3 ++-
+ hw/usb/hcd-dwc2.c               | 3 ++-
+ hw/usb/hcd-ehci.c               | 3 ++-
+ hw/usb/hcd-uhci.c               | 2 +-
+ hw/usb/host-libusb.c            | 6 ++++--
+ hw/usb/redirect.c               | 6 ++++--
+ hw/usb/xen-usb.c                | 3 ++-
+ hw/virtio/virtio-balloon.c      | 5 +++--
+ hw/virtio/virtio-crypto.c       | 3 ++-
+ 24 files changed, 62 insertions(+), 31 deletions(-)
+
+diff --git a/hw/9pfs/xen-9p-backend.c b/hw/9pfs/xen-9p-backend.c
+index 65c4979c3c..09f7c13588 100644
+--- a/hw/9pfs/xen-9p-backend.c
++++ b/hw/9pfs/xen-9p-backend.c
+@@ -60,6 +60,7 @@ typedef struct Xen9pfsDev {
+ 
+     int num_rings;
+     Xen9pfsRing *rings;
++    MemReentrancyGuard mem_reentrancy_guard;
+ } Xen9pfsDev;
+ 
+ static void xen_9pfs_disconnect(struct XenLegacyDevice *xendev);
+@@ -441,7 +442,9 @@ static int xen_9pfs_connect(struct XenLegacyDevice *xendev)
+         xen_9pdev->rings[i].ring.out = xen_9pdev->rings[i].data +
+                                        XEN_FLEX_RING_SIZE(ring_order);
+ 
+-        xen_9pdev->rings[i].bh = qemu_bh_new(xen_9pfs_bh, &xen_9pdev->rings[i]);
++        xen_9pdev->rings[i].bh = qemu_bh_new_guarded(xen_9pfs_bh,
++                                                     &xen_9pdev->rings[i],
++                                                     &xen_9pdev->mem_reentrancy_guard);
+         xen_9pdev->rings[i].out_cons = 0;
+         xen_9pdev->rings[i].out_size = 0;
+         xen_9pdev->rings[i].inprogress = false;
+diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
+index ee5a5352dc..5f0de7da1e 100644
+--- a/hw/block/dataplane/virtio-blk.c
++++ b/hw/block/dataplane/virtio-blk.c
+@@ -127,7 +127,8 @@ bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
+     } else {
+         s->ctx = qemu_get_aio_context();
+     }
+-    s->bh = aio_bh_new(s->ctx, notify_guest_bh, s);
++    s->bh = aio_bh_new_guarded(s->ctx, notify_guest_bh, s,
++                               &DEVICE(vdev)->mem_reentrancy_guard);
+     s->batch_notify_vqs = bitmap_new(conf->num_queues);
+ 
+     *dataplane = s;
+diff --git a/hw/block/dataplane/xen-block.c b/hw/block/dataplane/xen-block.c
+index 860787580a..07855feea6 100644
+--- a/hw/block/dataplane/xen-block.c
++++ b/hw/block/dataplane/xen-block.c
+@@ -631,8 +631,9 @@ XenBlockDataPlane *xen_block_dataplane_create(XenDevice *xendev,
+     } else {
+         dataplane->ctx = qemu_get_aio_context();
+     }
+-    dataplane->bh = aio_bh_new(dataplane->ctx, xen_block_dataplane_bh,
+-                               dataplane);
++    dataplane->bh = aio_bh_new_guarded(dataplane->ctx, xen_block_dataplane_bh,
++                                       dataplane,
++                                       &DEVICE(xendev)->mem_reentrancy_guard);
+ 
+     return dataplane;
+ }
+diff --git a/hw/char/virtio-serial-bus.c b/hw/char/virtio-serial-bus.c
+index f01ec2137c..f18124b155 100644
+--- a/hw/char/virtio-serial-bus.c
++++ b/hw/char/virtio-serial-bus.c
+@@ -985,7 +985,8 @@ static void virtser_port_device_realize(DeviceState *dev, Error **errp)
+         return;
+     }
+ 
+-    port->bh = qemu_bh_new(flush_queued_data_bh, port);
++    port->bh = qemu_bh_new_guarded(flush_queued_data_bh, port,
++                                   &dev->mem_reentrancy_guard);
+     port->elem = NULL;
+ }
+ 
+diff --git a/hw/display/qxl.c b/hw/display/qxl.c
+index bcd9e8716a..0f663b9912 100644
+--- a/hw/display/qxl.c
++++ b/hw/display/qxl.c
+@@ -2206,11 +2206,14 @@ static void qxl_realize_common(PCIQXLDevice *qxl, Error **errp)
+ 
+     qemu_add_vm_change_state_handler(qxl_vm_change_state_handler, qxl);
+ 
+-    qxl->update_irq = qemu_bh_new(qxl_update_irq_bh, qxl);
++    qxl->update_irq = qemu_bh_new_guarded(qxl_update_irq_bh, qxl,
++                                          &DEVICE(qxl)->mem_reentrancy_guard);
+     qxl_reset_state(qxl);
+ 
+-    qxl->update_area_bh = qemu_bh_new(qxl_render_update_area_bh, qxl);
+-    qxl->ssd.cursor_bh = qemu_bh_new(qemu_spice_cursor_refresh_bh, &qxl->ssd);
++    qxl->update_area_bh = qemu_bh_new_guarded(qxl_render_update_area_bh, qxl,
++                                              &DEVICE(qxl)->mem_reentrancy_guard);
++    qxl->ssd.cursor_bh = qemu_bh_new_guarded(qemu_spice_cursor_refresh_bh, &qxl->ssd,
++                                             &DEVICE(qxl)->mem_reentrancy_guard);
+ }
+ 
+ static void qxl_realize_primary(PCIDevice *dev, Error **errp)
+diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c
+index d78b9700c7..ecf9079145 100644
+--- a/hw/display/virtio-gpu.c
++++ b/hw/display/virtio-gpu.c
+@@ -1332,8 +1332,10 @@ void virtio_gpu_device_realize(DeviceState *qdev, Error **errp)
+ 
+     g->ctrl_vq = virtio_get_queue(vdev, 0);
+     g->cursor_vq = virtio_get_queue(vdev, 1);
+-    g->ctrl_bh = qemu_bh_new(virtio_gpu_ctrl_bh, g);
+-    g->cursor_bh = qemu_bh_new(virtio_gpu_cursor_bh, g);
++    g->ctrl_bh = qemu_bh_new_guarded(virtio_gpu_ctrl_bh, g,
++                                     &qdev->mem_reentrancy_guard);
++    g->cursor_bh = qemu_bh_new_guarded(virtio_gpu_cursor_bh, g,
++                                       &qdev->mem_reentrancy_guard);
+     QTAILQ_INIT(&g->reslist);
+     QTAILQ_INIT(&g->cmdq);
+     QTAILQ_INIT(&g->fenceq);
+diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
+index a94c6e26fb..7488b28065 100644
+--- a/hw/ide/ahci.c
++++ b/hw/ide/ahci.c
+@@ -1504,7 +1504,8 @@ static void ahci_cmd_done(const IDEDMA *dma)
+     ahci_write_fis_d2h(ad);
+ 
+     if (ad->port_regs.cmd_issue && !ad->check_bh) {
+-        ad->check_bh = qemu_bh_new(ahci_check_cmd_bh, ad);
++        ad->check_bh = qemu_bh_new_guarded(ahci_check_cmd_bh, ad,
++                                           &ad->mem_reentrancy_guard);
+         qemu_bh_schedule(ad->check_bh);
+     }
+ }
+diff --git a/hw/ide/ahci_internal.h b/hw/ide/ahci_internal.h
+index 109de9e2d1..a7768dd69e 100644
+--- a/hw/ide/ahci_internal.h
++++ b/hw/ide/ahci_internal.h
+@@ -321,6 +321,7 @@ struct AHCIDevice {
+     bool init_d2h_sent;
+     AHCICmdHdr *cur_cmd;
+     NCQTransferState ncq_tfs[AHCI_MAX_CMDS];
++    MemReentrancyGuard mem_reentrancy_guard;
+ };
+ 
+ struct AHCIPCIState {
+diff --git a/hw/ide/core.c b/hw/ide/core.c
+index 15138225be..05a32d0a99 100644
+--- a/hw/ide/core.c
++++ b/hw/ide/core.c
+@@ -510,6 +510,7 @@ BlockAIOCB *ide_issue_trim(
+         BlockCompletionFunc *cb, void *cb_opaque, void *opaque)
+ {
+     IDEState *s = opaque;
++    IDEDevice *dev = s->unit ? s->bus->slave : s->bus->master;
+     TrimAIOCB *iocb;
+ 
+     /* Paired with a decrement in ide_trim_bh_cb() */
+@@ -517,7 +518,8 @@ BlockAIOCB *ide_issue_trim(
+ 
+     iocb = blk_aio_get(&trim_aiocb_info, s->blk, cb, cb_opaque);
+     iocb->s = s;
+-    iocb->bh = qemu_bh_new(ide_trim_bh_cb, iocb);
++    iocb->bh = qemu_bh_new_guarded(ide_trim_bh_cb, iocb,
++                                   &DEVICE(dev)->mem_reentrancy_guard);
+     iocb->ret = 0;
+     iocb->qiov = qiov;
+     iocb->i = -1;
+diff --git a/hw/misc/imx_rngc.c b/hw/misc/imx_rngc.c
+index 632c03779c..082c6980ad 100644
+--- a/hw/misc/imx_rngc.c
++++ b/hw/misc/imx_rngc.c
+@@ -228,8 +228,10 @@ static void imx_rngc_realize(DeviceState *dev, Error **errp)
+     sysbus_init_mmio(sbd, &s->iomem);
+ 
+     sysbus_init_irq(sbd, &s->irq);
+-    s->self_test_bh = qemu_bh_new(imx_rngc_self_test, s);
+-    s->seed_bh = qemu_bh_new(imx_rngc_seed, s);
++    s->self_test_bh = qemu_bh_new_guarded(imx_rngc_self_test, s,
++                                          &dev->mem_reentrancy_guard);
++    s->seed_bh = qemu_bh_new_guarded(imx_rngc_seed, s,
++                                     &dev->mem_reentrancy_guard);
+ }
+ 
+ static void imx_rngc_reset(DeviceState *dev)
+diff --git a/hw/misc/macio/mac_dbdma.c b/hw/misc/macio/mac_dbdma.c
+index e220f1a927..f6a9e76fe7 100644
+--- a/hw/misc/macio/mac_dbdma.c
++++ b/hw/misc/macio/mac_dbdma.c
+@@ -912,7 +912,7 @@ static void mac_dbdma_realize(DeviceState *dev, Error **errp)
+ {
+     DBDMAState *s = MAC_DBDMA(dev);
+ 
+-    s->bh = qemu_bh_new(DBDMA_run_bh, s);
++    s->bh = qemu_bh_new_guarded(DBDMA_run_bh, s, &dev->mem_reentrancy_guard);
+ }
+ 
+ static void mac_dbdma_class_init(ObjectClass *oc, void *data)
+diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
+index 7e172ef829..ddaa8fa122 100644
+--- a/hw/net/virtio-net.c
++++ b/hw/net/virtio-net.c
+@@ -2753,7 +2753,8 @@ static void virtio_net_add_queue(VirtIONet *n, int index)
+         n->vqs[index].tx_vq =
+             virtio_add_queue(vdev, n->net_conf.tx_queue_size,
+                              virtio_net_handle_tx_bh);
+-        n->vqs[index].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[index]);
++        n->vqs[index].tx_bh = qemu_bh_new_guarded(virtio_net_tx_bh, &n->vqs[index],
++                                                  &DEVICE(vdev)->mem_reentrancy_guard);
+     }
+ 
+     n->vqs[index].tx_waiting = 0;
+diff --git a/hw/scsi/mptsas.c b/hw/scsi/mptsas.c
+index f6c7765544..ab8aaca85d 100644
+--- a/hw/scsi/mptsas.c
++++ b/hw/scsi/mptsas.c
+@@ -1313,7 +1313,8 @@ static void mptsas_scsi_realize(PCIDevice *dev, Error **errp)
+     }
+     s->max_devices = MPTSAS_NUM_PORTS;
+ 
+-    s->request_bh = qemu_bh_new(mptsas_fetch_requests, s);
++    s->request_bh = qemu_bh_new_guarded(mptsas_fetch_requests, s,
++                                        &DEVICE(dev)->mem_reentrancy_guard);
+ 
+     scsi_bus_init(&s->bus, sizeof(s->bus), &dev->qdev, &mptsas_scsi_info);
+ }
+diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
+index 77325d8cc7..b506ab7d04 100644
+--- a/hw/scsi/scsi-bus.c
++++ b/hw/scsi/scsi-bus.c
+@@ -192,7 +192,8 @@ static void scsi_dma_restart_cb(void *opaque, bool running, RunState state)
+         AioContext *ctx = blk_get_aio_context(s->conf.blk);
+         /* The reference is dropped in scsi_dma_restart_bh.*/
+         object_ref(OBJECT(s));
+-        s->bh = aio_bh_new(ctx, scsi_dma_restart_bh, s);
++        s->bh = aio_bh_new_guarded(ctx, scsi_dma_restart_bh, s,
++                                   &DEVICE(s)->mem_reentrancy_guard);
+         qemu_bh_schedule(s->bh);
+     }
+ }
+diff --git a/hw/scsi/vmw_pvscsi.c b/hw/scsi/vmw_pvscsi.c
+index cd76bd67ab..4c36febbc0 100644
+--- a/hw/scsi/vmw_pvscsi.c
++++ b/hw/scsi/vmw_pvscsi.c
+@@ -1178,7 +1178,8 @@ pvscsi_realizefn(PCIDevice *pci_dev, Error **errp)
+         pcie_endpoint_cap_init(pci_dev, PVSCSI_EXP_EP_OFFSET);
+     }
+ 
+-    s->completion_worker = qemu_bh_new(pvscsi_process_completion_queue, s);
++    s->completion_worker = qemu_bh_new_guarded(pvscsi_process_completion_queue, s,
++                                               &DEVICE(pci_dev)->mem_reentrancy_guard);
+ 
+     scsi_bus_init(&s->bus, sizeof(s->bus), DEVICE(pci_dev), &pvscsi_scsi_info);
+     /* override default SCSI bus hotplug-handler, with pvscsi's one */
+diff --git a/hw/usb/dev-uas.c b/hw/usb/dev-uas.c
+index 599d6b52a0..a36a7c3013 100644
+--- a/hw/usb/dev-uas.c
++++ b/hw/usb/dev-uas.c
+@@ -935,7 +935,8 @@ static void usb_uas_realize(USBDevice *dev, Error **errp)
+ 
+     QTAILQ_INIT(&uas->results);
+     QTAILQ_INIT(&uas->requests);
+-    uas->status_bh = qemu_bh_new(usb_uas_send_status_bh, uas);
++    uas->status_bh = qemu_bh_new_guarded(usb_uas_send_status_bh, uas,
++                                         &d->mem_reentrancy_guard);
+ 
+     dev->flags |= (1 << USB_DEV_FLAG_IS_SCSI_STORAGE);
+     scsi_bus_init(&uas->bus, sizeof(uas->bus), DEVICE(dev), &usb_uas_scsi_info);
+diff --git a/hw/usb/hcd-dwc2.c b/hw/usb/hcd-dwc2.c
+index e1d96acf7e..0e238f8422 100644
+--- a/hw/usb/hcd-dwc2.c
++++ b/hw/usb/hcd-dwc2.c
+@@ -1364,7 +1364,8 @@ static void dwc2_realize(DeviceState *dev, Error **errp)
+     s->fi = USB_FRMINTVL - 1;
+     s->eof_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, dwc2_frame_boundary, s);
+     s->frame_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, dwc2_work_timer, s);
+-    s->async_bh = qemu_bh_new(dwc2_work_bh, s);
++    s->async_bh = qemu_bh_new_guarded(dwc2_work_bh, s,
++                                      &dev->mem_reentrancy_guard);
+ 
+     sysbus_init_irq(sbd, &s->irq);
+ }
+diff --git a/hw/usb/hcd-ehci.c b/hw/usb/hcd-ehci.c
+index 6caa7ac6c2..df4ff6f2c1 100644
+--- a/hw/usb/hcd-ehci.c
++++ b/hw/usb/hcd-ehci.c
+@@ -2528,7 +2528,8 @@ void usb_ehci_realize(EHCIState *s, DeviceState *dev, Error **errp)
+     }
+ 
+     s->frame_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, ehci_work_timer, s);
+-    s->async_bh = qemu_bh_new(ehci_work_bh, s);
++    s->async_bh = qemu_bh_new_guarded(ehci_work_bh, s,
++                                      &dev->mem_reentrancy_guard);
+     s->device = dev;
+ 
+     s->vmstate = qemu_add_vm_change_state_handler(usb_ehci_vm_state_change, s);
+diff --git a/hw/usb/hcd-uhci.c b/hw/usb/hcd-uhci.c
+index 7930b868fa..469c5e57e9 100644
+--- a/hw/usb/hcd-uhci.c
++++ b/hw/usb/hcd-uhci.c
+@@ -1195,7 +1195,7 @@ void usb_uhci_common_realize(PCIDevice *dev, Error **errp)
+                               USB_SPEED_MASK_LOW | USB_SPEED_MASK_FULL);
+         }
+     }
+-    s->bh = qemu_bh_new(uhci_bh, s);
++    s->bh = qemu_bh_new_guarded(uhci_bh, s, &DEVICE(dev)->mem_reentrancy_guard);
+     s->frame_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, uhci_frame_timer, s);
+     s->num_ports_vmstate = NB_PORTS;
+     QTAILQ_INIT(&s->queues);
+diff --git a/hw/usb/host-libusb.c b/hw/usb/host-libusb.c
+index d0d46dd0a4..09b961116b 100644
+--- a/hw/usb/host-libusb.c
++++ b/hw/usb/host-libusb.c
+@@ -1141,7 +1141,8 @@ static void usb_host_nodev_bh(void *opaque)
+ static void usb_host_nodev(USBHostDevice *s)
+ {
+     if (!s->bh_nodev) {
+-        s->bh_nodev = qemu_bh_new(usb_host_nodev_bh, s);
++        s->bh_nodev = qemu_bh_new_guarded(usb_host_nodev_bh, s,
++                                          &DEVICE(s)->mem_reentrancy_guard);
+     }
+     qemu_bh_schedule(s->bh_nodev);
+ }
+@@ -1739,7 +1740,8 @@ static int usb_host_post_load(void *opaque, int version_id)
+     USBHostDevice *dev = opaque;
+ 
+     if (!dev->bh_postld) {
+-        dev->bh_postld = qemu_bh_new(usb_host_post_load_bh, dev);
++        dev->bh_postld = qemu_bh_new_guarded(usb_host_post_load_bh, dev,
++                                             &DEVICE(dev)->mem_reentrancy_guard);
+     }
+     qemu_bh_schedule(dev->bh_postld);
+     dev->bh_postld_pending = true;
+diff --git a/hw/usb/redirect.c b/hw/usb/redirect.c
+index 5f0ef9cb3b..59cd3cd7c4 100644
+--- a/hw/usb/redirect.c
++++ b/hw/usb/redirect.c
+@@ -1437,8 +1437,10 @@ static void usbredir_realize(USBDevice *udev, Error **errp)
+         }
+     }
+ 
+-    dev->chardev_close_bh = qemu_bh_new(usbredir_chardev_close_bh, dev);
+-    dev->device_reject_bh = qemu_bh_new(usbredir_device_reject_bh, dev);
++    dev->chardev_close_bh = qemu_bh_new_guarded(usbredir_chardev_close_bh, dev,
++                                                &DEVICE(dev)->mem_reentrancy_guard);
++    dev->device_reject_bh = qemu_bh_new_guarded(usbredir_device_reject_bh, dev,
++                                                &DEVICE(dev)->mem_reentrancy_guard);
+     dev->attach_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL, usbredir_do_attach, dev);
+ 
+     packet_id_queue_init(&dev->cancelled, dev, "cancelled");
+diff --git a/hw/usb/xen-usb.c b/hw/usb/xen-usb.c
+index 0f7369e7ed..dec91294ad 100644
+--- a/hw/usb/xen-usb.c
++++ b/hw/usb/xen-usb.c
+@@ -1021,7 +1021,8 @@ static void usbback_alloc(struct XenLegacyDevice *xendev)
+ 
+     QTAILQ_INIT(&usbif->req_free_q);
+     QSIMPLEQ_INIT(&usbif->hotplug_q);
+-    usbif->bh = qemu_bh_new(usbback_bh, usbif);
++    usbif->bh = qemu_bh_new_guarded(usbback_bh, usbif,
++                                    &DEVICE(xendev)->mem_reentrancy_guard);
+ }
+ 
+ static int usbback_free(struct XenLegacyDevice *xendev)
+diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
+index 9a4f491b54..f503572e27 100644
+--- a/hw/virtio/virtio-balloon.c
++++ b/hw/virtio/virtio-balloon.c
+@@ -917,8 +917,9 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
+         precopy_add_notifier(&s->free_page_hint_notify);
+ 
+         object_ref(OBJECT(s->iothread));
+-        s->free_page_bh = aio_bh_new(iothread_get_aio_context(s->iothread),
+-                                     virtio_ballloon_get_free_page_hints, s);
++        s->free_page_bh = aio_bh_new_guarded(iothread_get_aio_context(s->iothread),
++                                             virtio_ballloon_get_free_page_hints, s,
++                                             &dev->mem_reentrancy_guard);
+     }
+ 
+     if (virtio_has_feature(s->host_features, VIRTIO_BALLOON_F_REPORTING)) {
+diff --git a/hw/virtio/virtio-crypto.c b/hw/virtio/virtio-crypto.c
+index 54f9bbb789..1be7bb543c 100644
+--- a/hw/virtio/virtio-crypto.c
++++ b/hw/virtio/virtio-crypto.c
+@@ -817,7 +817,8 @@ static void virtio_crypto_device_realize(DeviceState *dev, Error **errp)
+         vcrypto->vqs[i].dataq =
+                  virtio_add_queue(vdev, 1024, virtio_crypto_handle_dataq_bh);
+         vcrypto->vqs[i].dataq_bh =
+-                 qemu_bh_new(virtio_crypto_dataq_bh, &vcrypto->vqs[i]);
++                 qemu_bh_new_guarded(virtio_crypto_dataq_bh, &vcrypto->vqs[i],
++                                     &dev->mem_reentrancy_guard);
+         vcrypto->vqs[i].vcrypto = vcrypto;
+     }
+ 
+-- 
+2.37.3
+

SOURCES/kvm-hw-s390x-Move-KVM-specific-PV-from-hw-to-target-s390.patch

@@ -0,0 +1,283 @@
+From 59f02a421ecdba6e856597367020926fc0cb5177 Mon Sep 17 00:00:00 2001
+From: Thomas Huth <thuth@redhat.com>
+Date: Mon, 15 Jan 2024 18:52:30 +0100
+Subject: [PATCH 4/5] hw/s390x: Move KVM specific PV from hw/ to
+ target/s390x/kvm/
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Thomas Huth <thuth@redhat.com>
+RH-MergeRequest: 348: s390x: Provide some more useful information if decryption of a PV image fails
+RH-Jira: RHEL-18214
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Acked-by: Cédric Le Goater <clg@redhat.com>
+RH-Commit: [4/5] f6095bfdb89268007a0741665284955db4752d46
+
+JIRA: https://issues.redhat.com/browse/RHEL-18214
+
+commit f5f9c6ea11bc807664fdeb9354915c2c9cdcbd89
+Author: Philippe Mathieu-Daudé <philmd@linaro.org>
+Date:   Sat Jun 24 22:06:44 2023 +0200
+
+    hw/s390x: Move KVM specific PV from hw/ to target/s390x/kvm/
+
+    Protected Virtualization (PV) is not a real hardware device:
+    it is a feature of the firmware on s390x that is exposed to
+    userspace via the KVM interface.
+
+    Move the pv.c/pv.h files to target/s390x/kvm/ to make this clearer.
+
+    Suggested-by: Thomas Huth <thuth@redhat.com>
+    Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+    Message-Id: <20230624200644.23931-1-philmd@linaro.org>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Conflicts:
+    hw/s390x/ipl.c
+    hw/s390x/s390-virtio-ccw.c
+    target/s390x/diag.c
+    (simple contextual conflict due to differce with #include statements)
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+---
+ MAINTAINERS                                 | 2 --
+ hw/s390x/ipl.c                              | 2 +-
+ hw/s390x/meson.build                        | 1 -
+ hw/s390x/s390-pci-kvm.c                     | 2 +-
+ hw/s390x/s390-virtio-ccw.c                  | 2 +-
+ hw/s390x/tod-kvm.c                          | 2 +-
+ target/s390x/arch_dump.c                    | 2 +-
+ target/s390x/cpu-sysemu.c                   | 2 +-
+ target/s390x/cpu_features.c                 | 2 +-
+ target/s390x/cpu_models.c                   | 2 +-
+ target/s390x/diag.c                         | 2 +-
+ target/s390x/helper.c                       | 2 +-
+ target/s390x/ioinst.c                       | 2 +-
+ target/s390x/kvm/kvm.c                      | 2 +-
+ target/s390x/kvm/meson.build                | 1 +
+ {hw/s390x => target/s390x/kvm}/pv.c         | 2 +-
+ {include/hw/s390x => target/s390x/kvm}/pv.h | 0
+ 17 files changed, 14 insertions(+), 16 deletions(-)
+ rename {hw/s390x => target/s390x/kvm}/pv.c (99%)
+ rename {include/hw/s390x => target/s390x/kvm}/pv.h (100%)
+
+diff --git a/MAINTAINERS b/MAINTAINERS
+index b893206fc3..d74ca51154 100644
+--- a/MAINTAINERS
++++ b/MAINTAINERS
+@@ -397,8 +397,6 @@ S: Supported
+ F: target/s390x/kvm/
+ F: target/s390x/machine.c
+ F: target/s390x/sigp.c
+-F: hw/s390x/pv.c
+-F: include/hw/s390x/pv.h
+ F: gdb-xml/s390*.xml
+ T: git https://github.com/borntraeger/qemu.git s390-next
+ L: qemu-s390x@nongnu.org
+diff --git a/hw/s390x/ipl.c b/hw/s390x/ipl.c
+index 9051d8652d..c25e247426 100644
+--- a/hw/s390x/ipl.c
++++ b/hw/s390x/ipl.c
+@@ -27,7 +27,7 @@
+ #include "hw/s390x/vfio-ccw.h"
+ #include "hw/s390x/css.h"
+ #include "hw/s390x/ebcdic.h"
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ #include "ipl.h"
+ #include "qemu/error-report.h"
+ #include "qemu/config-file.h"
+diff --git a/hw/s390x/meson.build b/hw/s390x/meson.build
+index 6e6e47fcda..bb3b42f613 100644
+--- a/hw/s390x/meson.build
++++ b/hw/s390x/meson.build
+@@ -22,7 +22,6 @@ s390x_ss.add(when: 'CONFIG_KVM', if_true: files(
+   'tod-kvm.c',
+   's390-skeys-kvm.c',
+   's390-stattrib-kvm.c',
+-  'pv.c',
+   's390-pci-kvm.c',
+ ))
+ s390x_ss.add(when: 'CONFIG_TCG', if_true: files(
+diff --git a/hw/s390x/s390-pci-kvm.c b/hw/s390x/s390-pci-kvm.c
+index 9134fe185f..ff41e4106d 100644
+--- a/hw/s390x/s390-pci-kvm.c
++++ b/hw/s390x/s390-pci-kvm.c
+@@ -14,7 +14,7 @@
+ #include <linux/kvm.h>
+ 
+ #include "kvm/kvm_s390x.h"
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ #include "hw/s390x/s390-pci-bus.h"
+ #include "hw/s390x/s390-pci-kvm.h"
+ #include "hw/s390x/s390-pci-inst.h"
+diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
+index 17146469ee..7bfa5b4e8f 100644
+--- a/hw/s390x/s390-virtio-ccw.c
++++ b/hw/s390x/s390-virtio-ccw.c
+@@ -40,7 +40,7 @@
+ #include "hw/qdev-properties.h"
+ #include "hw/s390x/tod.h"
+ #include "sysemu/sysemu.h"
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ #include "migration/blocker.h"
+ #include "qapi/visitor.h"
+ 
+diff --git a/hw/s390x/tod-kvm.c b/hw/s390x/tod-kvm.c
+index c804c979b5..9776cda50a 100644
+--- a/hw/s390x/tod-kvm.c
++++ b/hw/s390x/tod-kvm.c
+@@ -13,7 +13,7 @@
+ #include "qemu/module.h"
+ #include "sysemu/runstate.h"
+ #include "hw/s390x/tod.h"
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ #include "kvm/kvm_s390x.h"
+ 
+ static void kvm_s390_get_tod_raw(S390TOD *tod, Error **errp)
+diff --git a/target/s390x/arch_dump.c b/target/s390x/arch_dump.c
+index 3b1f178dc3..2554238c16 100644
+--- a/target/s390x/arch_dump.c
++++ b/target/s390x/arch_dump.c
+@@ -17,8 +17,8 @@
+ #include "s390x-internal.h"
+ #include "elf.h"
+ #include "sysemu/dump.h"
+-#include "hw/s390x/pv.h"
+ #include "kvm/kvm_s390x.h"
++#include "target/s390x/kvm/pv.h"
+ 
+ struct S390xUserRegsStruct {
+     uint64_t psw[2];
+diff --git a/target/s390x/cpu-sysemu.c b/target/s390x/cpu-sysemu.c
+index 5471e01ee8..547287a949 100644
+--- a/target/s390x/cpu-sysemu.c
++++ b/target/s390x/cpu-sysemu.c
+@@ -32,7 +32,7 @@
+ #include "qapi/qapi-visit-run-state.h"
+ #include "sysemu/hw_accel.h"
+ 
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ #include "hw/boards.h"
+ #include "sysemu/sysemu.h"
+ #include "sysemu/tcg.h"
+diff --git a/target/s390x/cpu_features.c b/target/s390x/cpu_features.c
+index 2e4e11d264..ebb155ce1c 100644
+--- a/target/s390x/cpu_features.c
++++ b/target/s390x/cpu_features.c
+@@ -15,7 +15,7 @@
+ #include "qemu/module.h"
+ #include "cpu_features.h"
+ #ifndef CONFIG_USER_ONLY
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ #endif
+ 
+ #define DEF_FEAT(_FEAT, _NAME, _TYPE, _BIT, _DESC) \
+diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
+index e7c586c76e..100c5e7b3a 100644
+--- a/target/s390x/cpu_models.c
++++ b/target/s390x/cpu_models.c
+@@ -22,7 +22,7 @@
+ #include "qemu/qemu-print.h"
+ #ifndef CONFIG_USER_ONLY
+ #include "sysemu/sysemu.h"
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ #endif
+ 
+ #define CPUDEF_INIT(_type, _gen, _ec_ga, _mha_pow, _hmfai, _name, _desc) \
+diff --git a/target/s390x/diag.c b/target/s390x/diag.c
+index 76b01dcd68..7c8714cc27 100644
+--- a/target/s390x/diag.c
++++ b/target/s390x/diag.c
+@@ -19,9 +19,9 @@
+ #include "sysemu/cpus.h"
+ #include "hw/s390x/ipl.h"
+ #include "hw/s390x/s390-virtio-ccw.h"
+-#include "hw/s390x/pv.h"
+ #include "sysemu/kvm.h"
+ #include "kvm/kvm_s390x.h"
++#include "target/s390x/kvm/pv.h"
+ 
+ int handle_diag_288(CPUS390XState *env, uint64_t r1, uint64_t r3)
+ {
+diff --git a/target/s390x/helper.c b/target/s390x/helper.c
+index 6e35473c7f..860977126a 100644
+--- a/target/s390x/helper.c
++++ b/target/s390x/helper.c
+@@ -24,7 +24,7 @@
+ #include "exec/gdbstub.h"
+ #include "qemu/timer.h"
+ #include "hw/s390x/ioinst.h"
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ #include "sysemu/hw_accel.h"
+ #include "sysemu/runstate.h"
+ #include "sysemu/tcg.h"
+diff --git a/target/s390x/ioinst.c b/target/s390x/ioinst.c
+index bdae5090bc..409f3e3e63 100644
+--- a/target/s390x/ioinst.c
++++ b/target/s390x/ioinst.c
+@@ -16,7 +16,7 @@
+ #include "hw/s390x/ioinst.h"
+ #include "trace.h"
+ #include "hw/s390x/s390-pci-bus.h"
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ 
+ /* All I/O instructions but chsc use the s format */
+ static uint64_t get_address_from_regs(CPUS390XState *env, uint32_t ipb,
+diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c
+index a963866ef4..6d1a6324b9 100644
+--- a/target/s390x/kvm/kvm.c
++++ b/target/s390x/kvm/kvm.c
+@@ -51,7 +51,7 @@
+ #include "exec/memattrs.h"
+ #include "hw/s390x/s390-virtio-ccw.h"
+ #include "hw/s390x/s390-virtio-hcall.h"
+-#include "hw/s390x/pv.h"
++#include "target/s390x/kvm/pv.h"
+ 
+ #ifndef DEBUG_KVM
+ #define DEBUG_KVM  0
+diff --git a/target/s390x/kvm/meson.build b/target/s390x/kvm/meson.build
+index aef52b6686..739d5b9f54 100644
+--- a/target/s390x/kvm/meson.build
++++ b/target/s390x/kvm/meson.build
+@@ -1,5 +1,6 @@
+ 
+ s390x_ss.add(when: 'CONFIG_KVM', if_true: files(
++  'pv.c',
+   'kvm.c'
+ ), if_false: files(
+   'stubs.c'
+diff --git a/hw/s390x/pv.c b/target/s390x/kvm/pv.c
+similarity index 99%
+rename from hw/s390x/pv.c
+rename to target/s390x/kvm/pv.c
+index 8a1c71436b..e14db4f41a 100644
+--- a/hw/s390x/pv.c
++++ b/target/s390x/kvm/pv.c
+@@ -19,9 +19,9 @@
+ #include "qom/object_interfaces.h"
+ #include "exec/confidential-guest-support.h"
+ #include "hw/s390x/ipl.h"
+-#include "hw/s390x/pv.h"
+ #include "hw/s390x/sclp.h"
+ #include "target/s390x/kvm/kvm_s390x.h"
++#include "target/s390x/kvm/pv.h"
+ 
+ static bool info_valid;
+ static struct kvm_s390_pv_info_vm info_vm;
+diff --git a/include/hw/s390x/pv.h b/target/s390x/kvm/pv.h
+similarity index 100%
+rename from include/hw/s390x/pv.h
+rename to target/s390x/kvm/pv.h
+-- 
+2.41.0
+

SOURCES/kvm-hw-s390x-pv-Restrict-Protected-Virtualization-to-sys.patch

@@ -0,0 +1,100 @@
+From 053faafcf523b0ea4d841c0af8e7e26a2cddd5e8 Mon Sep 17 00:00:00 2001
+From: Thomas Huth <thuth@redhat.com>
+Date: Mon, 15 Jan 2024 14:00:04 +0100
+Subject: [PATCH 3/5] hw/s390x/pv: Restrict Protected Virtualization to sysemu
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Thomas Huth <thuth@redhat.com>
+RH-MergeRequest: 348: s390x: Provide some more useful information if decryption of a PV image fails
+RH-Jira: RHEL-18214
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Acked-by: Cédric Le Goater <clg@redhat.com>
+RH-Commit: [3/5] 17b11f9fd2b53c7d33c09a62f28cfca19b18e798
+
+JIRA: https://issues.redhat.com/browse/RHEL-18214
+
+commit 3ea7e312671686e616efa1b8caa5f5ce2d06543a
+Author: Philippe Mathieu-Daudé <philmd@linaro.org>
+Date:   Sat Dec 17 16:24:52 2022 +0100
+
+    hw/s390x/pv: Restrict Protected Virtualization to sysemu
+
+    Protected Virtualization is irrelevant in user emulation.
+
+    Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+    Message-Id: <20221217152454.96388-4-philmd@linaro.org>
+    Reviewed-by: Thomas Huth <thuth@redhat.com>
+    Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Thomas Huth <thuth@redhat.com>
+---
+ target/s390x/cpu_features.c | 4 ++++
+ target/s390x/cpu_models.c   | 4 +++-
+ 2 files changed, 7 insertions(+), 1 deletion(-)
+
+diff --git a/target/s390x/cpu_features.c b/target/s390x/cpu_features.c
+index 5528acd082..2e4e11d264 100644
+--- a/target/s390x/cpu_features.c
++++ b/target/s390x/cpu_features.c
+@@ -14,7 +14,9 @@
+ #include "qemu/osdep.h"
+ #include "qemu/module.h"
+ #include "cpu_features.h"
++#ifndef CONFIG_USER_ONLY
+ #include "hw/s390x/pv.h"
++#endif
+ 
+ #define DEF_FEAT(_FEAT, _NAME, _TYPE, _BIT, _DESC) \
+     [S390_FEAT_##_FEAT] = {                        \
+@@ -107,6 +109,7 @@ void s390_fill_feat_block(const S390FeatBitmap features, S390FeatType type,
+         feat = find_next_bit(features, S390_FEAT_MAX, feat + 1);
+     }
+ 
++#ifndef CONFIG_USER_ONLY
+     if (!s390_is_pv()) {
+         return;
+     }
+@@ -147,6 +150,7 @@ void s390_fill_feat_block(const S390FeatBitmap features, S390FeatType type,
+     default:
+         return;
+     }
++#endif
+ }
+ 
+ void s390_add_from_feat_block(S390FeatBitmap features, S390FeatType type,
+diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
+index 454485e706..e7c586c76e 100644
+--- a/target/s390x/cpu_models.c
++++ b/target/s390x/cpu_models.c
+@@ -22,8 +22,8 @@
+ #include "qemu/qemu-print.h"
+ #ifndef CONFIG_USER_ONLY
+ #include "sysemu/sysemu.h"
+-#endif
+ #include "hw/s390x/pv.h"
++#endif
+ 
+ #define CPUDEF_INIT(_type, _gen, _ec_ga, _mha_pow, _hmfai, _name, _desc) \
+     {                                                                    \
+@@ -236,6 +236,7 @@ bool s390_has_feat(S390Feat feat)
+         return 0;
+     }
+ 
++#ifndef CONFIG_USER_ONLY
+     if (s390_is_pv()) {
+         switch (feat) {
+         case S390_FEAT_DIAG_318:
+@@ -259,6 +260,7 @@ bool s390_has_feat(S390Feat feat)
+             break;
+         }
+     }
++#endif
+     return test_bit(feat, cpu->model->features);
+ }
+ 
+-- 
+2.41.0
+

SOURCES/kvm-hw-scsi-lsi53c895a-Fix-reentrancy-issues-in-the-LSI-.patch

@@ -0,0 +1,260 @@
+From 57a26ba1c4053cdc426653f921e66f7a8efd3ce7 Mon Sep 17 00:00:00 2001
+From: Thomas Huth <thuth@redhat.com>
+Date: Mon, 22 May 2023 11:10:11 +0200
+Subject: [PATCH 12/15] hw/scsi/lsi53c895a: Fix reentrancy issues in the LSI
+ controller (CVE-2023-0330)
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [12/12] 28f5e04344109d8514869c50468bef481437201d (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+
+commit b987718bbb1d0eabf95499b976212dd5f0120d75
+Author: Thomas Huth <thuth@redhat.com>
+Date:   Mon May 22 11:10:11 2023 +0200
+
+    hw/scsi/lsi53c895a: Fix reentrancy issues in the LSI controller (CVE-2023-0330)
+
+    We cannot use the generic reentrancy guard in the LSI code, so
+    we have to manually prevent endless reentrancy here. The problematic
+    lsi_execute_script() function has already a way to detect whether
+    too many instructions have been executed - we just have to slightly
+    change the logic here that it also takes into account if the function
+    has been called too often in a reentrant way.
+
+    The code in fuzz-lsi53c895a-test.c has been taken from an earlier
+    patch by Mauro Matteo Cascella.
+
+    Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1563
+    Message-Id: <20230522091011.1082574-1-thuth@redhat.com>
+    Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+    Reviewed-by: Alexander Bulekov <alxndr@bu.edu>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/scsi/lsi53c895a.c               |  23 +++--
+ tests/qtest/fuzz-lsi53c895a-test.c | 161 +++++++++++++++++++++++++++++
+ 2 files changed, 178 insertions(+), 6 deletions(-)
+ create mode 100644 tests/qtest/fuzz-lsi53c895a-test.c
+
+diff --git a/hw/scsi/lsi53c895a.c b/hw/scsi/lsi53c895a.c
+index 2b9cb2ac5d..b60786fd56 100644
+--- a/hw/scsi/lsi53c895a.c
++++ b/hw/scsi/lsi53c895a.c
+@@ -1133,15 +1133,24 @@ static void lsi_execute_script(LSIState *s)
+     uint32_t addr, addr_high;
+     int opcode;
+     int insn_processed = 0;
++    static int reentrancy_level;
++
++    reentrancy_level++;
+ 
+     s->istat1 |= LSI_ISTAT1_SRUN;
+ again:
+-    if (++insn_processed > LSI_MAX_INSN) {
+-        /* Some windows drivers make the device spin waiting for a memory
+-           location to change.  If we have been executed a lot of code then
+-           assume this is the case and force an unexpected device disconnect.
+-           This is apparently sufficient to beat the drivers into submission.
+-         */
++    /*
++     * Some windows drivers make the device spin waiting for a memory location
++     * to change. If we have executed more than LSI_MAX_INSN instructions then
++     * assume this is the case and force an unexpected device disconnect. This
++     * is apparently sufficient to beat the drivers into submission.
++     *
++     * Another issue (CVE-2023-0330) can occur if the script is programmed to
++     * trigger itself again and again. Avoid this problem by stopping after
++     * being called multiple times in a reentrant way (8 is an arbitrary value
++     * which should be enough for all valid use cases).
++     */
++    if (++insn_processed > LSI_MAX_INSN || reentrancy_level > 8) {
+         if (!(s->sien0 & LSI_SIST0_UDC)) {
+             qemu_log_mask(LOG_GUEST_ERROR,
+                           "lsi_scsi: inf. loop with UDC masked");
+@@ -1595,6 +1604,8 @@ again:
+         }
+     }
+     trace_lsi_execute_script_stop();
++
++    reentrancy_level--;
+ }
+ 
+ static uint8_t lsi_reg_readb(LSIState *s, int offset)
+diff --git a/tests/qtest/fuzz-lsi53c895a-test.c b/tests/qtest/fuzz-lsi53c895a-test.c
+new file mode 100644
+index 0000000000..1b55928b9f
+--- /dev/null
++++ b/tests/qtest/fuzz-lsi53c895a-test.c
+@@ -0,0 +1,161 @@
++/* SPDX-License-Identifier: GPL-2.0-or-later */
++/*
++ * QTest fuzzer-generated testcase for LSI53C895A device
++ *
++ * Copyright (c) Red Hat
++ */
++
++#include "qemu/osdep.h"
++#include "libqtest.h"
++
++/*
++ * This used to trigger a DMA reentrancy issue
++ * leading to memory corruption bugs like stack
++ * overflow or use-after-free
++ * https://gitlab.com/qemu-project/qemu/-/issues/1563
++ */
++static void test_lsi_dma_reentrancy(void)
++{
++    QTestState *s;
++
++    s = qtest_init("-M q35 -m 512M -nodefaults "
++                   "-blockdev driver=null-co,node-name=null0 "
++                   "-device lsi53c810 -device scsi-cd,drive=null0");
++
++    qtest_outl(s, 0xcf8, 0x80000804); /* PCI Command Register */
++    qtest_outw(s, 0xcfc, 0x7);        /* Enables accesses */
++    qtest_outl(s, 0xcf8, 0x80000814); /* Memory Bar 1 */
++    qtest_outl(s, 0xcfc, 0xff100000); /* Set MMIO Address*/
++    qtest_outl(s, 0xcf8, 0x80000818); /* Memory Bar 2 */
++    qtest_outl(s, 0xcfc, 0xff000000); /* Set RAM Address*/
++    qtest_writel(s, 0xff000000, 0xc0000024);
++    qtest_writel(s, 0xff000114, 0x00000080);
++    qtest_writel(s, 0xff00012c, 0xff000000);
++    qtest_writel(s, 0xff000004, 0xff000114);
++    qtest_writel(s, 0xff000008, 0xff100014);
++    qtest_writel(s, 0xff10002f, 0x000000ff);
++
++    qtest_quit(s);
++}
++
++/*
++ * This used to trigger a UAF in lsi_do_msgout()
++ * https://gitlab.com/qemu-project/qemu/-/issues/972
++ */
++static void test_lsi_do_msgout_cancel_req(void)
++{
++    QTestState *s;
++
++    if (sizeof(void *) == 4) {
++        g_test_skip("memory size too big for 32-bit build");
++        return;
++    }
++
++    s = qtest_init("-M q35 -m 2G -nodefaults "
++                   "-device lsi53c895a,id=scsi "
++                   "-device scsi-hd,drive=disk0 "
++                   "-drive file=null-co://,id=disk0,if=none,format=raw");
++
++    qtest_outl(s, 0xcf8, 0x80000810);
++    qtest_outl(s, 0xcf8, 0xc000);
++    qtest_outl(s, 0xcf8, 0x80000810);
++    qtest_outw(s, 0xcfc, 0x7);
++    qtest_outl(s, 0xcf8, 0x80000810);
++    qtest_outl(s, 0xcfc, 0xc000);
++    qtest_outl(s, 0xcf8, 0x80000804);
++    qtest_outw(s, 0xcfc, 0x05);
++    qtest_writeb(s, 0x69736c10, 0x08);
++    qtest_writeb(s, 0x69736c13, 0x58);
++    qtest_writeb(s, 0x69736c1a, 0x01);
++    qtest_writeb(s, 0x69736c1b, 0x06);
++    qtest_writeb(s, 0x69736c22, 0x01);
++    qtest_writeb(s, 0x69736c23, 0x07);
++    qtest_writeb(s, 0x69736c2b, 0x02);
++    qtest_writeb(s, 0x69736c48, 0x08);
++    qtest_writeb(s, 0x69736c4b, 0x58);
++    qtest_writeb(s, 0x69736c52, 0x04);
++    qtest_writeb(s, 0x69736c53, 0x06);
++    qtest_writeb(s, 0x69736c5b, 0x02);
++    qtest_outl(s, 0xc02d, 0x697300);
++    qtest_writeb(s, 0x5a554662, 0x01);
++    qtest_writeb(s, 0x5a554663, 0x07);
++    qtest_writeb(s, 0x5a55466a, 0x10);
++    qtest_writeb(s, 0x5a55466b, 0x22);
++    qtest_writeb(s, 0x5a55466c, 0x5a);
++    qtest_writeb(s, 0x5a55466d, 0x5a);
++    qtest_writeb(s, 0x5a55466e, 0x34);
++    qtest_writeb(s, 0x5a55466f, 0x5a);
++    qtest_writeb(s, 0x5a345a5a, 0x77);
++    qtest_writeb(s, 0x5a345a5b, 0x55);
++    qtest_writeb(s, 0x5a345a5c, 0x51);
++    qtest_writeb(s, 0x5a345a5d, 0x27);
++    qtest_writeb(s, 0x27515577, 0x41);
++    qtest_outl(s, 0xc02d, 0x5a5500);
++    qtest_writeb(s, 0x364001d0, 0x08);
++    qtest_writeb(s, 0x364001d3, 0x58);
++    qtest_writeb(s, 0x364001da, 0x01);
++    qtest_writeb(s, 0x364001db, 0x26);
++    qtest_writeb(s, 0x364001dc, 0x0d);
++    qtest_writeb(s, 0x364001dd, 0xae);
++    qtest_writeb(s, 0x364001de, 0x41);
++    qtest_writeb(s, 0x364001df, 0x5a);
++    qtest_writeb(s, 0x5a41ae0d, 0xf8);
++    qtest_writeb(s, 0x5a41ae0e, 0x36);
++    qtest_writeb(s, 0x5a41ae0f, 0xd7);
++    qtest_writeb(s, 0x5a41ae10, 0x36);
++    qtest_writeb(s, 0x36d736f8, 0x0c);
++    qtest_writeb(s, 0x36d736f9, 0x80);
++    qtest_writeb(s, 0x36d736fa, 0x0d);
++    qtest_outl(s, 0xc02d, 0x364000);
++
++    qtest_quit(s);
++}
++
++/*
++ * This used to trigger the assert in lsi_do_dma()
++ * https://bugs.launchpad.net/qemu/+bug/697510
++ * https://bugs.launchpad.net/qemu/+bug/1905521
++ * https://bugs.launchpad.net/qemu/+bug/1908515
++ */
++static void test_lsi_do_dma_empty_queue(void)
++{
++    QTestState *s;
++
++    s = qtest_init("-M q35 -nographic -monitor none -serial none "
++                   "-drive if=none,id=drive0,"
++                            "file=null-co://,file.read-zeroes=on,format=raw "
++                   "-device lsi53c895a,id=scsi0 "
++                   "-device scsi-hd,drive=drive0,"
++                            "bus=scsi0.0,channel=0,scsi-id=0,lun=0");
++    qtest_outl(s, 0xcf8, 0x80001814);
++    qtest_outl(s, 0xcfc, 0xe1068000);
++    qtest_outl(s, 0xcf8, 0x80001818);
++    qtest_outl(s, 0xcf8, 0x80001804);
++    qtest_outw(s, 0xcfc, 0x7);
++    qtest_outl(s, 0xcf8, 0x80002010);
++
++    qtest_writeb(s, 0xe106802e, 0xff); /* Fill DSP bits 16-23 */
++    qtest_writeb(s, 0xe106802f, 0xff); /* Fill DSP bits 24-31: trigger SCRIPT */
++
++    qtest_quit(s);
++}
++
++int main(int argc, char **argv)
++{
++    g_test_init(&argc, &argv, NULL);
++
++    if (!qtest_has_device("lsi53c895a")) {
++        return 0;
++    }
++
++    qtest_add_func("fuzz/lsi53c895a/lsi_do_dma_empty_queue",
++                   test_lsi_do_dma_empty_queue);
++
++    qtest_add_func("fuzz/lsi53c895a/lsi_do_msgout_cancel_req",
++                   test_lsi_do_msgout_cancel_req);
++
++    qtest_add_func("fuzz/lsi53c895a/lsi_dma_reentrancy",
++                   test_lsi_dma_reentrancy);
++
++    return g_test_run();
++}
+-- 
+2.37.3
+

SOURCES/kvm-i386-cpu-Update-how-the-EBX-register-of-CPUID-0x8000.patch

@@ -0,0 +1,53 @@
+From 18ac13c7d64266238bd44b2188e0d044af3c3377 Mon Sep 17 00:00:00 2001
+From: Bandan Das <bsd@redhat.com>
+Date: Thu, 3 Aug 2023 15:14:14 -0400
+Subject: [PATCH 4/5] i386/cpu: Update how the EBX register of CPUID 0x8000001F
+ is set
+
+RH-Author: Bandan Das <None>
+RH-MergeRequest: 296: Updates to SEV reduced-phys-bits parameter
+RH-Bugzilla: 2214840
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+RH-Commit: [4/4] 8b236fd9bc4c177bfacf6220a429e711b5bf062e
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2214840
+
+commit fb6bbafc0f19385fb257ee073ed13dcaf613f2f8
+Author: Tom Lendacky <thomas.lendacky@amd.com>
+Date:   Fri Sep 30 10:14:30 2022 -0500
+
+    i386/cpu: Update how the EBX register of CPUID 0x8000001F is set
+
+    Update the setting of CPUID 0x8000001F EBX to clearly document the ranges
+    associated with fields being set.
+
+    Fixes: 6cb8f2a663 ("cpu/i386: populate CPUID 0x8000_001F when SEV is active")
+    Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
+    Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+    Message-Id: <5822fd7d02b575121380e1f493a8f6d9eba2b11a.1664550870.git.thomas.lendacky@amd.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Bandan Das <bsd@redhat.com>
+---
+ target/i386/cpu.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/target/i386/cpu.c b/target/i386/cpu.c
+index 9d3dcdcc0d..265f0aadfc 100644
+--- a/target/i386/cpu.c
++++ b/target/i386/cpu.c
+@@ -5836,8 +5836,8 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
+         if (sev_enabled()) {
+             *eax = 0x2;
+             *eax |= sev_es_enabled() ? 0x8 : 0;
+-            *ebx = sev_get_cbit_position();
+-            *ebx |= sev_get_reduced_phys_bits() << 6;
++            *ebx = sev_get_cbit_position() & 0x3f; /* EBX[5:0] */
++            *ebx |= (sev_get_reduced_phys_bits() & 0x3f) << 6; /* EBX[11:6] */
+         }
+         break;
+     default:
+-- 
+2.37.3
+

SOURCES/kvm-i386-do-kvm_put_msr_feature_control-first-thing-when.patch

@@ -1,16 +1,15 @@
-From 1bd939d374ec2e994ff47c84e16fa3bc1323a0fd Mon Sep 17 00:00:00 2001
+From f96220d64a31a4a52b2d132a503048579946f982 Mon Sep 17 00:00:00 2001
 From: Vitaly Kuznetsov <vkuznets@redhat.com>
 Date: Thu, 18 Aug 2022 17:01:13 +0200
-Subject: [PATCH 2/2] i386: do kvm_put_msr_feature_control() first thing when
+Subject: [PATCH 3/3] i386: do kvm_put_msr_feature_control() first thing when
  vCPU is reset
 
-RH-Author: Vitaly Kuznetsov <vkuznets@redhat.com>
-RH-MergeRequest: 216: i386: fix 'system_reset' when the VM is in VMX root operation
-RH-Bugzilla: 2116743
-RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
-RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
-RH-Acked-by: Peter Xu <peterx@redhat.com>
-RH-Commit: [2/2] f838a57f74487eb394794de00006d5d2b9e84344
+RH-Author: Miroslav Rezanina <mrezanin@redhat.com>
+RH-MergeRequest: 219: Synchronize qemu-6.2.0-20.el8.1 build from RHEL 8.7 to RHEL 8.8
+RH-Bugzilla: 2125271
+RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [2/2] 08e1e67db96801e4a35aa6b60a93b2c2f1641220
 
 kvm_put_sregs2() fails to reset 'locked' CR4/CR0 bits upon vCPU reset when
 it is in VMX root operation. Do kvm_put_msr_feature_control() before
@@ -64,5 +63,5 @@ index 81d729dc40..a06221d3e5 100644
  
      if (level == KVM_PUT_FULL_STATE) {
 -- 
-2.31.1
+2.35.3
 

SOURCES/kvm-i386-reset-KVM-nested-state-upon-CPU-reset.patch

@@ -1,15 +1,14 @@
-From 4ad00e318f8afbee0e455cfbb6bc693c808d87f3 Mon Sep 17 00:00:00 2001
+From 46e54544c3480658111d6f111d6c265dcea2e19b Mon Sep 17 00:00:00 2001
 From: Vitaly Kuznetsov <vkuznets@redhat.com>
 Date: Thu, 18 Aug 2022 17:01:12 +0200
-Subject: [PATCH 1/2] i386: reset KVM nested state upon CPU reset
+Subject: [PATCH 2/3] i386: reset KVM nested state upon CPU reset
 
-RH-Author: Vitaly Kuznetsov <vkuznets@redhat.com>
-RH-MergeRequest: 216: i386: fix 'system_reset' when the VM is in VMX root operation
-RH-Bugzilla: 2116743
-RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
-RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
-RH-Acked-by: Peter Xu <peterx@redhat.com>
-RH-Commit: [1/2] 20d2dabeda74b8cd5135228980a2414e66dc64f3
+RH-Author: Miroslav Rezanina <mrezanin@redhat.com>
+RH-MergeRequest: 219: Synchronize qemu-6.2.0-20.el8.1 build from RHEL 8.7 to RHEL 8.8
+RH-Bugzilla: 2125271
+RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [1/2] de4db7bceb6baaf69aec8b0ae9aa8887aa869e15
 
 Make sure env->nested_state is cleaned up when a vCPU is reset, it may
 be stale after an incoming migration, kvm_arch_put_registers() may
@@ -91,5 +90,5 @@ index bd439e56ad..81d729dc40 100644
  }
  
 -- 
-2.31.1
+2.35.3
 

SOURCES/kvm-i386-sev-Update-checks-and-information-related-to-re.patch

@@ -0,0 +1,78 @@
+From 19504ea76b6341c11213316402bb5194487e1f01 Mon Sep 17 00:00:00 2001
+From: Bandan Das <bsd@redhat.com>
+Date: Thu, 3 Aug 2023 15:13:19 -0400
+Subject: [PATCH 3/5] i386/sev: Update checks and information related to
+ reduced-phys-bits
+
+RH-Author: Bandan Das <None>
+RH-MergeRequest: 296: Updates to SEV reduced-phys-bits parameter
+RH-Bugzilla: 2214840
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+RH-Commit: [3/4] b617173d2b15fa39cdc02b5c1ac4d52e9b0dfede
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2214840
+
+commit 8168fed9f84e3128f7628969ae78af49433d5ce7
+Author: Tom Lendacky <thomas.lendacky@amd.com>
+Date:   Fri Sep 30 10:14:29 2022 -0500
+
+    i386/sev: Update checks and information related to reduced-phys-bits
+
+    The value of the reduced-phys-bits parameter is propogated to the CPUID
+    information exposed to the guest. Update the current validation check to
+    account for the size of the CPUID field (6-bits), ensuring the value is
+    in the range of 1 to 63.
+
+    Maintain backward compatibility, to an extent, by allowing a value greater
+    than 1 (so that the previously documented value of 5 still works), but not
+    allowing anything over 63.
+
+    Fixes: d8575c6c02 ("sev/i386: add command to initialize the memory encryption context")
+    Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
+    Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+    Message-Id: <cca5341a95ac73f904e6300f10b04f9c62e4e8ff.1664550870.git.thomas.lendacky@amd.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Bandan Das <bsd@redhat.com>
+---
+ target/i386/sev.c | 17 ++++++++++++++---
+ 1 file changed, 14 insertions(+), 3 deletions(-)
+
+diff --git a/target/i386/sev.c b/target/i386/sev.c
+index 025ff7a6f8..ba6a65e90c 100644
+--- a/target/i386/sev.c
++++ b/target/i386/sev.c
+@@ -892,15 +892,26 @@ int sev_kvm_init(ConfidentialGuestSupport *cgs, Error **errp)
+     host_cpuid(0x8000001F, 0, NULL, &ebx, NULL, NULL);
+     host_cbitpos = ebx & 0x3f;
+ 
++    /*
++     * The cbitpos value will be placed in bit positions 5:0 of the EBX
++     * register of CPUID 0x8000001F. No need to verify the range as the
++     * comparison against the host value accomplishes that.
++     */
+     if (host_cbitpos != sev->cbitpos) {
+         error_setg(errp, "%s: cbitpos check failed, host '%d' requested '%d'",
+                    __func__, host_cbitpos, sev->cbitpos);
+         goto err;
+     }
+ 
+-    if (sev->reduced_phys_bits < 1) {
+-        error_setg(errp, "%s: reduced_phys_bits check failed, it should be >=1,"
+-                   " requested '%d'", __func__, sev->reduced_phys_bits);
++    /*
++     * The reduced-phys-bits value will be placed in bit positions 11:6 of
++     * the EBX register of CPUID 0x8000001F, so verify the supplied value
++     * is in the range of 1 to 63.
++     */
++    if (sev->reduced_phys_bits < 1 || sev->reduced_phys_bits > 63) {
++        error_setg(errp, "%s: reduced_phys_bits check failed,"
++                   " it should be in the range of 1 to 63, requested '%d'",
++                   __func__, sev->reduced_phys_bits);
+         goto err;
+     }
+ 
+-- 
+2.37.3
+

SOURCES/kvm-include-elf.h-add-s390x-note-types.patch

@@ -0,0 +1,43 @@
+From 3fceb3b60a60c5008eecf99e45e269b757042b5a Mon Sep 17 00:00:00 2001
+From: Janosch Frank <frankja@linux.ibm.com>
+Date: Mon, 17 Oct 2022 08:38:20 +0000
+Subject: [PATCH 39/42] include/elf.h: add s390x note types
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 226: s390: Enhanced Interpretation for PCI Functions and Secure Execution guest dump
+RH-Bugzilla: 1664378 2043909
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Commit: [39/41] ebf0873744905abbe9cfc423a56c6d1b4f2ae936
+
+Adding two s390x note types
+
+Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
+Reviewed-by: Thomas Huth <thuth@redhat.com>
+Message-Id: <20221017083822.43118-9-frankja@linux.ibm.com>
+(cherry picked from commit 5433669c7a1884cc0394c360148965edf7519884)
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ include/elf.h | 2 ++
+ 1 file changed, 2 insertions(+)
+
+diff --git a/include/elf.h b/include/elf.h
+index 811bf4a1cb..4edab8e5a2 100644
+--- a/include/elf.h
++++ b/include/elf.h
+@@ -1647,6 +1647,8 @@ typedef struct elf64_shdr {
+ #define NT_TASKSTRUCT	4
+ #define NT_AUXV		6
+ #define NT_PRXFPREG     0x46e62b7f      /* copied from gdb5.1/include/elf/common.h */
++#define NT_S390_PV_CPU_DATA	0x30e	/* s390 protvirt cpu dump data */
++#define NT_S390_RI_CB	0x30d		/* s390 runtime instrumentation */
+ #define NT_S390_GS_CB   0x30b           /* s390 guarded storage registers */
+ #define NT_S390_VXRS_HIGH 0x30a         /* s390 vector registers 16-31 */
+ #define NT_S390_VXRS_LOW  0x309         /* s390 vector registers 0-15 (lower half) */
+-- 
+2.37.3
+

SOURCES/kvm-io-Add-support-for-MSG_PEEK-for-socket-channel.patch

@@ -0,0 +1,367 @@
+From 88b5e059462a72ca758d84c0d4d0895a03baac50 Mon Sep 17 00:00:00 2001
+From: "manish.mishra" <manish.mishra@nutanix.com>
+Date: Tue, 20 Dec 2022 18:44:17 +0000
+Subject: [PATCH 1/3] io: Add support for MSG_PEEK for socket channel
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Peter Xu <peterx@redhat.com>
+RH-MergeRequest: 258: migration: Fix multifd crash due to channel disorder
+RH-Bugzilla: 2137740
+RH-Acked-by: quintela1 <quintela@redhat.com>
+RH-Acked-by: Leonardo Brás <leobras@redhat.com>
+RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+RH-Commit: [1/2] 04fc6fae358599b8509f5355469d2e8720f01903
+
+Conflicts:
+	io/channel-null.c
+	migration/channel-block.c
+
+        Because these two files do not exist in rhel8.8 tree, dropping the
+        changes.
+
+MSG_PEEK peeks at the channel, The data is treated as unread and
+the next read shall still return this data. This support is
+currently added only for socket class. Extra parameter 'flags'
+is added to io_readv calls to pass extra read flags like MSG_PEEK.
+
+Reviewed-by: Peter Xu <peterx@redhat.com>
+Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
+Reviewed-by: Juan Quintela <quintela@redhat.com>
+Suggested-by: Daniel P. Berrange <berrange@redhat.com>
+Signed-off-by: manish.mishra <manish.mishra@nutanix.com>
+Signed-off-by: Juan Quintela <quintela@redhat.com>
+(cherry picked from commit 84615a19ddf2bfb38d7b3a0d487d2397ee55e4f3)
+Signed-off-by: Peter Xu <peterx@redhat.com>
+---
+ chardev/char-socket.c               |  4 ++--
+ include/io/channel.h                |  6 ++++++
+ io/channel-buffer.c                 |  1 +
+ io/channel-command.c                |  1 +
+ io/channel-file.c                   |  1 +
+ io/channel-socket.c                 | 19 ++++++++++++++++++-
+ io/channel-tls.c                    |  1 +
+ io/channel-websock.c                |  1 +
+ io/channel.c                        | 16 ++++++++++++----
+ migration/rdma.c                    |  1 +
+ scsi/qemu-pr-helper.c               |  2 +-
+ tests/qtest/tpm-emu.c               |  2 +-
+ tests/unit/test-io-channel-socket.c |  1 +
+ util/vhost-user-server.c            |  2 +-
+ 14 files changed, 48 insertions(+), 10 deletions(-)
+
+diff --git a/chardev/char-socket.c b/chardev/char-socket.c
+index 836cfa0bc2..4cdf79e0c2 100644
+--- a/chardev/char-socket.c
++++ b/chardev/char-socket.c
+@@ -339,11 +339,11 @@ static ssize_t tcp_chr_recv(Chardev *chr, char *buf, size_t len)
+     if (qio_channel_has_feature(s->ioc, QIO_CHANNEL_FEATURE_FD_PASS)) {
+         ret = qio_channel_readv_full(s->ioc, &iov, 1,
+                                      &msgfds, &msgfds_num,
+-                                     NULL);
++                                     0, NULL);
+     } else {
+         ret = qio_channel_readv_full(s->ioc, &iov, 1,
+                                      NULL, NULL,
+-                                     NULL);
++                                     0, NULL);
+     }
+ 
+     if (ret == QIO_CHANNEL_ERR_BLOCK) {
+diff --git a/include/io/channel.h b/include/io/channel.h
+index c680ee7480..716235d496 100644
+--- a/include/io/channel.h
++++ b/include/io/channel.h
+@@ -34,6 +34,8 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass,
+ 
+ #define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1
+ 
++#define QIO_CHANNEL_READ_FLAG_MSG_PEEK 0x1
++
+ typedef enum QIOChannelFeature QIOChannelFeature;
+ 
+ enum QIOChannelFeature {
+@@ -41,6 +43,7 @@ enum QIOChannelFeature {
+     QIO_CHANNEL_FEATURE_SHUTDOWN,
+     QIO_CHANNEL_FEATURE_LISTEN,
+     QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
++    QIO_CHANNEL_FEATURE_READ_MSG_PEEK,
+ };
+ 
+ 
+@@ -114,6 +117,7 @@ struct QIOChannelClass {
+                         size_t niov,
+                         int **fds,
+                         size_t *nfds,
++                        int flags,
+                         Error **errp);
+     int (*io_close)(QIOChannel *ioc,
+                     Error **errp);
+@@ -188,6 +192,7 @@ void qio_channel_set_name(QIOChannel *ioc,
+  * @niov: the length of the @iov array
+  * @fds: pointer to an array that will received file handles
+  * @nfds: pointer filled with number of elements in @fds on return
++ * @flags: read flags (QIO_CHANNEL_READ_FLAG_*)
+  * @errp: pointer to a NULL-initialized error object
+  *
+  * Read data from the IO channel, storing it in the
+@@ -224,6 +229,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
+                                size_t niov,
+                                int **fds,
+                                size_t *nfds,
++                               int flags,
+                                Error **errp);
+ 
+ 
+diff --git a/io/channel-buffer.c b/io/channel-buffer.c
+index bf52011be2..8096180f85 100644
+--- a/io/channel-buffer.c
++++ b/io/channel-buffer.c
+@@ -54,6 +54,7 @@ static ssize_t qio_channel_buffer_readv(QIOChannel *ioc,
+                                         size_t niov,
+                                         int **fds,
+                                         size_t *nfds,
++                                        int flags,
+                                         Error **errp)
+ {
+     QIOChannelBuffer *bioc = QIO_CHANNEL_BUFFER(ioc);
+diff --git a/io/channel-command.c b/io/channel-command.c
+index 5ff1691bad..2834413b3a 100644
+--- a/io/channel-command.c
++++ b/io/channel-command.c
+@@ -230,6 +230,7 @@ static ssize_t qio_channel_command_readv(QIOChannel *ioc,
+                                          size_t niov,
+                                          int **fds,
+                                          size_t *nfds,
++                                         int flags,
+                                          Error **errp)
+ {
+     QIOChannelCommand *cioc = QIO_CHANNEL_COMMAND(ioc);
+diff --git a/io/channel-file.c b/io/channel-file.c
+index 348a48545e..490f0e5d84 100644
+--- a/io/channel-file.c
++++ b/io/channel-file.c
+@@ -86,6 +86,7 @@ static ssize_t qio_channel_file_readv(QIOChannel *ioc,
+                                       size_t niov,
+                                       int **fds,
+                                       size_t *nfds,
++                                      int flags,
+                                       Error **errp)
+ {
+     QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
+diff --git a/io/channel-socket.c b/io/channel-socket.c
+index 6010ad7017..ca8b180b69 100644
+--- a/io/channel-socket.c
++++ b/io/channel-socket.c
+@@ -174,6 +174,9 @@ int qio_channel_socket_connect_sync(QIOChannelSocket *ioc,
+     }
+ #endif
+ 
++    qio_channel_set_feature(QIO_CHANNEL(ioc),
++                            QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
++
+     return 0;
+ }
+ 
+@@ -407,6 +410,9 @@ qio_channel_socket_accept(QIOChannelSocket *ioc,
+     }
+ #endif /* WIN32 */
+ 
++    qio_channel_set_feature(QIO_CHANNEL(cioc),
++                            QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
++
+     trace_qio_channel_socket_accept_complete(ioc, cioc, cioc->fd);
+     return cioc;
+ 
+@@ -497,6 +503,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
+                                         size_t niov,
+                                         int **fds,
+                                         size_t *nfds,
++                                        int flags,
+                                         Error **errp)
+ {
+     QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
+@@ -518,6 +525,10 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
+ 
+     }
+ 
++    if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) {
++        sflags |= MSG_PEEK;
++    }
++
+  retry:
+     ret = recvmsg(sioc->fd, &msg, sflags);
+     if (ret < 0) {
+@@ -625,11 +636,17 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
+                                         size_t niov,
+                                         int **fds,
+                                         size_t *nfds,
++                                        int flags,
+                                         Error **errp)
+ {
+     QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
+     ssize_t done = 0;
+     ssize_t i;
++    int sflags = 0;
++
++    if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) {
++        sflags |= MSG_PEEK;
++    }
+ 
+     for (i = 0; i < niov; i++) {
+         ssize_t ret;
+@@ -637,7 +654,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
+         ret = recv(sioc->fd,
+                    iov[i].iov_base,
+                    iov[i].iov_len,
+-                   0);
++                   sflags);
+         if (ret < 0) {
+             if (errno == EAGAIN) {
+                 if (done) {
+diff --git a/io/channel-tls.c b/io/channel-tls.c
+index 4ce890a538..c730cb8ec5 100644
+--- a/io/channel-tls.c
++++ b/io/channel-tls.c
+@@ -260,6 +260,7 @@ static ssize_t qio_channel_tls_readv(QIOChannel *ioc,
+                                      size_t niov,
+                                      int **fds,
+                                      size_t *nfds,
++                                     int flags,
+                                      Error **errp)
+ {
+     QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc);
+diff --git a/io/channel-websock.c b/io/channel-websock.c
+index 035dd6075b..13c94f2afe 100644
+--- a/io/channel-websock.c
++++ b/io/channel-websock.c
+@@ -1081,6 +1081,7 @@ static ssize_t qio_channel_websock_readv(QIOChannel *ioc,
+                                          size_t niov,
+                                          int **fds,
+                                          size_t *nfds,
++                                         int flags,
+                                          Error **errp)
+ {
+     QIOChannelWebsock *wioc = QIO_CHANNEL_WEBSOCK(ioc);
+diff --git a/io/channel.c b/io/channel.c
+index 0640941ac5..a8c7f11649 100644
+--- a/io/channel.c
++++ b/io/channel.c
+@@ -52,6 +52,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
+                                size_t niov,
+                                int **fds,
+                                size_t *nfds,
++                               int flags,
+                                Error **errp)
+ {
+     QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
+@@ -63,7 +64,14 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
+         return -1;
+     }
+ 
+-    return klass->io_readv(ioc, iov, niov, fds, nfds, errp);
++    if ((flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) &&
++        !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) {
++        error_setg_errno(errp, EINVAL,
++                         "Channel does not support peek read");
++        return -1;
++    }
++
++    return klass->io_readv(ioc, iov, niov, fds, nfds, flags, errp);
+ }
+ 
+ 
+@@ -146,7 +154,7 @@ int qio_channel_readv_full_all_eof(QIOChannel *ioc,
+     while ((nlocal_iov > 0) || local_fds) {
+         ssize_t len;
+         len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds,
+-                                     local_nfds, errp);
++                                     local_nfds, 0, errp);
+         if (len == QIO_CHANNEL_ERR_BLOCK) {
+             if (qemu_in_coroutine()) {
+                 qio_channel_yield(ioc, G_IO_IN);
+@@ -284,7 +292,7 @@ ssize_t qio_channel_readv(QIOChannel *ioc,
+                           size_t niov,
+                           Error **errp)
+ {
+-    return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, errp);
++    return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, 0, errp);
+ }
+ 
+ 
+@@ -303,7 +311,7 @@ ssize_t qio_channel_read(QIOChannel *ioc,
+                          Error **errp)
+ {
+     struct iovec iov = { .iov_base = buf, .iov_len = buflen };
+-    return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, errp);
++    return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, 0, errp);
+ }
+ 
+ 
+diff --git a/migration/rdma.c b/migration/rdma.c
+index 54acd2000e..dcf98bd7f8 100644
+--- a/migration/rdma.c
++++ b/migration/rdma.c
+@@ -2917,6 +2917,7 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc,
+                                       size_t niov,
+                                       int **fds,
+                                       size_t *nfds,
++                                      int flags,
+                                       Error **errp)
+ {
+     QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
+diff --git a/scsi/qemu-pr-helper.c b/scsi/qemu-pr-helper.c
+index f281daeced..12ec8e9368 100644
+--- a/scsi/qemu-pr-helper.c
++++ b/scsi/qemu-pr-helper.c
+@@ -612,7 +612,7 @@ static int coroutine_fn prh_read(PRHelperClient *client, void *buf, int sz,
+         iov.iov_base = buf;
+         iov.iov_len = sz;
+         n_read = qio_channel_readv_full(QIO_CHANNEL(client->ioc), &iov, 1,
+-                                        &fds, &nfds, errp);
++                                        &fds, &nfds, 0, errp);
+ 
+         if (n_read == QIO_CHANNEL_ERR_BLOCK) {
+             qio_channel_yield(QIO_CHANNEL(client->ioc), G_IO_IN);
+diff --git a/tests/qtest/tpm-emu.c b/tests/qtest/tpm-emu.c
+index 2994d1cf42..3cf1acaf7d 100644
+--- a/tests/qtest/tpm-emu.c
++++ b/tests/qtest/tpm-emu.c
+@@ -106,7 +106,7 @@ void *tpm_emu_ctrl_thread(void *data)
+         int *pfd = NULL;
+         size_t nfd = 0;
+ 
+-        qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, &error_abort);
++        qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, 0, &error_abort);
+         cmd = be32_to_cpu(cmd);
+         g_assert_cmpint(cmd, ==, CMD_SET_DATAFD);
+         g_assert_cmpint(nfd, ==, 1);
+diff --git a/tests/unit/test-io-channel-socket.c b/tests/unit/test-io-channel-socket.c
+index 6713886d02..de2930f203 100644
+--- a/tests/unit/test-io-channel-socket.c
++++ b/tests/unit/test-io-channel-socket.c
+@@ -452,6 +452,7 @@ static void test_io_channel_unix_fd_pass(void)
+                            G_N_ELEMENTS(iorecv),
+                            &fdrecv,
+                            &nfdrecv,
++                           0,
+                            &error_abort);
+ 
+     g_assert(nfdrecv == G_N_ELEMENTS(fdsend));
+diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c
+index 783d847a6d..e6a9ef72b7 100644
+--- a/util/vhost-user-server.c
++++ b/util/vhost-user-server.c
+@@ -102,7 +102,7 @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg)
+          * qio_channel_readv_full may have short reads, keeping calling it
+          * until getting VHOST_USER_HDR_SIZE or 0 bytes in total
+          */
+-        rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, &local_err);
++        rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, 0, &local_err);
+         if (rc < 0) {
+             if (rc == QIO_CHANNEL_ERR_BLOCK) {
+                 assert(local_err == NULL);
+-- 
+2.37.3
+

SOURCES/kvm-iotests-Make-144-deterministic-again.patch

@@ -0,0 +1,82 @@
+From 9b5e69ce5f4ba9541e55d801af16ece4969379e9 Mon Sep 17 00:00:00 2001
+From: Kevin Wolf <kwolf@redhat.com>
+Date: Fri, 9 Feb 2024 18:31:03 +0100
+Subject: [PATCH 4/4] iotests: Make 144 deterministic again
+
+RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
+RH-MergeRequest: 352: monitor: only run coroutine commands in qemu_aio_context
+RH-Jira: RHEL-7353
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
+RH-Commit: [4/4] 4974a32174abefb509b7c46671a364b4b991449e
+
+Since commit effd60c8 changed how QMP commands are processed, the order
+of the block-commit return value and job events in iotests 144 wasn't
+fixed and more and caused the test to fail intermittently.
+
+Change the test to cache events first and then print them in a
+predefined order.
+
+Waiting three times for JOB_STATUS_CHANGE is a bit uglier than just
+waiting for the JOB_STATUS_CHANGE that has "status": "ready", but the
+tooling we have doesn't seem to allow the latter easily.
+
+Fixes: effd60c878176bcaf97fa7ce2b12d04bb8ead6f7
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2126
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Message-id: 20240209173103.239994-1-kwolf@redhat.com
+Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
+(cherry picked from commit cc29c12ec629ba68a4a6cb7d165c94cc8502815a)
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+---
+ tests/qemu-iotests/144     | 12 +++++++++++-
+ tests/qemu-iotests/144.out |  2 +-
+ 2 files changed, 12 insertions(+), 2 deletions(-)
+
+diff --git a/tests/qemu-iotests/144 b/tests/qemu-iotests/144
+index 60e9ddd75f..8c50d6487e 100755
+--- a/tests/qemu-iotests/144
++++ b/tests/qemu-iotests/144
+@@ -83,12 +83,22 @@ echo
+ echo === Performing block-commit on active layer ===
+ echo
+ 
++capture_events="BLOCK_JOB_READY JOB_STATUS_CHANGE"
++
+ # Block commit on active layer, push the new overlay into base
+ _send_qemu_cmd $h "{ 'execute': 'block-commit',
+                                 'arguments': {
+                                                  'device': 'virtio0'
+                                               }
+-                    }" "READY"
++                    }" "return"
++
++_wait_event $h "JOB_STATUS_CHANGE"
++_wait_event $h "JOB_STATUS_CHANGE"
++_wait_event $h "JOB_STATUS_CHANGE"
++
++_wait_event $h "BLOCK_JOB_READY"
++
++capture_events=
+ 
+ _send_qemu_cmd $h "{ 'execute': 'block-job-complete',
+                                 'arguments': {
+diff --git a/tests/qemu-iotests/144.out b/tests/qemu-iotests/144.out
+index b3b4812015..2245ddfa10 100644
+--- a/tests/qemu-iotests/144.out
++++ b/tests/qemu-iotests/144.out
+@@ -25,9 +25,9 @@ Formatting 'TEST_DIR/tmp.qcow2', fmt=qcow2 cluster_size=65536 extended_l2=off co
+                                                  'device': 'virtio0'
+                                               }
+                     }
++{"return": {}}
+ {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "virtio0"}}
+ {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "virtio0"}}
+-{"return": {}}
+ {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "virtio0"}}
+ {"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "virtio0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
+ { 'execute': 'block-job-complete',
+-- 
+2.39.3
+

SOURCES/kvm-iotests-add-filter_qmp_generated_node_ids.patch

@@ -0,0 +1,49 @@
+From f164083416a9d09712b8cb8c654dd3b8988e6c5c Mon Sep 17 00:00:00 2001
+From: Stefan Hajnoczi <stefanha@redhat.com>
+Date: Thu, 18 Jan 2024 09:48:21 -0500
+Subject: [PATCH 1/4] iotests: add filter_qmp_generated_node_ids()
+
+RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
+RH-MergeRequest: 352: monitor: only run coroutine commands in qemu_aio_context
+RH-Jira: RHEL-7353
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
+RH-Commit: [1/4] cc276c8ef9e140203afc19fcd8b5b8e20577054d
+
+Add a filter function for QMP responses that contain QEMU's
+automatically generated node ids. The ids change between runs and must
+be masked in the reference output.
+
+The next commit will use this new function.
+
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+Message-ID: <20240118144823.1497953-2-stefanha@redhat.com>
+Reviewed-by: Kevin Wolf <kwolf@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit da62b507a20510d819bcfbe8f5e573409b954006)
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+---
+ tests/qemu-iotests/iotests.py | 7 +++++++
+ 1 file changed, 7 insertions(+)
+
+diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
+index 2ef493755c..fd41f93421 100644
+--- a/tests/qemu-iotests/iotests.py
++++ b/tests/qemu-iotests/iotests.py
+@@ -521,6 +521,13 @@ def _filter(_key, value):
+ def filter_generated_node_ids(msg):
+     return re.sub("#block[0-9]+", "NODE_NAME", msg)
+ 
++def filter_qmp_generated_node_ids(qmsg):
++    def _filter(_key, value):
++        if is_str(value):
++            return filter_generated_node_ids(value)
++        return value
++    return filter_qmp(qmsg, _filter)
++
+ def filter_img_info(output, filename):
+     lines = []
+     for line in output.split('\n'):
+-- 
+2.39.3
+

SOURCES/kvm-iotests-iov-padding-New-test.patch

@@ -0,0 +1,187 @@
+From 084e211448f40c3e9d9b1907f6c98dca9f998bc3 Mon Sep 17 00:00:00 2001
+From: Hanna Czenczek <hreitz@redhat.com>
+Date: Tue, 11 Apr 2023 19:34:18 +0200
+Subject: [PATCH 4/5] iotests/iov-padding: New test
+
+RH-Author: Hanna Czenczek <hreitz@redhat.com>
+RH-MergeRequest: 291: block: Split padded I/O vectors exceeding IOV_MAX
+RH-Bugzilla: 2141964
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Commit: [4/5] a80be9c26ebd5503745989cd6823cb4814264258
+
+Test that even vectored IO requests with 1024 vector elements that are
+not aligned to the device's request alignment will succeed.
+
+Reviewed-by: Eric Blake <eblake@redhat.com>
+Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+Message-Id: <20230411173418.19549-5-hreitz@redhat.com>
+(cherry picked from commit d7e1905e3f54ff9512db4c7a946a8603b62b108d)
+Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
+---
+ tests/qemu-iotests/tests/iov-padding     | 85 ++++++++++++++++++++++++
+ tests/qemu-iotests/tests/iov-padding.out | 59 ++++++++++++++++
+ 2 files changed, 144 insertions(+)
+ create mode 100755 tests/qemu-iotests/tests/iov-padding
+ create mode 100644 tests/qemu-iotests/tests/iov-padding.out
+
+diff --git a/tests/qemu-iotests/tests/iov-padding b/tests/qemu-iotests/tests/iov-padding
+new file mode 100755
+index 0000000000..b9604900c7
+--- /dev/null
++++ b/tests/qemu-iotests/tests/iov-padding
+@@ -0,0 +1,85 @@
++#!/usr/bin/env bash
++# group: rw quick
++#
++# Check the interaction of request padding (to fit alignment restrictions) with
++# vectored I/O from the guest
++#
++# Copyright Red Hat
++#
++# 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/>.
++#
++
++seq=$(basename $0)
++echo "QA output created by $seq"
++
++status=1	# failure is the default!
++
++_cleanup()
++{
++    _cleanup_test_img
++}
++trap "_cleanup; exit \$status" 0 1 2 3 15
++
++# get standard environment, filters and checks
++cd ..
++. ./common.rc
++. ./common.filter
++
++_supported_fmt raw
++_supported_proto file
++
++_make_test_img 1M
++
++IMGSPEC="driver=blkdebug,align=4096,image.driver=file,image.filename=$TEST_IMG"
++
++# Four combinations:
++# - Offset 4096, length 1023 * 512 + 512: Fully aligned to 4k
++# - Offset 4096, length 1023 * 512 + 4096: Head is aligned, tail is not
++# - Offset 512, length 1023 * 512 + 512: Neither head nor tail are aligned
++# - Offset 512, length 1023 * 512 + 4096: Tail is aligned, head is not
++for start_offset in 4096 512; do
++    for last_element_length in 512 4096; do
++        length=$((1023 * 512 + $last_element_length))
++
++        echo
++        echo "== performing 1024-element vectored requests to image (offset: $start_offset; length: $length) =="
++
++        # Fill with data for testing
++        $QEMU_IO -c 'write -P 1 0 1M' "$TEST_IMG" | _filter_qemu_io
++
++        # 1023 512-byte buffers, and then one with length $last_element_length
++        cmd_params="-P 2 $start_offset $(yes 512 | head -n 1023 | tr '\n' ' ') $last_element_length"
++        QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS_NO_FMT" $QEMU_IO \
++            -c "writev $cmd_params" \
++            --image-opts \
++            "$IMGSPEC" \
++            | _filter_qemu_io
++
++        # Read all patterns -- read the part we just wrote with writev twice,
++        # once "normally", and once with a readv, so we see that that works, too
++        QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS_NO_FMT" $QEMU_IO \
++            -c "read -P 1 0 $start_offset" \
++            -c "read -P 2 $start_offset $length" \
++            -c "readv $cmd_params" \
++            -c "read -P 1 $((start_offset + length)) $((1024 * 1024 - length - start_offset))" \
++            --image-opts \
++            "$IMGSPEC" \
++            | _filter_qemu_io
++    done
++done
++
++# success, all done
++echo "*** done"
++rm -f $seq.full
++status=0
+diff --git a/tests/qemu-iotests/tests/iov-padding.out b/tests/qemu-iotests/tests/iov-padding.out
+new file mode 100644
+index 0000000000..e07a91fac7
+--- /dev/null
++++ b/tests/qemu-iotests/tests/iov-padding.out
+@@ -0,0 +1,59 @@
++QA output created by iov-padding
++Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
++
++== performing 1024-element vectored requests to image (offset: 4096; length: 524288) ==
++wrote 1048576/1048576 bytes at offset 0
++1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++wrote 524288/524288 bytes at offset 4096
++512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 4096/4096 bytes at offset 0
++4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 524288/524288 bytes at offset 4096
++512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 524288/524288 bytes at offset 4096
++512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 520192/520192 bytes at offset 528384
++508 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++
++== performing 1024-element vectored requests to image (offset: 4096; length: 527872) ==
++wrote 1048576/1048576 bytes at offset 0
++1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++wrote 527872/527872 bytes at offset 4096
++515.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 4096/4096 bytes at offset 0
++4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 527872/527872 bytes at offset 4096
++515.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 527872/527872 bytes at offset 4096
++515.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 516608/516608 bytes at offset 531968
++504.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++
++== performing 1024-element vectored requests to image (offset: 512; length: 524288) ==
++wrote 1048576/1048576 bytes at offset 0
++1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++wrote 524288/524288 bytes at offset 512
++512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 512/512 bytes at offset 0
++512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 524288/524288 bytes at offset 512
++512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 524288/524288 bytes at offset 512
++512 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 523776/523776 bytes at offset 524800
++511.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++
++== performing 1024-element vectored requests to image (offset: 512; length: 527872) ==
++wrote 1048576/1048576 bytes at offset 0
++1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++wrote 527872/527872 bytes at offset 512
++515.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 512/512 bytes at offset 0
++512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 527872/527872 bytes at offset 512
++515.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 527872/527872 bytes at offset 512
++515.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++read 520192/520192 bytes at offset 528384
++508 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++*** done
+-- 
+2.39.3
+

SOURCES/kvm-iotests-port-141-to-Python-for-reliable-QMP-testing.patch

@@ -0,0 +1,601 @@
+From 968c8ff7ea7d43bf29d8e5f6e9e17f84168c22c4 Mon Sep 17 00:00:00 2001
+From: Stefan Hajnoczi <stefanha@redhat.com>
+Date: Thu, 18 Jan 2024 09:48:22 -0500
+Subject: [PATCH 2/4] iotests: port 141 to Python for reliable QMP testing
+
+RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
+RH-MergeRequest: 352: monitor: only run coroutine commands in qemu_aio_context
+RH-Jira: RHEL-7353
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
+RH-Commit: [2/4] ff0899262544b1b61b4c7de2eb798b664fe5202e
+
+The common.qemu bash functions allow tests to interact with the QMP
+monitor of a QEMU process. I spent two days trying to update 141 when
+the order of the test output changed, but found it would still fail
+occassionally because printf() and QMP events race with synchronous QMP
+communication.
+
+I gave up and ported 141 to the existing Python API for QMP tests. The
+Python API is less affected by the order in which QEMU prints output
+because it does not print all QMP traffic by default.
+
+The next commit changes the order in which QMP messages are received.
+Make 141 reliable first.
+
+Cc: Hanna Czenczek <hreitz@redhat.com>
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+Message-ID: <20240118144823.1497953-3-stefanha@redhat.com>
+Reviewed-by: Kevin Wolf <kwolf@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit 9ee2dd4c22a3639c5462b3fc20df60c005c3de64)
+Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+
+Conflicts:
+  tests/qemu-iotests/141
+  tests/qemu-iotests/141.out
+
+  This commit replaces these files anyway, so apply our changes instead
+  of dragging in more dependencies to resolve context conflicts.
+---
+ tests/qemu-iotests/141     | 307 ++++++++++++++++---------------------
+ tests/qemu-iotests/141.out | 204 ++++++------------------
+ 2 files changed, 178 insertions(+), 333 deletions(-)
+
+diff --git a/tests/qemu-iotests/141 b/tests/qemu-iotests/141
+index 115cc1691e..a7d3985a02 100755
+--- a/tests/qemu-iotests/141
++++ b/tests/qemu-iotests/141
+@@ -1,9 +1,12 @@
+-#!/usr/bin/env bash
++#!/usr/bin/env python3
+ # group: rw auto quick
+ #
+ # Test case for ejecting BDSs with block jobs still running on them
+ #
+-# Copyright (C) 2016 Red Hat, Inc.
++# Originally written in bash by Hanna Czenczek, ported to Python by Stefan
++# Hajnoczi.
++#
++# Copyright Red Hat
+ #
+ # 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
+@@ -19,177 +22,129 @@
+ # along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ #
+ 
+-# creator
+-owner=mreitz@redhat.com
+-
+-seq="$(basename $0)"
+-echo "QA output created by $seq"
+-
+-status=1	# failure is the default!
+-
+-_cleanup()
+-{
+-    _cleanup_qemu
+-    _cleanup_test_img
+-    for img in "$TEST_DIR"/{b,m,o}.$IMGFMT; do
+-        _rm_test_img "$img"
+-    done
+-}
+-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
+-
+-
+-test_blockjob()
+-{
+-    _send_qemu_cmd $QEMU_HANDLE \
+-        "{'execute': 'blockdev-add',
+-          'arguments': {
+-              'node-name': 'drv0',
+-              'driver': '$IMGFMT',
+-              'file': {
+-                  'driver': 'file',
+-                  'filename': '$TEST_IMG'
+-              }}}" \
+-        'return'
+-
+-    # If "$2" is an event, we may or may not see it before the
+-    # {"return": {}}.  Therefore, filter the {"return": {}} out both
+-    # here and in the next command.  (Naturally, if we do not see it
+-    # here, we will see it before the next command can be executed,
+-    # so it will appear in the next _send_qemu_cmd's output.)
+-    _send_qemu_cmd $QEMU_HANDLE \
+-        "$1" \
+-        "$2" \
+-        | _filter_img_create | _filter_qmp_empty_return
+-
+-    # We want this to return an error because the block job is still running
+-    _send_qemu_cmd $QEMU_HANDLE \
+-        "{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}" \
+-        'error' | _filter_generated_node_ids | _filter_qmp_empty_return
+-
+-    _send_qemu_cmd $QEMU_HANDLE \
+-        "{'execute': 'block-job-cancel',
+-          'arguments': {'device': 'job0'}}" \
+-        "$3"
+-
+-    _send_qemu_cmd $QEMU_HANDLE \
+-        "{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}" \
+-        'return'
+-}
+-
+-
+-TEST_IMG="$TEST_DIR/b.$IMGFMT" _make_test_img 1M
+-TEST_IMG="$TEST_DIR/m.$IMGFMT" _make_test_img -b "$TEST_DIR/b.$IMGFMT" -F $IMGFMT 1M
+-_make_test_img -b "$TEST_DIR/m.$IMGFMT" 1M -F $IMGFMT
+-
+-_launch_qemu -nodefaults
+-
+-_send_qemu_cmd $QEMU_HANDLE \
+-    "{'execute': 'qmp_capabilities'}" \
+-    'return'
+-
+-echo
+-echo '=== Testing drive-backup ==='
+-echo
+-
+-# drive-backup will not send BLOCK_JOB_READY by itself, and cancelling the job
+-# will consequently result in BLOCK_JOB_CANCELLED being emitted.
+-
+-test_blockjob \
+-    "{'execute': 'drive-backup',
+-      'arguments': {'job-id': 'job0',
+-                    'device': 'drv0',
+-                    'target': '$TEST_DIR/o.$IMGFMT',
+-                    'format': '$IMGFMT',
+-                    'sync': 'none'}}" \
+-    'return' \
+-    '"status": "null"'
+-
+-echo
+-echo '=== Testing drive-mirror ==='
+-echo
+-
+-# drive-mirror will send BLOCK_JOB_READY basically immediately, and cancelling
+-# the job will consequently result in BLOCK_JOB_COMPLETED being emitted.
+-
+-test_blockjob \
+-    "{'execute': 'drive-mirror',
+-      'arguments': {'job-id': 'job0',
+-                    'device': 'drv0',
+-                    'target': '$TEST_DIR/o.$IMGFMT',
+-                    'format': '$IMGFMT',
+-                    'sync': 'none'}}" \
+-    'BLOCK_JOB_READY' \
+-    '"status": "null"'
+-
+-echo
+-echo '=== Testing active block-commit ==='
+-echo
+-
+-# An active block-commit will send BLOCK_JOB_READY basically immediately, and
+-# cancelling the job will consequently result in BLOCK_JOB_COMPLETED being
+-# emitted.
+-
+-test_blockjob \
+-    "{'execute': 'block-commit',
+-      'arguments': {'job-id': 'job0', 'device': 'drv0'}}" \
+-    'BLOCK_JOB_READY' \
+-    '"status": "null"'
+-
+-echo
+-echo '=== Testing non-active block-commit ==='
+-echo
+-
+-# Give block-commit something to work on, otherwise it would be done
+-# immediately, send a BLOCK_JOB_COMPLETED and ejecting the BDS would work just
+-# fine without the block job still running.
+-
+-$QEMU_IO -c 'write 0 1M' "$TEST_DIR/m.$IMGFMT" | _filter_qemu_io
+-
+-test_blockjob \
+-    "{'execute': 'block-commit',
+-      'arguments': {'job-id': 'job0',
+-                    'device': 'drv0',
+-                    'top':    '$TEST_DIR/m.$IMGFMT',
+-                    'speed':  1}}" \
+-    'return' \
+-    '"status": "null"'
+-
+-echo
+-echo '=== Testing block-stream ==='
+-echo
+-
+-# Give block-stream something to work on, otherwise it would be done
+-# immediately, send a BLOCK_JOB_COMPLETED and ejecting the BDS would work just
+-# fine without the block job still running.
+-
+-$QEMU_IO -c 'write 0 1M' "$TEST_DIR/b.$IMGFMT" | _filter_qemu_io
+-
+-# With some data to stream (and @speed set to 1), block-stream will not complete
+-# until we send the block-job-cancel command.
+-
+-test_blockjob \
+-    "{'execute': 'block-stream',
+-      'arguments': {'job-id': 'job0',
+-                    'device': 'drv0',
+-                    'speed': 1}}" \
+-    'return' \
+-    '"status": "null"'
+-
+-_cleanup_qemu
+-
+-# success, all done
+-echo "*** done"
+-rm -f $seq.full
+-status=0
++import iotests
++
++# Common filters to mask values that vary in the test output
++QMP_FILTERS = [iotests.filter_qmp_testfiles, \
++               iotests.filter_qmp_imgfmt]
++
++
++class TestCase:
++    def __init__(self, name, vm, image_path, cancel_event):
++        self.name = name
++        self.vm = vm
++        self.image_path = image_path
++        self.cancel_event = cancel_event
++
++    def __enter__(self):
++        iotests.log(f'=== Testing {self.name} ===')
++        self.vm.qmp_log('blockdev-add', \
++                        node_name='drv0', \
++                        driver=iotests.imgfmt, \
++                        file={'driver': 'file', 'filename': self.image_path}, \
++                        filters=QMP_FILTERS)
++
++    def __exit__(self, *exc_details):
++        # This is expected to fail because the job still exists
++        self.vm.qmp_log('blockdev-del', node_name='drv0', \
++                        filters=[iotests.filter_qmp_generated_node_ids])
++
++        self.vm.qmp_log('block-job-cancel', device='job0')
++        event = self.vm.event_wait(self.cancel_event)
++        iotests.log(event, filters=[iotests.filter_qmp_event])
++
++        # This time it succeeds
++        self.vm.qmp_log('blockdev-del', node_name='drv0')
++
++        # Separate test cases in output
++        iotests.log('')
++
++
++def main() -> None:
++    with iotests.FilePath('bottom', 'middle', 'top', 'target') as \
++            (bottom_path, middle_path, top_path, target_path), \
++         iotests.VM() as vm:
++
++        iotests.log('Creating bottom <- middle <- top backing file chain...')
++        IMAGE_SIZE='1M'
++        iotests.qemu_img_create('-f', iotests.imgfmt, bottom_path, IMAGE_SIZE)
++        iotests.qemu_img_create('-f', iotests.imgfmt, \
++                                '-F', iotests.imgfmt, \
++                                '-b', bottom_path, \
++                                middle_path, \
++                                IMAGE_SIZE)
++        iotests.qemu_img_create('-f', iotests.imgfmt, \
++                                '-F', iotests.imgfmt, \
++                                '-b', middle_path, \
++                                top_path, \
++                                IMAGE_SIZE)
++
++        iotests.log('Starting VM...')
++        vm.add_args('-nodefaults')
++        vm.launch()
++
++        # drive-backup will not send BLOCK_JOB_READY by itself, and cancelling
++        # the job will consequently result in BLOCK_JOB_CANCELLED being
++        # emitted.
++        with TestCase('drive-backup', vm, top_path, 'BLOCK_JOB_CANCELLED'):
++            vm.qmp_log('drive-backup', \
++                       job_id='job0', \
++                       device='drv0', \
++                       target=target_path, \
++                       format=iotests.imgfmt, \
++                       sync='none', \
++                       filters=QMP_FILTERS)
++
++        # drive-mirror will send BLOCK_JOB_READY basically immediately, and
++        # cancelling the job will consequently result in BLOCK_JOB_COMPLETED
++        # being emitted.
++        with TestCase('drive-mirror', vm, top_path, 'BLOCK_JOB_COMPLETED'):
++            vm.qmp_log('drive-mirror', \
++                       job_id='job0', \
++                       device='drv0', \
++                       target=target_path, \
++                       format=iotests.imgfmt, \
++                       sync='none', \
++                       filters=QMP_FILTERS)
++            event = vm.event_wait('BLOCK_JOB_READY')
++            assert event is not None # silence mypy
++            iotests.log(event, filters=[iotests.filter_qmp_event])
++
++        # An active block-commit will send BLOCK_JOB_READY basically
++        # immediately, and cancelling the job will consequently result in
++        # BLOCK_JOB_COMPLETED being emitted.
++        with TestCase('active block-commit', vm, top_path, \
++                      'BLOCK_JOB_COMPLETED'):
++            vm.qmp_log('block-commit', \
++                       job_id='job0', \
++                       device='drv0')
++            event = vm.event_wait('BLOCK_JOB_READY')
++            assert event is not None # silence mypy
++            iotests.log(event, filters=[iotests.filter_qmp_event])
++
++        # Give block-commit something to work on, otherwise it would be done
++        # immediately, send a BLOCK_JOB_COMPLETED and ejecting the BDS would
++        # work just fine without the block job still running.
++        iotests.qemu_io(middle_path, '-c', f'write 0 {IMAGE_SIZE}')
++        with TestCase('non-active block-commit', vm, top_path, \
++                      'BLOCK_JOB_CANCELLED'):
++            vm.qmp_log('block-commit', \
++                       job_id='job0', \
++                       device='drv0', \
++                       top=middle_path, \
++                       speed=1, \
++                       filters=[iotests.filter_qmp_testfiles])
++
++        # Give block-stream something to work on, otherwise it would be done
++        # immediately, send a BLOCK_JOB_COMPLETED and ejecting the BDS would
++        # work just fine without the block job still running.
++        iotests.qemu_io(bottom_path, '-c', f'write 0 {IMAGE_SIZE}')
++        with TestCase('block-stream', vm, top_path, 'BLOCK_JOB_CANCELLED'):
++            vm.qmp_log('block-stream', \
++                       job_id='job0', \
++                       device='drv0', \
++                       speed=1)
++
++if __name__ == '__main__':
++    iotests.script_main(main, supported_fmts=['qcow2', 'qed'],
++                        supported_protocols=['file'])
+diff --git a/tests/qemu-iotests/141.out b/tests/qemu-iotests/141.out
+index c4c15fb275..91b7ba50af 100644
+--- a/tests/qemu-iotests/141.out
++++ b/tests/qemu-iotests/141.out
+@@ -1,179 +1,69 @@
+-QA output created by 141
+-Formatting 'TEST_DIR/b.IMGFMT', fmt=IMGFMT size=1048576
+-Formatting 'TEST_DIR/m.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/b.IMGFMT backing_fmt=IMGFMT
+-Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/m.IMGFMT backing_fmt=IMGFMT
+-{'execute': 'qmp_capabilities'}
+-{"return": {}}
+-
++Creating bottom <- middle <- top backing file chain...
++Starting VM...
+ === Testing drive-backup ===
+-
+-{'execute': 'blockdev-add',
+-          'arguments': {
+-              'node-name': 'drv0',
+-              'driver': 'IMGFMT',
+-              'file': {
+-                  'driver': 'file',
+-                  'filename': 'TEST_DIR/t.IMGFMT'
+-              }}}
+-{"return": {}}
+-{'execute': 'drive-backup',
+-'arguments': {'job-id': 'job0',
+-'device': 'drv0',
+-'target': 'TEST_DIR/o.IMGFMT',
+-'format': 'IMGFMT',
+-'sync': 'none'}}
+-Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "paused", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
++{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
++{"return": {}}
++{"execute": "drive-backup", "arguments": {"device": "drv0", "format": "IMGFMT", "job-id": "job0", "sync": "none", "target": "TEST_DIR/PID-target"}}
++{"return": {}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
+ {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: node is used as backing hd of 'NODE_NAME'"}}
+-{'execute': 'block-job-cancel',
+-          'arguments': {'device': 'job0'}}
++{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
+ {"return": {}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 0, "speed": 0, "type": "backup"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
++{"data": {"device": "job0", "len": 1048576, "offset": 0, "speed": 0, "type": "backup"}, "event": "BLOCK_JOB_CANCELLED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
+ {"return": {}}
+ 
+ === Testing drive-mirror ===
+-
+-{'execute': 'blockdev-add',
+-          'arguments': {
+-              'node-name': 'drv0',
+-              'driver': 'IMGFMT',
+-              'file': {
+-                  'driver': 'file',
+-                  'filename': 'TEST_DIR/t.IMGFMT'
+-              }}}
+-{"return": {}}
+-{'execute': 'drive-mirror',
+-'arguments': {'job-id': 'job0',
+-'device': 'drv0',
+-'target': 'TEST_DIR/o.IMGFMT',
+-'format': 'IMGFMT',
+-'sync': 'none'}}
+-Formatting 'TEST_DIR/o.IMGFMT', fmt=IMGFMT size=1048576 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
++{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
++{"return": {}}
++{"execute": "drive-mirror", "arguments": {"device": "drv0", "format": "IMGFMT", "job-id": "job0", "sync": "none", "target": "TEST_DIR/PID-target"}}
++{"return": {}}
++{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
+ {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: mirror"}}
+-{'execute': 'block-job-cancel',
+-          'arguments': {'device': 'job0'}}
++{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
+ {"return": {}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
++{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "mirror"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
+ {"return": {}}
+ 
+ === Testing active block-commit ===
+-
+-{'execute': 'blockdev-add',
+-          'arguments': {
+-              'node-name': 'drv0',
+-              'driver': 'IMGFMT',
+-              'file': {
+-                  'driver': 'file',
+-                  'filename': 'TEST_DIR/t.IMGFMT'
+-              }}}
+-{"return": {}}
+-{'execute': 'block-commit',
+-'arguments': {'job-id': 'job0', 'device': 'drv0'}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
++{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
++{"return": {}}
++{"execute": "block-commit", "arguments": {"device": "drv0", "job-id": "job0"}}
++{"return": {}}
++{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
+ {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: commit"}}
+-{'execute': 'block-job-cancel',
+-          'arguments': {'device': 'job0'}}
++{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
+ {"return": {}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
++{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
+ {"return": {}}
+ 
+ === Testing non-active block-commit ===
+-
+-wrote 1048576/1048576 bytes at offset 0
+-1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+-{'execute': 'blockdev-add',
+-          'arguments': {
+-              'node-name': 'drv0',
+-              'driver': 'IMGFMT',
+-              'file': {
+-                  'driver': 'file',
+-                  'filename': 'TEST_DIR/t.IMGFMT'
+-              }}}
+-{"return": {}}
+-{'execute': 'block-commit',
+-'arguments': {'job-id': 'job0',
+-'device': 'drv0',
+-'top':    'TEST_DIR/m.IMGFMT',
+-'speed':  1}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
+-{"error": {"class": "GenericError", "desc": "Node drv0 is in use"}}
+-{'execute': 'block-job-cancel',
+-          'arguments': {'device': 'job0'}}
+-{"return": {}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "commit"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
++{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
++{"return": {}}
++{"execute": "block-commit", "arguments": {"device": "drv0", "job-id": "job0", "speed": 1, "top": "TEST_DIR/PID-middle"}}
++{"return": {}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
++{"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: commit"}}
++{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
++{"return": {}}
++{"data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "commit"}, "event": "BLOCK_JOB_CANCELLED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
+ {"return": {}}
+ 
+ === Testing block-stream ===
+-
+-wrote 1048576/1048576 bytes at offset 0
+-1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+-{'execute': 'blockdev-add',
+-          'arguments': {
+-              'node-name': 'drv0',
+-              'driver': 'IMGFMT',
+-              'file': {
+-                  'driver': 'file',
+-                  'filename': 'TEST_DIR/t.IMGFMT'
+-              }}}
+-{"return": {}}
+-{'execute': 'block-stream',
+-'arguments': {'job-id': 'job0',
+-'device': 'drv0',
+-'speed': 1}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "job0"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
++{"execute": "blockdev-add", "arguments": {"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/PID-top"}, "node-name": "drv0"}}
++{"return": {}}
++{"execute": "block-stream", "arguments": {"device": "drv0", "job-id": "job0", "speed": 1}}
++{"return": {}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
+ {"error": {"class": "GenericError", "desc": "Node 'drv0' is busy: block device is in use by block job: stream"}}
+-{'execute': 'block-job-cancel',
+-          'arguments': {'device': 'job0'}}
++{"execute": "block-job-cancel", "arguments": {"device": "job0"}}
+ {"return": {}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "aborting", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "BLOCK_JOB_CANCELLED", "data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "stream"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "job0"}}
+-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}}
+-{'execute': 'blockdev-del',
+-          'arguments': {'node-name': 'drv0'}}
++{"data": {"device": "job0", "len": 1048576, "offset": 524288, "speed": 1, "type": "stream"}, "event": "BLOCK_JOB_CANCELLED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}}
++{"execute": "blockdev-del", "arguments": {"node-name": "drv0"}}
+ {"return": {}}
+-*** done
++
+-- 
+2.39.3
+

SOURCES/kvm-kvm-Atomic-memslot-updates.patch

@@ -0,0 +1,290 @@
+From 93ec857c46911b95ed8e3abc6a9d432ae847c084 Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Mon, 16 Jan 2023 07:51:56 -0500
+Subject: [PATCH 06/11] kvm: Atomic memslot updates
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 247: accel: introduce accelerator blocker API
+RH-Bugzilla: 2161188
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [3/3] 520e41c0f58066a7381a5f6b32b81bc01cce51c0
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2161188
+
+commit f39b7d2b96e3e73c01bb678cd096f7baf0b9ab39
+Author: David Hildenbrand <david@redhat.com>
+Date:   Fri Nov 11 10:47:58 2022 -0500
+
+    kvm: Atomic memslot updates
+
+    If we update an existing memslot (e.g., resize, split), we temporarily
+    remove the memslot to re-add it immediately afterwards. These updates
+    are not atomic, especially not for KVM VCPU threads, such that we can
+    get spurious faults.
+
+    Let's inhibit most KVM ioctls while performing relevant updates, such
+    that we can perform the update just as if it would happen atomically
+    without additional kernel support.
+
+    We capture the add/del changes and apply them in the notifier commit
+    stage instead. There, we can check for overlaps and perform the ioctl
+    inhibiting only if really required (-> overlap).
+
+    To keep things simple we don't perform additional checks that wouldn't
+    actually result in an overlap -- such as !RAM memory regions in some
+    cases (see kvm_set_phys_mem()).
+
+    To minimize cache-line bouncing, use a separate indicator
+    (in_ioctl_lock) per CPU.  Also, make sure to hold the kvm_slots_lock
+    while performing both actions (removing+re-adding).
+
+    We have to wait until all IOCTLs were exited and block new ones from
+    getting executed.
+
+    This approach cannot result in a deadlock as long as the inhibitor does
+    not hold any locks that might hinder an IOCTL from getting finished and
+    exited - something fairly unusual. The inhibitor will always hold the BQL.
+
+    AFAIKs, one possible candidate would be userfaultfd. If a page cannot be
+    placed (e.g., during postcopy), because we're waiting for a lock, or if the
+    userfaultfd thread cannot process a fault, because it is waiting for a
+    lock, there could be a deadlock. However, the BQL is not applicable here,
+    because any other guest memory access while holding the BQL would already
+    result in a deadlock.
+
+    Nothing else in the kernel should block forever and wait for userspace
+    intervention.
+
+    Note: pause_all_vcpus()/resume_all_vcpus() or
+    start_exclusive()/end_exclusive() cannot be used, as they either drop
+    the BQL or require to be called without the BQL - something inhibitors
+    cannot handle. We need a low-level locking mechanism that is
+    deadlock-free even when not releasing the BQL.
+
+    Signed-off-by: David Hildenbrand <david@redhat.com>
+    Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+    Tested-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+    Message-Id: <20221111154758.1372674-4-eesposit@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Conflicts:
+	accel/kvm/kvm-all.c: include "sysemu/dirtylimit.h" is missing in
+	rhel 8.8.0
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ accel/kvm/kvm-all.c      | 101 ++++++++++++++++++++++++++++++++++-----
+ include/sysemu/kvm_int.h |   8 ++++
+ 2 files changed, 98 insertions(+), 11 deletions(-)
+
+diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
+index 221aadfda7..3b7bc39823 100644
+--- a/accel/kvm/kvm-all.c
++++ b/accel/kvm/kvm-all.c
+@@ -31,6 +31,7 @@
+ #include "sysemu/kvm_int.h"
+ #include "sysemu/runstate.h"
+ #include "sysemu/cpus.h"
++#include "sysemu/accel-blocker.h"
+ #include "qemu/bswap.h"
+ #include "exec/memory.h"
+ #include "exec/ram_addr.h"
+@@ -45,6 +46,7 @@
+ #include "qemu/guest-random.h"
+ #include "sysemu/hw_accel.h"
+ #include "kvm-cpus.h"
++#include "qemu/range.h"
+ 
+ #include "hw/boards.h"
+ 
+@@ -1334,6 +1336,7 @@ void kvm_set_max_memslot_size(hwaddr max_slot_size)
+     kvm_max_slot_size = max_slot_size;
+ }
+ 
++/* Called with KVMMemoryListener.slots_lock held */
+ static void kvm_set_phys_mem(KVMMemoryListener *kml,
+                              MemoryRegionSection *section, bool add)
+ {
+@@ -1368,14 +1371,12 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
+     ram = memory_region_get_ram_ptr(mr) + mr_offset;
+     ram_start_offset = memory_region_get_ram_addr(mr) + mr_offset;
+ 
+-    kvm_slots_lock();
+-
+     if (!add) {
+         do {
+             slot_size = MIN(kvm_max_slot_size, size);
+             mem = kvm_lookup_matching_slot(kml, start_addr, slot_size);
+             if (!mem) {
+-                goto out;
++                return;
+             }
+             if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+                 /*
+@@ -1413,7 +1414,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
+             start_addr += slot_size;
+             size -= slot_size;
+         } while (size);
+-        goto out;
++        return;
+     }
+ 
+     /* register the new slot */
+@@ -1438,9 +1439,6 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
+         ram += slot_size;
+         size -= slot_size;
+     } while (size);
+-
+-out:
+-    kvm_slots_unlock();
+ }
+ 
+ static void *kvm_dirty_ring_reaper_thread(void *data)
+@@ -1492,18 +1490,95 @@ static void kvm_region_add(MemoryListener *listener,
+                            MemoryRegionSection *section)
+ {
+     KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
++    KVMMemoryUpdate *update;
++
++    update = g_new0(KVMMemoryUpdate, 1);
++    update->section = *section;
+ 
+-    memory_region_ref(section->mr);
+-    kvm_set_phys_mem(kml, section, true);
++    QSIMPLEQ_INSERT_TAIL(&kml->transaction_add, update, next);
+ }
+ 
+ static void kvm_region_del(MemoryListener *listener,
+                            MemoryRegionSection *section)
+ {
+     KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
++    KVMMemoryUpdate *update;
++
++    update = g_new0(KVMMemoryUpdate, 1);
++    update->section = *section;
++
++    QSIMPLEQ_INSERT_TAIL(&kml->transaction_del, update, next);
++}
++
++static void kvm_region_commit(MemoryListener *listener)
++{
++    KVMMemoryListener *kml = container_of(listener, KVMMemoryListener,
++                                          listener);
++    KVMMemoryUpdate *u1, *u2;
++    bool need_inhibit = false;
++
++    if (QSIMPLEQ_EMPTY(&kml->transaction_add) &&
++        QSIMPLEQ_EMPTY(&kml->transaction_del)) {
++        return;
++    }
++
++    /*
++     * We have to be careful when regions to add overlap with ranges to remove.
++     * We have to simulate atomic KVM memslot updates by making sure no ioctl()
++     * is currently active.
++     *
++     * The lists are order by addresses, so it's easy to find overlaps.
++     */
++    u1 = QSIMPLEQ_FIRST(&kml->transaction_del);
++    u2 = QSIMPLEQ_FIRST(&kml->transaction_add);
++    while (u1 && u2) {
++        Range r1, r2;
++
++        range_init_nofail(&r1, u1->section.offset_within_address_space,
++                          int128_get64(u1->section.size));
++        range_init_nofail(&r2, u2->section.offset_within_address_space,
++                          int128_get64(u2->section.size));
++
++        if (range_overlaps_range(&r1, &r2)) {
++            need_inhibit = true;
++            break;
++        }
++        if (range_lob(&r1) < range_lob(&r2)) {
++            u1 = QSIMPLEQ_NEXT(u1, next);
++        } else {
++            u2 = QSIMPLEQ_NEXT(u2, next);
++        }
++    }
++
++    kvm_slots_lock();
++    if (need_inhibit) {
++        accel_ioctl_inhibit_begin();
++    }
++
++    /* Remove all memslots before adding the new ones. */
++    while (!QSIMPLEQ_EMPTY(&kml->transaction_del)) {
++        u1 = QSIMPLEQ_FIRST(&kml->transaction_del);
++        QSIMPLEQ_REMOVE_HEAD(&kml->transaction_del, next);
+ 
+-    kvm_set_phys_mem(kml, section, false);
+-    memory_region_unref(section->mr);
++        kvm_set_phys_mem(kml, &u1->section, false);
++        memory_region_unref(u1->section.mr);
++
++        g_free(u1);
++    }
++    while (!QSIMPLEQ_EMPTY(&kml->transaction_add)) {
++        u1 = QSIMPLEQ_FIRST(&kml->transaction_add);
++        QSIMPLEQ_REMOVE_HEAD(&kml->transaction_add, next);
++
++        memory_region_ref(u1->section.mr);
++        kvm_set_phys_mem(kml, &u1->section, true);
++
++        g_free(u1);
++    }
++
++    if (need_inhibit) {
++        accel_ioctl_inhibit_end();
++    }
++    kvm_slots_unlock();
+ }
+ 
+ static void kvm_log_sync(MemoryListener *listener,
+@@ -1647,8 +1722,12 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
+         kml->slots[i].slot = i;
+     }
+ 
++    QSIMPLEQ_INIT(&kml->transaction_add);
++    QSIMPLEQ_INIT(&kml->transaction_del);
++
+     kml->listener.region_add = kvm_region_add;
+     kml->listener.region_del = kvm_region_del;
++    kml->listener.commit = kvm_region_commit;
+     kml->listener.log_start = kvm_log_start;
+     kml->listener.log_stop = kvm_log_stop;
+     kml->listener.priority = 10;
+diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
+index 1f5487d9b7..7e18c0a3c0 100644
+--- a/include/sysemu/kvm_int.h
++++ b/include/sysemu/kvm_int.h
+@@ -11,6 +11,7 @@
+ 
+ #include "exec/memory.h"
+ #include "qemu/accel.h"
++#include "qemu/queue.h"
+ #include "sysemu/kvm.h"
+ 
+ typedef struct KVMSlot
+@@ -30,10 +31,17 @@ typedef struct KVMSlot
+     ram_addr_t ram_start_offset;
+ } KVMSlot;
+ 
++typedef struct KVMMemoryUpdate {
++    QSIMPLEQ_ENTRY(KVMMemoryUpdate) next;
++    MemoryRegionSection section;
++} KVMMemoryUpdate;
++
+ typedef struct KVMMemoryListener {
+     MemoryListener listener;
+     KVMSlot *slots;
+     int as_id;
++    QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_add;
++    QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_del;
+ } KVMMemoryListener;
+ 
+ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
+-- 
+2.37.3
+

SOURCES/kvm-lsi53c895a-disable-reentrancy-detection-for-MMIO-reg.patch

@@ -0,0 +1,71 @@
+From 8f19df61a101c1e57a1bce8adddb57a4a7123a77 Mon Sep 17 00:00:00 2001
+From: Thomas Huth <thuth@redhat.com>
+Date: Tue, 16 May 2023 11:05:56 +0200
+Subject: [PATCH 11/15] lsi53c895a: disable reentrancy detection for MMIO
+ region, too
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [11/12] 8016c86f8432f5ea06c831d1181e87e6d45a6a50 (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+
+commit d139fe9ad8a27bcc50b4ead77d2f97d191a0e95e
+Author: Thomas Huth <thuth@redhat.com>
+Date:   Tue May 16 11:05:56 2023 +0200
+
+    lsi53c895a: disable reentrancy detection for MMIO region, too
+
+    While trying to use a SCSI disk on the LSI controller with an
+    older version of Fedora (25), I'm getting:
+
+     qemu: warning: Blocked re-entrant IO on MemoryRegion: lsi-mmio at addr: 0x34
+
+    and the SCSI controller is not usable. Seems like we have to
+    disable the reentrancy checker for the MMIO region, too, to
+    get this working again.
+
+    The problem could be reproduced it like this:
+
+    ./qemu-system-x86_64 -accel kvm -m 2G -machine q35 \
+     -device lsi53c810,id=lsi1 -device scsi-hd,drive=d0 \
+     -drive if=none,id=d0,file=.../somedisk.qcow2 \
+     -cdrom Fedora-Everything-netinst-i386-25-1.3.iso
+
+    Where somedisk.qcow2 is an image that contains already some partitions
+    and file systems.
+
+    In the boot menu of Fedora, go to
+    "Troubleshooting" -> "Rescue a Fedora system" -> "3) Skip to shell"
+
+    Then check "dmesg | grep -i 53c" for failure messages, and try to mount
+    a partition from somedisk.qcow2.
+
+    Message-Id: <20230516090556.553813-1-thuth@redhat.com>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/scsi/lsi53c895a.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/hw/scsi/lsi53c895a.c b/hw/scsi/lsi53c895a.c
+index 1e15e13fbf..2b9cb2ac5d 100644
+--- a/hw/scsi/lsi53c895a.c
++++ b/hw/scsi/lsi53c895a.c
+@@ -2306,6 +2306,7 @@ static void lsi_scsi_realize(PCIDevice *dev, Error **errp)
+      * re-entrancy guard.
+      */
+     s->ram_io.disable_reentrancy_guard = true;
++    s->mmio_io.disable_reentrancy_guard = true;
+ 
+     address_space_init(&s->pci_io_as, pci_address_space_io(dev), "lsi-pci-io");
+     qdev_init_gpio_out(d, &s->ext_irq, 1);
+-- 
+2.37.3
+

SOURCES/kvm-lsi53c895a-disable-reentrancy-detection-for-script-R.patch

@@ -0,0 +1,59 @@
+From 3cffdbf3224ac21016dbee69cb2382c322d4bfbb Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Tue, 9 May 2023 10:29:03 -0400
+Subject: [PATCH 05/15] lsi53c895a: disable reentrancy detection for script RAM
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [5/12] b5334c3a34b38ed1dccf0030d5704e51e00fdce3 (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+
+commit bfd6e7ae6a72b84e2eb9574f56e6ec037f05182c
+Author: Alexander Bulekov <alxndr@bu.edu>
+Date:   Thu Apr 27 17:10:10 2023 -0400
+
+    lsi53c895a: disable reentrancy detection for script RAM
+
+    As the code is designed to use the memory APIs to access the script ram,
+    disable reentrancy checks for the pseudo-RAM ram_io MemoryRegion.
+
+    In the future, ram_io may be converted from an IO to a proper RAM MemoryRegion.
+
+    Reported-by: Fiona Ebner <f.ebner@proxmox.com>
+    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
+    Reviewed-by: Thomas Huth <thuth@redhat.com>
+    Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
+    Message-Id: <20230427211013.2994127-6-alxndr@bu.edu>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/scsi/lsi53c895a.c | 6 ++++++
+ 1 file changed, 6 insertions(+)
+
+diff --git a/hw/scsi/lsi53c895a.c b/hw/scsi/lsi53c895a.c
+index 85e907a785..1e15e13fbf 100644
+--- a/hw/scsi/lsi53c895a.c
++++ b/hw/scsi/lsi53c895a.c
+@@ -2301,6 +2301,12 @@ static void lsi_scsi_realize(PCIDevice *dev, Error **errp)
+     memory_region_init_io(&s->io_io, OBJECT(s), &lsi_io_ops, s,
+                           "lsi-io", 256);
+ 
++    /*
++     * Since we use the address-space API to interact with ram_io, disable the
++     * re-entrancy guard.
++     */
++    s->ram_io.disable_reentrancy_guard = true;
++
+     address_space_init(&s->pci_io_as, pci_address_space_io(dev), "lsi-pci-io");
+     qdev_init_gpio_out(d, &s->ext_irq, 1);
+ 
+-- 
+2.37.3
+

SOURCES/kvm-memory-prevent-dma-reentracy-issues.patch

@@ -0,0 +1,151 @@
+From e0c811c2d13f995fe1b095f48637316be5978b0e Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Tue, 9 May 2023 10:29:03 -0400
+Subject: [PATCH 01/15] memory: prevent dma-reentracy issues
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [1/12] 8fced41b4b2105343e8f0250286b771bcb43c81f (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+CVE: CVE-2023-0330
+
+commit a2e1753b8054344f32cf94f31c6399a58794a380
+Author: Alexander Bulekov <alxndr@bu.edu>
+Date:   Thu Apr 27 17:10:06 2023 -0400
+
+    memory: prevent dma-reentracy issues
+
+    Add a flag to the DeviceState, when a device is engaged in PIO/MMIO/DMA.
+    This flag is set/checked prior to calling a device's MemoryRegion
+    handlers, and set when device code initiates DMA.  The purpose of this
+    flag is to prevent two types of DMA-based reentrancy issues:
+
+    1.) mmio -> dma -> mmio case
+    2.) bh -> dma write -> mmio case
+
+    These issues have led to problems such as stack-exhaustion and
+    use-after-frees.
+
+    Summary of the problem from Peter Maydell:
+    https://lore.kernel.org/qemu-devel/CAFEAcA_23vc7hE3iaM-JVA6W38LK4hJoWae5KcknhPRD5fPBZA@mail.gmail.com
+
+    Resolves: https://gitlab.com/qemu-project/qemu/-/issues/62
+    Resolves: https://gitlab.com/qemu-project/qemu/-/issues/540
+    Resolves: https://gitlab.com/qemu-project/qemu/-/issues/541
+    Resolves: https://gitlab.com/qemu-project/qemu/-/issues/556
+    Resolves: https://gitlab.com/qemu-project/qemu/-/issues/557
+    Resolves: https://gitlab.com/qemu-project/qemu/-/issues/827
+    Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1282
+    Resolves: CVE-2023-0330
+
+    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
+    Reviewed-by: Thomas Huth <thuth@redhat.com>
+    Message-Id: <20230427211013.2994127-2-alxndr@bu.edu>
+    [thuth: Replace warn_report() with warn_report_once()]
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ include/exec/memory.h  |  5 +++++
+ include/hw/qdev-core.h |  7 +++++++
+ softmmu/memory.c       | 16 ++++++++++++++++
+ 3 files changed, 28 insertions(+)
+
+diff --git a/include/exec/memory.h b/include/exec/memory.h
+index 20f1b27377..e089f90f9b 100644
+--- a/include/exec/memory.h
++++ b/include/exec/memory.h
+@@ -734,6 +734,8 @@ struct MemoryRegion {
+     bool is_iommu;
+     RAMBlock *ram_block;
+     Object *owner;
++    /* owner as TYPE_DEVICE. Used for re-entrancy checks in MR access hotpath */
++    DeviceState *dev;
+ 
+     const MemoryRegionOps *ops;
+     void *opaque;
+@@ -757,6 +759,9 @@ struct MemoryRegion {
+     unsigned ioeventfd_nb;
+     MemoryRegionIoeventfd *ioeventfds;
+     RamDiscardManager *rdm; /* Only for RAM */
++
++    /* For devices designed to perform re-entrant IO into their own IO MRs */
++    bool disable_reentrancy_guard;
+ };
+ 
+ struct IOMMUMemoryRegion {
+diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
+index 20d3066595..14226f860d 100644
+--- a/include/hw/qdev-core.h
++++ b/include/hw/qdev-core.h
+@@ -162,6 +162,10 @@ struct NamedClockList {
+     QLIST_ENTRY(NamedClockList) node;
+ };
+ 
++typedef struct {
++    bool engaged_in_io;
++} MemReentrancyGuard;
++
+ /**
+  * DeviceState:
+  * @realized: Indicates whether the device has been fully constructed.
+@@ -193,6 +197,9 @@ struct DeviceState {
+     int instance_id_alias;
+     int alias_required_for_version;
+     ResettableState reset;
++
++    /* Is the device currently in mmio/pio/dma? Used to prevent re-entrancy */
++    MemReentrancyGuard mem_reentrancy_guard;
+ };
+ 
+ struct DeviceListener {
+diff --git a/softmmu/memory.c b/softmmu/memory.c
+index 7340e19ff5..102f0a4248 100644
+--- a/softmmu/memory.c
++++ b/softmmu/memory.c
+@@ -541,6 +541,18 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
+         access_size_max = 4;
+     }
+ 
++    /* Do not allow more than one simultaneous access to a device's IO Regions */
++    if (mr->dev && !mr->disable_reentrancy_guard &&
++        !mr->ram_device && !mr->ram && !mr->rom_device && !mr->readonly) {
++        if (mr->dev->mem_reentrancy_guard.engaged_in_io) {
++            warn_report_once("Blocked re-entrant IO on MemoryRegion: "
++                             "%s at addr: 0x%" HWADDR_PRIX,
++                             memory_region_name(mr), addr);
++            return MEMTX_ACCESS_ERROR;
++        }
++        mr->dev->mem_reentrancy_guard.engaged_in_io = true;
++    }
++
+     /* FIXME: support unaligned access? */
+     access_size = MAX(MIN(size, access_size_max), access_size_min);
+     access_mask = MAKE_64BIT_MASK(0, access_size * 8);
+@@ -555,6 +567,9 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
+                         access_mask, attrs);
+         }
+     }
++    if (mr->dev) {
++        mr->dev->mem_reentrancy_guard.engaged_in_io = false;
++    }
+     return r;
+ }
+ 
+@@ -1169,6 +1184,7 @@ static void memory_region_do_init(MemoryRegion *mr,
+     }
+     mr->name = g_strdup(name);
+     mr->owner = owner;
++    mr->dev = (DeviceState *) object_dynamic_cast(mr->owner, TYPE_DEVICE);
+     mr->ram_block = NULL;
+ 
+     if (name) {
+-- 
+2.37.3
+

SOURCES/kvm-memory-stricter-checks-prior-to-unsetting-engaged_in.patch

@@ -0,0 +1,68 @@
+From c24e38eb508b3fb42ce3ea62fe8de0be6a95a6a8 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Wed, 7 Jun 2023 11:45:09 -0400
+Subject: [PATCH 10/15] memory: stricter checks prior to unsetting
+ engaged_in_io
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 277: memory: prevent dma-reentracy issues
+RH-Bugzilla: 1999236
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [10/12] 773b62a84b2bd4f5ee7fb8e1cfb3bb91c3a01de1 (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
+Upstream: Merged
+CVE: CVE-2021-3750
+
+commit 3884bf6468ac6bbb58c2b3feaa74e87f821b52f3
+Author: Alexander Bulekov <alxndr@bu.edu>
+Date:   Tue May 16 04:40:02 2023 -0400
+
+    memory: stricter checks prior to unsetting engaged_in_io
+
+    engaged_in_io could be unset by an MR with re-entrancy checks disabled.
+    Ensure that only MRs that can set the engaged_in_io flag can unset it.
+
+    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
+    Message-Id: <20230516084002.3813836-1-alxndr@bu.edu>
+    Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ softmmu/memory.c | 4 +++-
+ 1 file changed, 3 insertions(+), 1 deletion(-)
+
+diff --git a/softmmu/memory.c b/softmmu/memory.c
+index 102f0a4248..6b98615357 100644
+--- a/softmmu/memory.c
++++ b/softmmu/memory.c
+@@ -533,6 +533,7 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
+     unsigned access_size;
+     unsigned i;
+     MemTxResult r = MEMTX_OK;
++    bool reentrancy_guard_applied = false;
+ 
+     if (!access_size_min) {
+         access_size_min = 1;
+@@ -551,6 +552,7 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
+             return MEMTX_ACCESS_ERROR;
+         }
+         mr->dev->mem_reentrancy_guard.engaged_in_io = true;
++        reentrancy_guard_applied = true;
+     }
+ 
+     /* FIXME: support unaligned access? */
+@@ -567,7 +569,7 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
+                         access_mask, attrs);
+         }
+     }
+-    if (mr->dev) {
++    if (mr->dev && reentrancy_guard_applied) {
+         mr->dev->mem_reentrancy_guard.engaged_in_io = false;
+     }
+     return r;
+-- 
+2.37.3
+

SOURCES/kvm-migration-Attempt-disk-reactivation-in-more-failure-.patch

@@ -0,0 +1,111 @@
+From a1f2a51d1a789c46e806adb332236ca16d538bf9 Mon Sep 17 00:00:00 2001
+From: Eric Blake <eblake@redhat.com>
+Date: Tue, 2 May 2023 15:52:12 -0500
+Subject: [PATCH 3/5] migration: Attempt disk reactivation in more failure
+ scenarios
+
+RH-Author: Eric Blake <eblake@redhat.com>
+RH-MergeRequest: 273: migration: prevent source core dump if NFS dies mid-migration
+RH-Bugzilla: 2177957
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Acked-by: quintela1 <quintela@redhat.com>
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Commit: [3/3] e84bf1e7233c0273ca3136ecaa6b2cfc9c0efacb (ebblake/qemu-kvm)
+
+Commit fe904ea824 added a fail_inactivate label, which tries to
+reactivate disks on the source after a failure while s->state ==
+MIGRATION_STATUS_ACTIVE, but didn't actually use the label if
+qemu_savevm_state_complete_precopy() failed.  This failure to
+reactivate is also present in commit 6039dd5b1c (also covering the new
+s->state == MIGRATION_STATUS_DEVICE state) and 403d18ae (ensuring
+s->block_inactive is set more reliably).
+
+Consolidate the two labels back into one - no matter HOW migration is
+failed, if there is any chance we can reach vm_start() after having
+attempted inactivation, it is essential that we have tried to restart
+disks before then.  This also makes the cleanup more like
+migrate_fd_cancel().
+
+Suggested-by: Kevin Wolf <kwolf@redhat.com>
+Signed-off-by: Eric Blake <eblake@redhat.com>
+Message-Id: <20230502205212.134680-1-eblake@redhat.com>
+Acked-by: Peter Xu <peterx@redhat.com>
+Reviewed-by: Juan Quintela <quintela@redhat.com>
+Reviewed-by: Kevin Wolf <kwolf@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit 6dab4c93ecfae48e2e67b984d1032c1e988d3005)
+[eblake: downstream migrate_colo() => migrate_colo_enabled()]
+Signed-off-by: Eric Blake <eblake@redhat.com>
+---
+ migration/migration.c | 24 ++++++++++++++----------
+ 1 file changed, 14 insertions(+), 10 deletions(-)
+
+diff --git a/migration/migration.c b/migration/migration.c
+index 6ba8eb0fdf..817170d52d 100644
+--- a/migration/migration.c
++++ b/migration/migration.c
+@@ -3255,6 +3255,11 @@ static void migration_completion(MigrationState *s)
+                                             MIGRATION_STATUS_DEVICE);
+             }
+             if (ret >= 0) {
++                /*
++                 * Inactivate disks except in COLO, and track that we
++                 * have done so in order to remember to reactivate
++                 * them if migration fails or is cancelled.
++                 */
+                 s->block_inactive = !migrate_colo_enabled();
+                 qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
+                 ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false,
+@@ -3290,13 +3295,13 @@ static void migration_completion(MigrationState *s)
+         rp_error = await_return_path_close_on_source(s);
+         trace_migration_return_path_end_after(rp_error);
+         if (rp_error) {
+-            goto fail_invalidate;
++            goto fail;
+         }
+     }
+ 
+     if (qemu_file_get_error(s->to_dst_file)) {
+         trace_migration_completion_file_err();
+-        goto fail_invalidate;
++        goto fail;
+     }
+ 
+     if (!migrate_colo_enabled()) {
+@@ -3306,26 +3311,25 @@ static void migration_completion(MigrationState *s)
+ 
+     return;
+ 
+-fail_invalidate:
+-    /* If not doing postcopy, vm_start() will be called: let's regain
+-     * control on images.
+-     */
+-    if (s->state == MIGRATION_STATUS_ACTIVE ||
+-        s->state == MIGRATION_STATUS_DEVICE) {
++fail:
++    if (s->block_inactive && (s->state == MIGRATION_STATUS_ACTIVE ||
++                              s->state == MIGRATION_STATUS_DEVICE)) {
++        /*
++         * If not doing postcopy, vm_start() will be called: let's
++         * regain control on images.
++         */
+         Error *local_err = NULL;
+ 
+         qemu_mutex_lock_iothread();
+         bdrv_invalidate_cache_all(&local_err);
+         if (local_err) {
+             error_report_err(local_err);
+-            s->block_inactive = true;
+         } else {
+             s->block_inactive = false;
+         }
+         qemu_mutex_unlock_iothread();
+     }
+ 
+-fail:
+     migrate_set_state(&s->state, current_active_state,
+                       MIGRATION_STATUS_FAILED);
+ }
+-- 
+2.39.1
+

SOURCES/kvm-migration-Disable-postcopy-multifd-migration.patch

@@ -0,0 +1,59 @@
+From dd6d0eace90285c017ae40cba0ffa95ccd963ebd Mon Sep 17 00:00:00 2001
+From: Leonardo Bras <leobras@redhat.com>
+Date: Tue, 20 Jun 2023 14:51:03 -0300
+Subject: [PATCH 15/15] migration: Disable postcopy + multifd migration
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Leonardo Brás <leobras@redhat.com>
+RH-MergeRequest: 287: migration: Disable postcopy + multifd migration
+RH-Bugzilla: 2169733
+RH-Acked-by: Peter Xu <peterx@redhat.com>
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Commit: [1/1] 07d26fbac35b7586fe790304f03d316ed26a4ef2
+
+Since the introduction of multifd, it's possible to perform a multifd
+migration and finish it using postcopy.
+
+A bug introduced by yank (fixed on cfc3bcf373) was previously preventing
+a successful use of this migration scenario, and now thing should be
+working on most scenarios.
+
+But since there is not enough testing/support nor any reported users for
+this scenario, we should disable this combination before it may cause any
+problems for users.
+
+Suggested-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+Signed-off-by: Leonardo Bras <leobras@redhat.com>
+Acked-by: Peter Xu <peterx@redhat.com>
+Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+Reviewed-by: Juan Quintela <quintela@redhat.com>
+Signed-off-by: Juan Quintela <quintela@redhat.com>
+(cherry picked from commit b405dfff1ea3cf0530b628895b5a7a50dc8c6996)
+[leobras: moves logic from options.c -> migration.c and use cap_list
+instead of new_caps for backward compatibility]
+Signed-off-by: Leonardo Bras <leobras@redhat.com>
+---
+ migration/migration.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+diff --git a/migration/migration.c b/migration/migration.c
+index 817170d52d..1ad82e63f0 100644
+--- a/migration/migration.c
++++ b/migration/migration.c
+@@ -1246,6 +1246,11 @@ static bool migrate_caps_check(bool *cap_list,
+             error_setg(errp, "Postcopy is not compatible with ignore-shared");
+             return false;
+         }
++
++        if (cap_list[MIGRATION_CAPABILITY_MULTIFD]) {
++            error_setg(errp, "Postcopy is not yet compatible with multifd");
++            return false;
++        }
+     }
+ 
+     if (cap_list[MIGRATION_CAPABILITY_BACKGROUND_SNAPSHOT]) {
+-- 
+2.37.3
+

SOURCES/kvm-migration-Handle-block-device-inactivation-failures-.patch

@@ -0,0 +1,117 @@
+From 1b07c7663b6a5c19c9303088d63c39dba7e3bb36 Mon Sep 17 00:00:00 2001
+From: Eric Blake <eblake@redhat.com>
+Date: Fri, 14 Apr 2023 10:33:58 -0500
+Subject: [PATCH 1/5] migration: Handle block device inactivation failures
+ better
+
+RH-Author: Eric Blake <eblake@redhat.com>
+RH-MergeRequest: 273: migration: prevent source core dump if NFS dies mid-migration
+RH-Bugzilla: 2177957
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Acked-by: quintela1 <quintela@redhat.com>
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Commit: [1/3] 5892c17ca0a21d824d176e7398d12f7cf991651d (ebblake/qemu-kvm)
+
+Consider what happens when performing a migration between two host
+machines connected to an NFS server serving multiple block devices to
+the guest, when the NFS server becomes unavailable.  The migration
+attempts to inactivate all block devices on the source (a necessary
+step before the destination can take over); but if the NFS server is
+non-responsive, the attempt to inactivate can itself fail.  When that
+happens, the destination fails to get the migrated guest (good,
+because the source wasn't able to flush everything properly):
+
+  (qemu) qemu-kvm: load of migration failed: Input/output error
+
+at which point, our only hope for the guest is for the source to take
+back control.  With the current code base, the host outputs a message, but then appears to resume:
+
+  (qemu) qemu-kvm: qemu_savevm_state_complete_precopy_non_iterable: bdrv_inactivate_all() failed (-1)
+
+  (src qemu)info status
+   VM status: running
+
+but a second migration attempt now asserts:
+
+  (src qemu) qemu-kvm: ../block.c:6738: int bdrv_inactivate_recurse(BlockDriverState *): Assertion `!(bs->open_flags & BDRV_O_INACTIVE)' failed.
+
+Whether the guest is recoverable on the source after the first failure
+is debatable, but what we do not want is to have qemu itself fail due
+to an assertion.  It looks like the problem is as follows:
+
+In migration.c:migration_completion(), the source sets 'inactivate' to
+true (since COLO is not enabled), then tries
+savevm.c:qemu_savevm_state_complete_precopy() with a request to
+inactivate block devices.  In turn, this calls
+block.c:bdrv_inactivate_all(), which fails when flushing runs up
+against the non-responsive NFS server.  With savevm failing, we are
+now left in a state where some, but not all, of the block devices have
+been inactivated; but migration_completion() then jumps to 'fail'
+rather than 'fail_invalidate' and skips an attempt to reclaim those
+those disks by calling bdrv_activate_all().  Even if we do attempt to
+reclaim disks, we aren't taking note of failure there, either.
+
+Thus, we have reached a state where the migration engine has forgotten
+all state about whether a block device is inactive, because we did not
+set s->block_inactive in enough places; so migration allows the source
+to reach vm_start() and resume execution, violating the block layer
+invariant that the guest CPUs should not be restarted while a device
+is inactive.  Note that the code in migration.c:migrate_fd_cancel()
+will also try to reactivate all block devices if s->block_inactive was
+set, but because we failed to set that flag after the first failure,
+the source assumes it has reclaimed all devices, even though it still
+has remaining inactivated devices and does not try again.  Normally,
+qmp_cont() will also try to reactivate all disks (or correctly fail if
+the disks are not reclaimable because NFS is not yet back up), but the
+auto-resumption of the source after a migration failure does not go
+through qmp_cont().  And because we have left the block layer in an
+inconsistent state with devices still inactivated, the later migration
+attempt is hitting the assertion failure.
+
+Since it is important to not resume the source with inactive disks,
+this patch marks s->block_inactive before attempting inactivation,
+rather than after succeeding, in order to prevent any vm_start() until
+it has successfully reactivated all devices.
+
+See also https://bugzilla.redhat.com/show_bug.cgi?id=2058982
+
+Signed-off-by: Eric Blake <eblake@redhat.com>
+Reviewed-by: Juan Quintela <quintela@redhat.com>
+Acked-by: Lukas Straub <lukasstraub2@web.de>
+Tested-by: Lukas Straub <lukasstraub2@web.de>
+Signed-off-by: Juan Quintela <quintela@redhat.com>
+(cherry picked from commit 403d18ae384239876764bbfa111d6cc5dcb673d1)
+---
+ migration/migration.c | 5 ++---
+ 1 file changed, 2 insertions(+), 3 deletions(-)
+
+diff --git a/migration/migration.c b/migration/migration.c
+index 0885549de0..08e5e8f013 100644
+--- a/migration/migration.c
++++ b/migration/migration.c
+@@ -3256,13 +3256,11 @@ static void migration_completion(MigrationState *s)
+                                             MIGRATION_STATUS_DEVICE);
+             }
+             if (ret >= 0) {
++                s->block_inactive = inactivate;
+                 qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
+                 ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false,
+                                                          inactivate);
+             }
+-            if (inactivate && ret >= 0) {
+-                s->block_inactive = true;
+-            }
+         }
+         qemu_mutex_unlock_iothread();
+ 
+@@ -3321,6 +3319,7 @@ fail_invalidate:
+         bdrv_invalidate_cache_all(&local_err);
+         if (local_err) {
+             error_report_err(local_err);
++            s->block_inactive = true;
+         } else {
+             s->block_inactive = false;
+         }
+-- 
+2.39.1
+

SOURCES/kvm-migration-Minor-control-flow-simplification.patch

@@ -0,0 +1,53 @@
+From e79d0506184e861350d2a3e62dd986aa03d30aa8 Mon Sep 17 00:00:00 2001
+From: Eric Blake <eblake@redhat.com>
+Date: Thu, 20 Apr 2023 09:35:51 -0500
+Subject: [PATCH 2/5] migration: Minor control flow simplification
+
+RH-Author: Eric Blake <eblake@redhat.com>
+RH-MergeRequest: 273: migration: prevent source core dump if NFS dies mid-migration
+RH-Bugzilla: 2177957
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Acked-by: quintela1 <quintela@redhat.com>
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Commit: [2/3] f00b21b6ebd377af79af93ac18f103f8dc0309d6 (ebblake/qemu-kvm)
+
+No need to declare a temporary variable.
+
+Suggested-by: Juan Quintela <quintela@redhat.com>
+Fixes: 1df36e8c6289 ("migration: Handle block device inactivation failures better")
+Signed-off-by: Eric Blake <eblake@redhat.com>
+Reviewed-by: Juan Quintela <quintela@redhat.com>
+Signed-off-by: Juan Quintela <quintela@redhat.com>
+(cherry picked from commit 5d39f44d7ac5c63f53d4d0900ceba9521bc27e49)
+---
+ migration/migration.c | 5 ++---
+ 1 file changed, 2 insertions(+), 3 deletions(-)
+
+diff --git a/migration/migration.c b/migration/migration.c
+index 08e5e8f013..6ba8eb0fdf 100644
+--- a/migration/migration.c
++++ b/migration/migration.c
+@@ -3248,7 +3248,6 @@ static void migration_completion(MigrationState *s)
+         ret = global_state_store();
+ 
+         if (!ret) {
+-            bool inactivate = !migrate_colo_enabled();
+             ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+             trace_migration_completion_vm_stop(ret);
+             if (ret >= 0) {
+@@ -3256,10 +3255,10 @@ static void migration_completion(MigrationState *s)
+                                             MIGRATION_STATUS_DEVICE);
+             }
+             if (ret >= 0) {
+-                s->block_inactive = inactivate;
++                s->block_inactive = !migrate_colo_enabled();
+                 qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
+                 ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false,
+-                                                         inactivate);
++                                                         s->block_inactive);
+             }
+         }
+         qemu_mutex_unlock_iothread();
+-- 
+2.39.1
+

SOURCES/kvm-migration-Read-state-once.patch

@@ -0,0 +1,76 @@
+From 34eae2d7ef928a7e0e10cc30fe76839c005998eb Mon Sep 17 00:00:00 2001
+From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
+Date: Wed, 13 Apr 2022 12:33:29 +0100
+Subject: [PATCH 07/11] migration: Read state once
+
+RH-Author: Dr. David Alan Gilbert <dgilbert@redhat.com>
+RH-MergeRequest: 249: migration: Read state once
+RH-Bugzilla: 2074205
+RH-Acked-by: Peter Xu <peterx@redhat.com>
+RH-Acked-by: Laszlo Ersek <lersek@redhat.com>
+RH-Acked-by: Jon Maloy <jmaloy@redhat.com>
+RH-Acked-by: quintela1 <quintela@redhat.com>
+RH-Commit: [1/1] 9aa47b492a646fce4e66ebd9b7d7a85286d16051
+
+The 'status' field for the migration is updated normally using
+an atomic operation from the migration thread.
+Most readers of it aren't that careful, and in most cases it doesn't
+matter.
+
+In query_migrate->fill_source_migration_info the 'state'
+is read twice; the first time to decide which state fields to fill in,
+and then secondly to copy the state to the status field; that can end up
+with a status that's inconsistent; e.g. setting up the fields
+for 'setup' and then having an 'active' status.  In that case
+libvirt gets upset by the lack of ram info.
+The symptom is:
+   libvirt.libvirtError: internal error: migration was active, but no RAM info was set
+
+Read the state exactly once in fill_source_migration_info.
+
+This is a possible fix for:
+https://bugzilla.redhat.com/show_bug.cgi?id=2074205
+
+Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+Message-Id: <20220413113329.103696-1-dgilbert@redhat.com>
+Reviewed-by: Juan Quintela <quintela@redhat.com>
+Reviewed-by: Peter Xu <peterx@redhat.com>
+Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+(cherry picked from commit 552de79bfdd5e9e53847eb3c6d6e4cd898a4370e)
+---
+ migration/migration.c | 5 +++--
+ 1 file changed, 3 insertions(+), 2 deletions(-)
+
+diff --git a/migration/migration.c b/migration/migration.c
+index 51e6726dac..d8b24a2c91 100644
+--- a/migration/migration.c
++++ b/migration/migration.c
+@@ -1071,6 +1071,7 @@ static void populate_disk_info(MigrationInfo *info)
+ static void fill_source_migration_info(MigrationInfo *info)
+ {
+     MigrationState *s = migrate_get_current();
++    int state = qatomic_read(&s->state);
+     GSList *cur_blocker = migration_blockers;
+ 
+     info->blocked_reasons = NULL;
+@@ -1090,7 +1091,7 @@ static void fill_source_migration_info(MigrationInfo *info)
+     }
+     info->has_blocked_reasons = info->blocked_reasons != NULL;
+ 
+-    switch (s->state) {
++    switch (state) {
+     case MIGRATION_STATUS_NONE:
+         /* no migration has happened ever */
+         /* do not overwrite destination migration status */
+@@ -1135,7 +1136,7 @@ static void fill_source_migration_info(MigrationInfo *info)
+         info->has_status = true;
+         break;
+     }
+-    info->status = s->state;
++    info->status = state;
+ }
+ 
+ typedef enum WriteTrackingSupport {
+-- 
+2.37.3
+

SOURCES/kvm-migration-check-magic-value-for-deciding-the-mapping.patch

@@ -0,0 +1,296 @@
+From f21a343af4b4d0c6e5181ae0abd0f6280dc8296c Mon Sep 17 00:00:00 2001
+From: "manish.mishra" <manish.mishra@nutanix.com>
+Date: Tue, 20 Dec 2022 18:44:18 +0000
+Subject: [PATCH 2/3] migration: check magic value for deciding the mapping of
+ channels
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Peter Xu <peterx@redhat.com>
+RH-MergeRequest: 258: migration: Fix multifd crash due to channel disorder
+RH-Bugzilla: 2137740
+RH-Acked-by: quintela1 <quintela@redhat.com>
+RH-Acked-by: Leonardo Brás <leobras@redhat.com>
+RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+RH-Commit: [2/2] f97bebef3d3e372cfd660e5ddb6cffba791840d2
+
+Conflicts:
+        migration/migration.c
+        migration/multifd.c
+        migration/postcopy-ram.c
+        migration/postcopy-ram.h
+
+        There're a bunch of conflicts due to missing upstream patches on
+        e.g. on qemufile reworks, postcopy preempt.  We don't plan to have
+        preempt in rhel8 at all, probably the same as the rest.
+
+Current logic assumes that channel connections on the destination side are
+always established in the same order as the source and the first one will
+always be the main channel followed by the multifid or post-copy
+preemption channel. This may not be always true, as even if a channel has a
+connection established on the source side it can be in the pending state on
+the destination side and a newer connection can be established first.
+Basically causing out of order mapping of channels on the destination side.
+Currently, all channels except post-copy preempt send a magic number, this
+patch uses that magic number to decide the type of channel. This logic is
+applicable only for precopy(multifd) live migration, as mentioned, the
+post-copy preempt channel does not send any magic number. Also, tls live
+migrations already does tls handshake before creating other channels, so
+this issue is not possible with tls, hence this logic is avoided for tls
+live migrations. This patch uses read peek to check the magic number of
+channels so that current data/control stream management remains
+un-effected.
+
+Reviewed-by: Peter Xu <peterx@redhat.com>
+Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
+Reviewed-by: Juan Quintela <quintela@redhat.com>
+Suggested-by: Daniel P. Berrange <berrange@redhat.com>
+Signed-off-by: manish.mishra <manish.mishra@nutanix.com>
+Signed-off-by: Juan Quintela <quintela@redhat.com>
+(cherry picked from commit 6720c2b32725e6ac404f22851a0ecd0a71d0cbe2)
+Signed-off-by: Peter Xu <peterx@redhat.com>
+---
+ migration/channel.c   | 45 ++++++++++++++++++++++++++++++++++++++
+ migration/channel.h   |  5 +++++
+ migration/migration.c | 51 +++++++++++++++++++++++++++++++------------
+ migration/multifd.c   | 19 ++++++++--------
+ migration/multifd.h   |  2 +-
+ 5 files changed, 98 insertions(+), 24 deletions(-)
+
+diff --git a/migration/channel.c b/migration/channel.c
+index 086b5c0d8b..ee308fef23 100644
+--- a/migration/channel.c
++++ b/migration/channel.c
+@@ -98,3 +98,48 @@ void migration_channel_connect(MigrationState *s,
+     g_free(s->hostname);
+     error_free(error);
+ }
++
++
++/**
++ * @migration_channel_read_peek - Peek at migration channel, without
++ *     actually removing it from channel buffer.
++ *
++ * @ioc: the channel object
++ * @buf: the memory region to read data into
++ * @buflen: the number of bytes to read in @buf
++ * @errp: pointer to a NULL-initialized error object
++ *
++ * Returns 0 if successful, returns -1 and sets @errp if fails.
++ */
++int migration_channel_read_peek(QIOChannel *ioc,
++                                const char *buf,
++                                const size_t buflen,
++                                Error **errp)
++{
++    ssize_t len = 0;
++    struct iovec iov = { .iov_base = (char *)buf, .iov_len = buflen };
++
++    while (true) {
++        len = qio_channel_readv_full(ioc, &iov, 1, NULL, NULL,
++                                     QIO_CHANNEL_READ_FLAG_MSG_PEEK, errp);
++
++        if (len <= 0 && len != QIO_CHANNEL_ERR_BLOCK) {
++            error_setg(errp,
++                       "Failed to peek at channel");
++            return -1;
++        }
++
++        if (len == buflen) {
++            break;
++        }
++
++        /* 1ms sleep. */
++        if (qemu_in_coroutine()) {
++            qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 1000000);
++        } else {
++            g_usleep(1000);
++        }
++    }
++
++    return 0;
++}
+diff --git a/migration/channel.h b/migration/channel.h
+index 67a461c28a..5bdb8208a7 100644
+--- a/migration/channel.h
++++ b/migration/channel.h
+@@ -24,4 +24,9 @@ void migration_channel_connect(MigrationState *s,
+                                QIOChannel *ioc,
+                                const char *hostname,
+                                Error *error_in);
++
++int migration_channel_read_peek(QIOChannel *ioc,
++                                const char *buf,
++                                const size_t buflen,
++                                Error **errp);
+ #endif
+diff --git a/migration/migration.c b/migration/migration.c
+index d8b24a2c91..0885549de0 100644
+--- a/migration/migration.c
++++ b/migration/migration.c
+@@ -32,6 +32,7 @@
+ #include "savevm.h"
+ #include "qemu-file-channel.h"
+ #include "qemu-file.h"
++#include "channel.h"
+ #include "migration/vmstate.h"
+ #include "block/block.h"
+ #include "qapi/error.h"
+@@ -637,10 +638,6 @@ static bool migration_incoming_setup(QEMUFile *f, Error **errp)
+ {
+     MigrationIncomingState *mis = migration_incoming_get_current();
+ 
+-    if (multifd_load_setup(errp) != 0) {
+-        return false;
+-    }
+-
+     if (!mis->from_src_file) {
+         mis->from_src_file = f;
+     }
+@@ -701,10 +698,42 @@ void migration_fd_process_incoming(QEMUFile *f, Error **errp)
+ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp)
+ {
+     MigrationIncomingState *mis = migration_incoming_get_current();
++    bool default_channel = true;
++    uint32_t channel_magic = 0;
+     Error *local_err = NULL;
+-    bool start_migration;
++    int ret = 0;
+ 
+-    if (!mis->from_src_file) {
++    if (migrate_use_multifd() && !migrate_postcopy_ram() &&
++        qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) {
++        /*
++         * With multiple channels, it is possible that we receive channels
++         * out of order on destination side, causing incorrect mapping of
++         * source channels on destination side. Check channel MAGIC to
++         * decide type of channel. Please note this is best effort, postcopy
++         * preempt channel does not send any magic number so avoid it for
++         * postcopy live migration. Also tls live migration already does
++         * tls handshake while initializing main channel so with tls this
++         * issue is not possible.
++         */
++        ret = migration_channel_read_peek(ioc, (void *)&channel_magic,
++                                          sizeof(channel_magic), &local_err);
++
++        if (ret != 0) {
++            error_propagate(errp, local_err);
++            return;
++        }
++
++        default_channel = (channel_magic == cpu_to_be32(QEMU_VM_FILE_MAGIC));
++    } else {
++        default_channel = !mis->from_src_file;
++    }
++
++    if (multifd_load_setup(errp) != 0) {
++        error_setg(errp, "Failed to setup multifd channels");
++        return;
++    }
++
++    if (default_channel) {
+         /* The first connection (multifd may have multiple) */
+         QEMUFile *f = qemu_fopen_channel_input(ioc);
+ 
+@@ -716,23 +745,17 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp)
+         if (!migration_incoming_setup(f, errp)) {
+             return;
+         }
+-
+-        /*
+-         * Common migration only needs one channel, so we can start
+-         * right now.  Multifd needs more than one channel, we wait.
+-         */
+-        start_migration = !migrate_use_multifd();
+     } else {
+         /* Multiple connections */
+         assert(migrate_use_multifd());
+-        start_migration = multifd_recv_new_channel(ioc, &local_err);
++        multifd_recv_new_channel(ioc, &local_err);
+         if (local_err) {
+             error_propagate(errp, local_err);
+             return;
+         }
+     }
+ 
+-    if (start_migration) {
++    if (migration_has_all_channels()) {
+         migration_incoming_process();
+     }
+ }
+diff --git a/migration/multifd.c b/migration/multifd.c
+index 7c16523e6b..75ac052d2f 100644
+--- a/migration/multifd.c
++++ b/migration/multifd.c
+@@ -1183,9 +1183,14 @@ int multifd_load_setup(Error **errp)
+     uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size();
+     uint8_t i;
+ 
+-    if (!migrate_use_multifd()) {
++    /*
++     * Return successfully if multiFD recv state is already initialised
++     * or multiFD is not enabled.
++     */
++    if (multifd_recv_state || !migrate_use_multifd()) {
+         return 0;
+     }
++
+     if (!migrate_multifd_is_allowed()) {
+         error_setg(errp, "multifd is not supported by current protocol");
+         return -1;
+@@ -1244,11 +1249,9 @@ bool multifd_recv_all_channels_created(void)
+ 
+ /*
+  * Try to receive all multifd channels to get ready for the migration.
+- * - Return true and do not set @errp when correctly receiving all channels;
+- * - Return false and do not set @errp when correctly receiving the current one;
+- * - Return false and set @errp when failing to receive the current channel.
++ * Sets @errp when failing to receive the current channel.
+  */
+-bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
++void multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
+ {
+     MultiFDRecvParams *p;
+     Error *local_err = NULL;
+@@ -1261,7 +1264,7 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
+                                 "failed to receive packet"
+                                 " via multifd channel %d: ",
+                                 qatomic_read(&multifd_recv_state->count));
+-        return false;
++        return;
+     }
+     trace_multifd_recv_new_channel(id);
+ 
+@@ -1271,7 +1274,7 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
+                    id);
+         multifd_recv_terminate_threads(local_err);
+         error_propagate(errp, local_err);
+-        return false;
++        return;
+     }
+     p->c = ioc;
+     object_ref(OBJECT(ioc));
+@@ -1282,6 +1285,4 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
+     qemu_thread_create(&p->thread, p->name, multifd_recv_thread, p,
+                        QEMU_THREAD_JOINABLE);
+     qatomic_inc(&multifd_recv_state->count);
+-    return qatomic_read(&multifd_recv_state->count) ==
+-           migrate_multifd_channels();
+ }
+diff --git a/migration/multifd.h b/migration/multifd.h
+index 11d5e273e6..9c0a2a0701 100644
+--- a/migration/multifd.h
++++ b/migration/multifd.h
+@@ -20,7 +20,7 @@ void multifd_save_cleanup(void);
+ int multifd_load_setup(Error **errp);
+ int multifd_load_cleanup(Error **errp);
+ bool multifd_recv_all_channels_created(void);
+-bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp);
++void multifd_recv_new_channel(QIOChannel *ioc, Error **errp);
+ void multifd_recv_sync_main(void);
+ int multifd_send_sync_main(QEMUFile *f);
+ int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset);
+-- 
+2.37.3
+

SOURCES/kvm-nbd-server-Request-TCP_NODELAY.patch

@@ -0,0 +1,55 @@
+From 17c5524ada3f2ca9a9c645f540bedc5575302059 Mon Sep 17 00:00:00 2001
+From: Eric Blake <eblake@redhat.com>
+Date: Mon, 3 Apr 2023 19:40:47 -0500
+Subject: [PATCH 5/5] nbd/server: Request TCP_NODELAY
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Eric Blake <eblake@redhat.com>
+RH-MergeRequest: 274: nbd: improve TLS performance of NBD server
+RH-Bugzilla: 2035712
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Commit: [2/2] 092145077756cda2a4f849c5911031b0fc4a2134 (ebblake/qemu-kvm)
+
+Nagle's algorithm adds latency in order to reduce network packet
+overhead on small packets.  But when we are already using corking to
+merge smaller packets into transactional requests, the extra delay
+from TCP defaults just gets in the way (see recent commit bd2cd4a4).
+
+For reference, qemu as an NBD client already requests TCP_NODELAY (see
+nbd_connect() in nbd/client-connection.c); as does libnbd as a client
+[1], and nbdkit as a server [2].  Furthermore, the NBD spec recommends
+the use of TCP_NODELAY [3].
+
+[1] https://gitlab.com/nbdkit/libnbd/-/blob/a48a1142/generator/states-connect.c#L39
+[2] https://gitlab.com/nbdkit/nbdkit/-/blob/45b72f5b/server/sockets.c#L430
+[3] https://github.com/NetworkBlockDevice/nbd/blob/master/doc/proto.md#protocol-phases
+
+CC: Florian Westphal <fw@strlen.de>
+Signed-off-by: Eric Blake <eblake@redhat.com>
+Message-Id: <20230404004047.142086-1-eblake@redhat.com>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+(cherry picked from commit f1426881a827a6d3f31b65616c4a8db1e9e7c45e)
+Signed-off-by: Eric Blake <eblake@redhat.com>
+---
+ nbd/server.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/nbd/server.c b/nbd/server.c
+index a5edc7f681..6db124cf53 100644
+--- a/nbd/server.c
++++ b/nbd/server.c
+@@ -2738,6 +2738,7 @@ void nbd_client_new(QIOChannelSocket *sioc,
+     }
+     client->tlsauthz = g_strdup(tlsauthz);
+     client->sioc = sioc;
++    qio_channel_set_delay(QIO_CHANNEL(sioc), false);
+     object_ref(OBJECT(client->sioc));
+     client->ioc = QIO_CHANNEL(sioc);
+     object_ref(OBJECT(client->ioc));
+-- 
+2.39.1
+

SOURCES/kvm-nbd-server-push-pending-frames-after-sending-reply.patch

@@ -0,0 +1,72 @@
+From 170872370c6f3c916e741eb32d80431995d7a870 Mon Sep 17 00:00:00 2001
+From: Florian Westphal <fw@strlen.de>
+Date: Fri, 24 Mar 2023 11:47:20 +0100
+Subject: [PATCH 4/5] nbd/server: push pending frames after sending reply
+
+RH-Author: Eric Blake <eblake@redhat.com>
+RH-MergeRequest: 274: nbd: improve TLS performance of NBD server
+RH-Bugzilla: 2035712
+RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
+RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Commit: [1/2] ab92c06c48810aa40380de0433dcac4c6e4be9a5 (ebblake/qemu-kvm)
+
+qemu-nbd doesn't set TCP_NODELAY on the tcp socket.
+
+Kernel waits for more data and avoids transmission of small packets.
+Without TLS this is barely noticeable, but with TLS this really shows.
+
+Booting a VM via qemu-nbd on localhost (with tls) takes more than
+2 minutes on my system.  tcpdump shows frequent wait periods, where no
+packets get sent for a 40ms period.
+
+Add explicit (un)corking when processing (and responding to) requests.
+"TCP_CORK, &zero" after earlier "CORK, &one" will flush pending data.
+
+VM Boot time:
+main:    no tls:  23s, with tls: 2m45s
+patched: no tls:  14s, with tls: 15s
+
+VM Boot time, qemu-nbd via network (same lan):
+main:    no tls:  18s, with tls: 1m50s
+patched: no tls:  17s, with tls: 18s
+
+Future optimization: if we could detect if there is another pending
+request we could defer the uncork operation because more data would be
+appended.
+
+Signed-off-by: Florian Westphal <fw@strlen.de>
+Message-Id: <20230324104720.2498-1-fw@strlen.de>
+Reviewed-by: Eric Blake <eblake@redhat.com>
+Reviewed-by: Kevin Wolf <kwolf@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit bd2cd4a441ded163b62371790876f28a9b834317)
+Signed-off-by: Eric Blake <eblake@redhat.com>
+---
+ nbd/server.c | 3 +++
+ 1 file changed, 3 insertions(+)
+
+diff --git a/nbd/server.c b/nbd/server.c
+index 4630dd7322..a5edc7f681 100644
+--- a/nbd/server.c
++++ b/nbd/server.c
+@@ -2647,6 +2647,8 @@ static coroutine_fn void nbd_trip(void *opaque)
+         goto disconnect;
+     }
+ 
++    qio_channel_set_cork(client->ioc, true);
++
+     if (ret < 0) {
+         /* It wans't -EIO, so, according to nbd_co_receive_request()
+          * semantics, we should return the error to the client. */
+@@ -2672,6 +2674,7 @@ static coroutine_fn void nbd_trip(void *opaque)
+         goto disconnect;
+     }
+ 
++    qio_channel_set_cork(client->ioc, false);
+ done:
+     nbd_request_put(req);
+     nbd_client_put(client);
+-- 
+2.39.1
+

SOURCES/kvm-net-Provide-MemReentrancyGuard-to-qemu_new_nic.patch

@@ -0,0 +1,611 @@
+From 2ae925a6d55a77627be8d1146f2b9ed139dbdb77 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Thu, 23 Nov 2023 11:30:46 -0500
+Subject: [PATCH 1/4] net: Provide MemReentrancyGuard * to qemu_new_nic()
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 331: net: Provide MemReentrancyGuard * to qemu_new_nic()
+RH-Jira: RHEL-7309
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
+RH-Acked-by: Jason Wang <jasowang@redhat.com>
+RH-Commit: [1/2] bc963fb349b90288f547de97a5cbe9a74f856419 (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Jira: https://issues.redhat.com/browse/RHEL-7309
+CVE: CVE-2023-3019
+Upstream: Merged
+Conflicts: hw/net/hw/net/xen_nic.c seems to have undergone significant changes upstream,
+           so the change had to be manually adapted to the old code.
+
+commit 7d0fefdf81f5973334c344f6b8e1896c309dff66
+Author: Akihiko Odaki <akihiko.odaki@daynix.com>
+Date:   Thu Jun 1 12:18:58 2023 +0900
+
+    net: Provide MemReentrancyGuard * to qemu_new_nic()
+
+    Recently MemReentrancyGuard was added to DeviceState to record that the
+    device is engaging in I/O. The network device backend needs to update it
+    when delivering a packet to a device.
+
+    In preparation for such a change, add MemReentrancyGuard * as a
+    parameter of qemu_new_nic().
+
+    Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
+    Reviewed-by: Alexander Bulekov <alxndr@bu.edu>
+    Signed-off-by: Jason Wang <jasowang@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ hw/net/allwinner-sun8i-emac.c | 3 ++-
+ hw/net/allwinner_emac.c       | 3 ++-
+ hw/net/cadence_gem.c          | 3 ++-
+ hw/net/dp8393x.c              | 3 ++-
+ hw/net/e1000.c                | 3 ++-
+ hw/net/e1000e.c               | 2 +-
+ hw/net/eepro100.c             | 4 +++-
+ hw/net/etraxfs_eth.c          | 3 ++-
+ hw/net/fsl_etsec/etsec.c      | 3 ++-
+ hw/net/ftgmac100.c            | 3 ++-
+ hw/net/i82596.c               | 2 +-
+ hw/net/imx_fec.c              | 2 +-
+ hw/net/lan9118.c              | 3 ++-
+ hw/net/mcf_fec.c              | 3 ++-
+ hw/net/mipsnet.c              | 3 ++-
+ hw/net/msf2-emac.c            | 3 ++-
+ hw/net/ne2000-isa.c           | 3 ++-
+ hw/net/ne2000-pci.c           | 3 ++-
+ hw/net/npcm7xx_emc.c          | 3 ++-
+ hw/net/opencores_eth.c        | 3 ++-
+ hw/net/pcnet.c                | 3 ++-
+ hw/net/rocker/rocker_fp.c     | 4 ++--
+ hw/net/rtl8139.c              | 3 ++-
+ hw/net/smc91c111.c            | 3 ++-
+ hw/net/spapr_llan.c           | 3 ++-
+ hw/net/stellaris_enet.c       | 3 ++-
+ hw/net/sungem.c               | 2 +-
+ hw/net/sunhme.c               | 3 ++-
+ hw/net/tulip.c                | 3 ++-
+ hw/net/virtio-net.c           | 6 ++++--
+ hw/net/vmxnet3.c              | 2 +-
+ hw/net/xen_nic.c              | 3 ++-
+ hw/net/xgmac.c                | 3 ++-
+ hw/net/xilinx_axienet.c       | 3 ++-
+ hw/net/xilinx_ethlite.c       | 3 ++-
+ hw/usb/dev-network.c          | 3 ++-
+ include/net/net.h             | 1 +
+ net/net.c                     | 1 +
+ 38 files changed, 72 insertions(+), 38 deletions(-)
+
+diff --git a/hw/net/allwinner-sun8i-emac.c b/hw/net/allwinner-sun8i-emac.c
+index ff611f18fb..9d0885ee15 100644
+--- a/hw/net/allwinner-sun8i-emac.c
++++ b/hw/net/allwinner-sun8i-emac.c
+@@ -810,7 +810,8 @@ static void allwinner_sun8i_emac_realize(DeviceState *dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_allwinner_sun8i_emac_info, &s->conf,
+-                           object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ }
+ 
+diff --git a/hw/net/allwinner_emac.c b/hw/net/allwinner_emac.c
+index ddddf35c45..b3d73143bf 100644
+--- a/hw/net/allwinner_emac.c
++++ b/hw/net/allwinner_emac.c
+@@ -453,7 +453,8 @@ static void aw_emac_realize(DeviceState *dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_aw_emac_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ 
+     fifo8_create(&s->rx_fifo, RX_FIFO_SIZE);
+diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c
+index 24b3a0ff66..cb61a76417 100644
+--- a/hw/net/cadence_gem.c
++++ b/hw/net/cadence_gem.c
+@@ -1633,7 +1633,8 @@ static void gem_realize(DeviceState *dev, Error **errp)
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+ 
+     s->nic = qemu_new_nic(&net_gem_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+ 
+     if (s->jumbo_max_len > MAX_FRAME_SIZE) {
+         error_setg(errp, "jumbo-max-len is greater than %d",
+diff --git a/hw/net/dp8393x.c b/hw/net/dp8393x.c
+index 45b954e46c..abfcc6f69f 100644
+--- a/hw/net/dp8393x.c
++++ b/hw/net/dp8393x.c
+@@ -943,7 +943,8 @@ static void dp8393x_realize(DeviceState *dev, Error **errp)
+                           "dp8393x-regs", SONIC_REG_COUNT << s->it_shift);
+ 
+     s->nic = qemu_new_nic(&net_dp83932_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ 
+     s->watchdog = timer_new_ns(QEMU_CLOCK_VIRTUAL, dp8393x_watchdog, s);
+diff --git a/hw/net/e1000.c b/hw/net/e1000.c
+index 282d01e374..86da1ae39e 100644
+--- a/hw/net/e1000.c
++++ b/hw/net/e1000.c
+@@ -1733,7 +1733,8 @@ static void pci_e1000_realize(PCIDevice *pci_dev, Error **errp)
+                                macaddr);
+ 
+     d->nic = qemu_new_nic(&net_e1000_info, &d->conf,
+-                          object_get_typename(OBJECT(d)), dev->id, d);
++                          object_get_typename(OBJECT(d)), dev->id,
++                          &dev->mem_reentrancy_guard, d);
+ 
+     qemu_format_nic_info_str(qemu_get_queue(d->nic), macaddr);
+ 
+diff --git a/hw/net/e1000e.c b/hw/net/e1000e.c
+index d35bc1f0b0..c6096fa848 100644
+--- a/hw/net/e1000e.c
++++ b/hw/net/e1000e.c
+@@ -340,7 +340,7 @@ e1000e_init_net_peer(E1000EState *s, PCIDevice *pci_dev, uint8_t *macaddr)
+     int i;
+ 
+     s->nic = qemu_new_nic(&net_e1000e_info, &s->conf,
+-        object_get_typename(OBJECT(s)), dev->id, s);
++        object_get_typename(OBJECT(s)), dev->id, &dev->mem_reentrancy_guard, s);
+ 
+     s->core.max_queue_num = s->conf.peers.queues ? s->conf.peers.queues - 1 : 0;
+ 
+diff --git a/hw/net/eepro100.c b/hw/net/eepro100.c
+index 16e95ef9cc..16ca4dda04 100644
+--- a/hw/net/eepro100.c
++++ b/hw/net/eepro100.c
+@@ -1865,7 +1865,9 @@ static void e100_nic_realize(PCIDevice *pci_dev, Error **errp)
+     nic_reset(s);
+ 
+     s->nic = qemu_new_nic(&net_eepro100_info, &s->conf,
+-                          object_get_typename(OBJECT(pci_dev)), pci_dev->qdev.id, s);
++                          object_get_typename(OBJECT(pci_dev)),
++                          pci_dev->qdev.id,
++                          &pci_dev->qdev.mem_reentrancy_guard, s);
+ 
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+     TRACE(OTHER, logout("%s\n", qemu_get_queue(s->nic)->info_str));
+diff --git a/hw/net/etraxfs_eth.c b/hw/net/etraxfs_eth.c
+index 1b82aec794..ba57a978d1 100644
+--- a/hw/net/etraxfs_eth.c
++++ b/hw/net/etraxfs_eth.c
+@@ -618,7 +618,8 @@ static void etraxfs_eth_realize(DeviceState *dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_etraxfs_info, &s->conf,
+-                          object_get_typename(OBJECT(s)), dev->id, s);
++                          object_get_typename(OBJECT(s)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ 
+     s->phy.read = tdk_read;
+diff --git a/hw/net/fsl_etsec/etsec.c b/hw/net/fsl_etsec/etsec.c
+index bd9d62b559..f790613b52 100644
+--- a/hw/net/fsl_etsec/etsec.c
++++ b/hw/net/fsl_etsec/etsec.c
+@@ -391,7 +391,8 @@ static void etsec_realize(DeviceState *dev, Error **errp)
+     eTSEC        *etsec = ETSEC_COMMON(dev);
+ 
+     etsec->nic = qemu_new_nic(&net_etsec_info, &etsec->conf,
+-                              object_get_typename(OBJECT(dev)), dev->id, etsec);
++                              object_get_typename(OBJECT(dev)), dev->id,
++                              &dev->mem_reentrancy_guard, etsec);
+     qemu_format_nic_info_str(qemu_get_queue(etsec->nic), etsec->conf.macaddr.a);
+ 
+     etsec->ptimer = ptimer_init(etsec_timer_hit, etsec, PTIMER_POLICY_DEFAULT);
+diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c
+index 25685ba3a9..781e7f352e 100644
+--- a/hw/net/ftgmac100.c
++++ b/hw/net/ftgmac100.c
+@@ -1111,7 +1111,8 @@ static void ftgmac100_realize(DeviceState *dev, Error **errp)
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+ 
+     s->nic = qemu_new_nic(&net_ftgmac100_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ }
+ 
+diff --git a/hw/net/i82596.c b/hw/net/i82596.c
+index ec21e2699a..dc64246f75 100644
+--- a/hw/net/i82596.c
++++ b/hw/net/i82596.c
+@@ -743,7 +743,7 @@ void i82596_common_init(DeviceState *dev, I82596State *s, NetClientInfo *info)
+         qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     }
+     s->nic = qemu_new_nic(info, &s->conf, object_get_typename(OBJECT(dev)),
+-                dev->id, s);
++                dev->id, &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ 
+     if (USE_TIMER) {
+diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c
+index 9c7035bc94..ed19ee9350 100644
+--- a/hw/net/imx_fec.c
++++ b/hw/net/imx_fec.c
+@@ -1310,7 +1310,7 @@ static void imx_eth_realize(DeviceState *dev, Error **errp)
+ 
+     s->nic = qemu_new_nic(&imx_eth_net_info, &s->conf,
+                           object_get_typename(OBJECT(dev)),
+-                          dev->id, s);
++                          dev->id, &dev->mem_reentrancy_guard, s);
+ 
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ }
+diff --git a/hw/net/lan9118.c b/hw/net/lan9118.c
+index 6aff424cbe..942bce9ae6 100644
+--- a/hw/net/lan9118.c
++++ b/hw/net/lan9118.c
+@@ -1354,7 +1354,8 @@ static void lan9118_realize(DeviceState *dev, Error **errp)
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+ 
+     s->nic = qemu_new_nic(&net_lan9118_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+     s->eeprom[0] = 0xa5;
+     for (i = 0; i < 6; i++) {
+diff --git a/hw/net/mcf_fec.c b/hw/net/mcf_fec.c
+index 25e3e453ab..a6be7bf413 100644
+--- a/hw/net/mcf_fec.c
++++ b/hw/net/mcf_fec.c
+@@ -643,7 +643,8 @@ static void mcf_fec_realize(DeviceState *dev, Error **errp)
+     mcf_fec_state *s = MCF_FEC_NET(dev);
+ 
+     s->nic = qemu_new_nic(&net_mcf_fec_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ }
+ 
+diff --git a/hw/net/mipsnet.c b/hw/net/mipsnet.c
+index 2ade72dea0..8e925de867 100644
+--- a/hw/net/mipsnet.c
++++ b/hw/net/mipsnet.c
+@@ -255,7 +255,8 @@ static void mipsnet_realize(DeviceState *dev, Error **errp)
+     sysbus_init_irq(sbd, &s->irq);
+ 
+     s->nic = qemu_new_nic(&net_mipsnet_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ }
+ 
+diff --git a/hw/net/msf2-emac.c b/hw/net/msf2-emac.c
+index 9278fdce0b..1efa3dbf01 100644
+--- a/hw/net/msf2-emac.c
++++ b/hw/net/msf2-emac.c
+@@ -527,7 +527,8 @@ static void msf2_emac_realize(DeviceState *dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_msf2_emac_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ }
+ 
+diff --git a/hw/net/ne2000-isa.c b/hw/net/ne2000-isa.c
+index dd6f6e34d3..30bd20c293 100644
+--- a/hw/net/ne2000-isa.c
++++ b/hw/net/ne2000-isa.c
+@@ -74,7 +74,8 @@ static void isa_ne2000_realizefn(DeviceState *dev, Error **errp)
+     ne2000_reset(s);
+ 
+     s->nic = qemu_new_nic(&net_ne2000_isa_info, &s->c,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->c.macaddr.a);
+ }
+ 
+diff --git a/hw/net/ne2000-pci.c b/hw/net/ne2000-pci.c
+index 9e5d10859a..4f8a699081 100644
+--- a/hw/net/ne2000-pci.c
++++ b/hw/net/ne2000-pci.c
+@@ -71,7 +71,8 @@ static void pci_ne2000_realize(PCIDevice *pci_dev, Error **errp)
+ 
+     s->nic = qemu_new_nic(&net_ne2000_info, &s->c,
+                           object_get_typename(OBJECT(pci_dev)),
+-                          pci_dev->qdev.id, s);
++                          pci_dev->qdev.id,
++                          &pci_dev->qdev.mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->c.macaddr.a);
+ }
+ 
+diff --git a/hw/net/npcm7xx_emc.c b/hw/net/npcm7xx_emc.c
+index 7c892f820f..dd1d0ad3bc 100644
+--- a/hw/net/npcm7xx_emc.c
++++ b/hw/net/npcm7xx_emc.c
+@@ -802,7 +802,8 @@ static void npcm7xx_emc_realize(DeviceState *dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&emc->conf.macaddr);
+     emc->nic = qemu_new_nic(&net_npcm7xx_emc_info, &emc->conf,
+-                            object_get_typename(OBJECT(dev)), dev->id, emc);
++                            object_get_typename(OBJECT(dev)), dev->id,
++                            &dev->mem_reentrancy_guard, emc);
+     qemu_format_nic_info_str(qemu_get_queue(emc->nic), emc->conf.macaddr.a);
+ }
+ 
+diff --git a/hw/net/opencores_eth.c b/hw/net/opencores_eth.c
+index 0b3dc3146e..f96d6ea2cc 100644
+--- a/hw/net/opencores_eth.c
++++ b/hw/net/opencores_eth.c
+@@ -732,7 +732,8 @@ static void sysbus_open_eth_realize(DeviceState *dev, Error **errp)
+     sysbus_init_irq(sbd, &s->irq);
+ 
+     s->nic = qemu_new_nic(&net_open_eth_info, &s->conf,
+-                          object_get_typename(OBJECT(s)), dev->id, s);
++                          object_get_typename(OBJECT(s)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+ }
+ 
+ static void qdev_open_eth_reset(DeviceState *dev)
+diff --git a/hw/net/pcnet.c b/hw/net/pcnet.c
+index dcd3fc4948..da910a70bf 100644
+--- a/hw/net/pcnet.c
++++ b/hw/net/pcnet.c
+@@ -1718,7 +1718,8 @@ void pcnet_common_init(DeviceState *dev, PCNetState *s, NetClientInfo *info)
+     s->poll_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, pcnet_poll_timer, s);
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+-    s->nic = qemu_new_nic(info, &s->conf, object_get_typename(OBJECT(dev)), dev->id, s);
++    s->nic = qemu_new_nic(info, &s->conf, object_get_typename(OBJECT(dev)),
++                          dev->id, &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ 
+     /* Initialize the PROM */
+diff --git a/hw/net/rocker/rocker_fp.c b/hw/net/rocker/rocker_fp.c
+index cbeed65bd5..0d21948ada 100644
+--- a/hw/net/rocker/rocker_fp.c
++++ b/hw/net/rocker/rocker_fp.c
+@@ -241,8 +241,8 @@ FpPort *fp_port_alloc(Rocker *r, char *sw_name,
+     port->conf.bootindex = -1;
+     port->conf.peers = *peers;
+ 
+-    port->nic = qemu_new_nic(&fp_port_info, &port->conf,
+-                             sw_name, NULL, port);
++    port->nic = qemu_new_nic(&fp_port_info, &port->conf, sw_name, NULL,
++                             &DEVICE(r)->mem_reentrancy_guard, port);
+     qemu_format_nic_info_str(qemu_get_queue(port->nic),
+                              port->conf.macaddr.a);
+ 
+diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
+index 3ffb9dd22c..a3565c7159 100644
+--- a/hw/net/rtl8139.c
++++ b/hw/net/rtl8139.c
+@@ -3400,7 +3400,8 @@ static void pci_rtl8139_realize(PCIDevice *dev, Error **errp)
+     s->eeprom.contents[9] = s->conf.macaddr.a[4] | s->conf.macaddr.a[5] << 8;
+ 
+     s->nic = qemu_new_nic(&net_rtl8139_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), d->id, s);
++                          object_get_typename(OBJECT(dev)), d->id,
++                          &d->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ 
+     s->cplus_txbuffer = NULL;
+diff --git a/hw/net/smc91c111.c b/hw/net/smc91c111.c
+index ad778cd8fc..4eda971ef3 100644
+--- a/hw/net/smc91c111.c
++++ b/hw/net/smc91c111.c
+@@ -783,7 +783,8 @@ static void smc91c111_realize(DeviceState *dev, Error **errp)
+     sysbus_init_irq(sbd, &s->irq);
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_smc91c111_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+     /* ??? Save/restore.  */
+ }
+diff --git a/hw/net/spapr_llan.c b/hw/net/spapr_llan.c
+index a6876a936d..475d5f3a34 100644
+--- a/hw/net/spapr_llan.c
++++ b/hw/net/spapr_llan.c
+@@ -325,7 +325,8 @@ static void spapr_vlan_realize(SpaprVioDevice *sdev, Error **errp)
+     memcpy(&dev->perm_mac.a, &dev->nicconf.macaddr.a, sizeof(dev->perm_mac.a));
+ 
+     dev->nic = qemu_new_nic(&net_spapr_vlan_info, &dev->nicconf,
+-                            object_get_typename(OBJECT(sdev)), sdev->qdev.id, dev);
++                            object_get_typename(OBJECT(sdev)), sdev->qdev.id,
++                            &sdev->qdev.mem_reentrancy_guard, dev);
+     qemu_format_nic_info_str(qemu_get_queue(dev->nic), dev->nicconf.macaddr.a);
+ 
+     dev->rxp_timer = timer_new_us(QEMU_CLOCK_VIRTUAL, spapr_vlan_flush_rx_queue,
+diff --git a/hw/net/stellaris_enet.c b/hw/net/stellaris_enet.c
+index 8dd60783d8..6768a6912f 100644
+--- a/hw/net/stellaris_enet.c
++++ b/hw/net/stellaris_enet.c
+@@ -492,7 +492,8 @@ static void stellaris_enet_realize(DeviceState *dev, Error **errp)
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+ 
+     s->nic = qemu_new_nic(&net_stellaris_enet_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ }
+ 
+diff --git a/hw/net/sungem.c b/hw/net/sungem.c
+index 3684a4d733..c12d44e9dc 100644
+--- a/hw/net/sungem.c
++++ b/hw/net/sungem.c
+@@ -1361,7 +1361,7 @@ static void sungem_realize(PCIDevice *pci_dev, Error **errp)
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_sungem_info, &s->conf,
+                           object_get_typename(OBJECT(dev)),
+-                          dev->id, s);
++                          dev->id, &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic),
+                              s->conf.macaddr.a);
+ }
+diff --git a/hw/net/sunhme.c b/hw/net/sunhme.c
+index fc34905f87..fa98528d71 100644
+--- a/hw/net/sunhme.c
++++ b/hw/net/sunhme.c
+@@ -892,7 +892,8 @@ static void sunhme_realize(PCIDevice *pci_dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_sunhme_info, &s->conf,
+-                          object_get_typename(OBJECT(d)), d->id, s);
++                          object_get_typename(OBJECT(d)), d->id,
++                          &d->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ }
+ 
+diff --git a/hw/net/tulip.c b/hw/net/tulip.c
+index ca69f7ea5e..985c4c14a4 100644
+--- a/hw/net/tulip.c
++++ b/hw/net/tulip.c
+@@ -981,7 +981,8 @@ static void pci_tulip_realize(PCIDevice *pci_dev, Error **errp)
+ 
+     s->nic = qemu_new_nic(&net_tulip_info, &s->c,
+                           object_get_typename(OBJECT(pci_dev)),
+-                          pci_dev->qdev.id, s);
++                          pci_dev->qdev.id,
++                          &pci_dev->qdev.mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->c.macaddr.a);
+ }
+ 
+diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
+index ddaa8fa122..f5f07f8e63 100644
+--- a/hw/net/virtio-net.c
++++ b/hw/net/virtio-net.c
+@@ -3512,10 +3512,12 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
+          * Happen when virtio_net_set_netclient_name has been called.
+          */
+         n->nic = qemu_new_nic(&net_virtio_info, &n->nic_conf,
+-                              n->netclient_type, n->netclient_name, n);
++                              n->netclient_type, n->netclient_name,
++                              &dev->mem_reentrancy_guard, n);
+     } else {
+         n->nic = qemu_new_nic(&net_virtio_info, &n->nic_conf,
+-                              object_get_typename(OBJECT(dev)), dev->id, n);
++                              object_get_typename(OBJECT(dev)), dev->id,
++                              &dev->mem_reentrancy_guard, n);
+     }
+ 
+     for (i = 0; i < n->max_queue_pairs; i++) {
+diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c
+index f65af4e9ef..d4df039c55 100644
+--- a/hw/net/vmxnet3.c
++++ b/hw/net/vmxnet3.c
+@@ -2078,7 +2078,7 @@ static void vmxnet3_net_init(VMXNET3State *s)
+ 
+     s->nic = qemu_new_nic(&net_vmxnet3_info, &s->conf,
+                           object_get_typename(OBJECT(s)),
+-                          d->id, s);
++                          d->id, &d->mem_reentrancy_guard, s);
+ 
+     s->peer_has_vhdr = vmxnet3_peer_has_vnet_hdr(s);
+     s->tx_sop = true;
+diff --git a/hw/net/xen_nic.c b/hw/net/xen_nic.c
+index 5c815b4f0c..3d0b7820d3 100644
+--- a/hw/net/xen_nic.c
++++ b/hw/net/xen_nic.c
+@@ -294,7 +294,8 @@ static int net_init(struct XenLegacyDevice *xendev)
+     }
+ 
+     netdev->nic = qemu_new_nic(&net_xen_info, &netdev->conf,
+-                               "xen", NULL, netdev);
++                               "xen", NULL,
++                               &xendev->qdev.mem_reentrancy_guard, netdev);
+ 
+     snprintf(qemu_get_queue(netdev->nic)->info_str,
+              sizeof(qemu_get_queue(netdev->nic)->info_str),
+diff --git a/hw/net/xgmac.c b/hw/net/xgmac.c
+index 0ab6ae91aa..1f4f277d84 100644
+--- a/hw/net/xgmac.c
++++ b/hw/net/xgmac.c
+@@ -402,7 +402,8 @@ static void xgmac_enet_realize(DeviceState *dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_xgmac_enet_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ 
+     s->regs[XGMAC_ADDR_HIGH(0)] = (s->conf.macaddr.a[5] << 8) |
+diff --git a/hw/net/xilinx_axienet.c b/hw/net/xilinx_axienet.c
+index 990ff3a1c2..8a34243803 100644
+--- a/hw/net/xilinx_axienet.c
++++ b/hw/net/xilinx_axienet.c
+@@ -968,7 +968,8 @@ static void xilinx_enet_realize(DeviceState *dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_xilinx_enet_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ 
+     tdk_init(&s->TEMAC.phy);
+diff --git a/hw/net/xilinx_ethlite.c b/hw/net/xilinx_ethlite.c
+index 6e09f7e422..80cb869e22 100644
+--- a/hw/net/xilinx_ethlite.c
++++ b/hw/net/xilinx_ethlite.c
+@@ -235,7 +235,8 @@ static void xilinx_ethlite_realize(DeviceState *dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_xilinx_ethlite_info, &s->conf,
+-                          object_get_typename(OBJECT(dev)), dev->id, s);
++                          object_get_typename(OBJECT(dev)), dev->id,
++                          &dev->mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+ }
+ 
+diff --git a/hw/usb/dev-network.c b/hw/usb/dev-network.c
+index 6c49c16015..ae447a8bc3 100644
+--- a/hw/usb/dev-network.c
++++ b/hw/usb/dev-network.c
+@@ -1362,7 +1362,8 @@ static void usb_net_realize(USBDevice *dev, Error **errp)
+ 
+     qemu_macaddr_default_if_unset(&s->conf.macaddr);
+     s->nic = qemu_new_nic(&net_usbnet_info, &s->conf,
+-                          object_get_typename(OBJECT(s)), s->dev.qdev.id, s);
++                          object_get_typename(OBJECT(s)), s->dev.qdev.id,
++                          &s->dev.qdev.mem_reentrancy_guard, s);
+     qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a);
+     snprintf(s->usbstring_mac, sizeof(s->usbstring_mac),
+              "%02x%02x%02x%02x%02x%02x",
+diff --git a/include/net/net.h b/include/net/net.h
+index 523136c7ac..1457b6c014 100644
+--- a/include/net/net.h
++++ b/include/net/net.h
+@@ -145,6 +145,7 @@ NICState *qemu_new_nic(NetClientInfo *info,
+                        NICConf *conf,
+                        const char *model,
+                        const char *name,
++                       MemReentrancyGuard *reentrancy_guard,
+                        void *opaque);
+ void qemu_del_nic(NICState *nic);
+ NetClientState *qemu_get_subqueue(NICState *nic, int queue_index);
+diff --git a/net/net.c b/net/net.c
+index f0d14dbfc1..669e194c4b 100644
+--- a/net/net.c
++++ b/net/net.c
+@@ -299,6 +299,7 @@ NICState *qemu_new_nic(NetClientInfo *info,
+                        NICConf *conf,
+                        const char *model,
+                        const char *name,
++                       MemReentrancyGuard *reentrancy_guard,
+                        void *opaque)
+ {
+     NetClientState **peers = conf->peers.ncs;
+-- 
+2.41.0
+

SOURCES/kvm-net-Update-MemReentrancyGuard-for-NIC.patch

@@ -0,0 +1,105 @@
+From d58671091daf8c325a6f1cd87737d94b5fb51d12 Mon Sep 17 00:00:00 2001
+From: Jon Maloy <jmaloy@redhat.com>
+Date: Thu, 23 Nov 2023 11:30:46 -0500
+Subject: [PATCH 2/4] net: Update MemReentrancyGuard for NIC
+
+RH-Author: Jon Maloy <jmaloy@redhat.com>
+RH-MergeRequest: 331: net: Provide MemReentrancyGuard * to qemu_new_nic()
+RH-Jira: RHEL-7309
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
+RH-Acked-by: Jason Wang <jasowang@redhat.com>
+RH-Commit: [2/2] b116efe725dd838c2cab9bd2240112f3c6c46d6a (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)
+
+Jira: https://issues.redhat.com/browse/RHEL-7309
+CVE: CVE-2023-3019
+Upstream: Merged
+
+commit 9050f976e447444ea6ee2ba12c9f77e4b0dc54bc
+Author: Akihiko Odaki <akihiko.odaki@daynix.com>
+Date:   Thu Jun 1 12:18:59 2023 +0900
+
+    net: Update MemReentrancyGuard for NIC
+
+    Recently MemReentrancyGuard was added to DeviceState to record that the
+    device is engaging in I/O. The network device backend needs to update it
+    when delivering a packet to a device.
+
+    This implementation follows what bottom half does, but it does not add
+    a tracepoint for the case that the network device backend started
+    delivering a packet to a device which is already engaging in I/O. This
+    is because such reentrancy frequently happens for
+    qemu_flush_queued_packets() and is insignificant.
+
+    Fixes: CVE-2023-3019
+    Reported-by: Alexander Bulekov <alxndr@bu.edu>
+    Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
+    Acked-by: Alexander Bulekov <alxndr@bu.edu>
+    Signed-off-by: Jason Wang <jasowang@redhat.com>
+
+Signed-off-by: Jon Maloy <jmaloy@redhat.com>
+---
+ include/net/net.h |  1 +
+ net/net.c         | 14 ++++++++++++++
+ 2 files changed, 15 insertions(+)
+
+diff --git a/include/net/net.h b/include/net/net.h
+index 1457b6c014..11d4564ea1 100644
+--- a/include/net/net.h
++++ b/include/net/net.h
+@@ -112,6 +112,7 @@ struct NetClientState {
+ typedef struct NICState {
+     NetClientState *ncs;
+     NICConf *conf;
++    MemReentrancyGuard *reentrancy_guard;
+     void *opaque;
+     bool peer_deleted;
+ } NICState;
+diff --git a/net/net.c b/net/net.c
+index 669e194c4b..b3008a52b7 100644
+--- a/net/net.c
++++ b/net/net.c
+@@ -312,6 +312,7 @@ NICState *qemu_new_nic(NetClientInfo *info,
+     nic = g_malloc0(info->size + sizeof(NetClientState) * queues);
+     nic->ncs = (void *)nic + info->size;
+     nic->conf = conf;
++    nic->reentrancy_guard = reentrancy_guard,
+     nic->opaque = opaque;
+ 
+     for (i = 0; i < queues; i++) {
+@@ -767,6 +768,7 @@ static ssize_t qemu_deliver_packet_iov(NetClientState *sender,
+                                        int iovcnt,
+                                        void *opaque)
+ {
++    MemReentrancyGuard *owned_reentrancy_guard;
+     NetClientState *nc = opaque;
+     int ret;
+ 
+@@ -779,12 +781,24 @@ static ssize_t qemu_deliver_packet_iov(NetClientState *sender,
+         return 0;
+     }
+ 
++    if (nc->info->type != NET_CLIENT_DRIVER_NIC ||
++        qemu_get_nic(nc)->reentrancy_guard->engaged_in_io) {
++        owned_reentrancy_guard = NULL;
++    } else {
++        owned_reentrancy_guard = qemu_get_nic(nc)->reentrancy_guard;
++        owned_reentrancy_guard->engaged_in_io = true;
++    }
++
+     if (nc->info->receive_iov && !(flags & QEMU_NET_PACKET_FLAG_RAW)) {
+         ret = nc->info->receive_iov(nc, iov, iovcnt);
+     } else {
+         ret = nc_sendv_compat(nc, iov, iovcnt, flags);
+     }
+ 
++    if (owned_reentrancy_guard) {
++        owned_reentrancy_guard->engaged_in_io = false;
++    }
++
+     if (ret == 0) {
+         nc->receive_disabled = 1;
+     }
+-- 
+2.41.0
+

SOURCES/kvm-pc-bios-Add-support-for-List-Directed-IPL-from-ECKD-.patch

@@ -0,0 +1,376 @@
+From e11cffc152d9af9194139a37f86e357cb36298e8 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
+Date: Thu, 25 May 2023 12:50:19 +0200
+Subject: [PATCH 22/22] pc-bios: Add support for List-Directed IPL from ECKD
+ DASD
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Cédric Le Goater <clg@redhat.com>
+RH-MergeRequest: 279: Backport latest s390x-related fixes from upstream QEMU for qemu-kvm in RHEL 8.9
+RH-Bugzilla: 2169308 2209605
+RH-Acked-by: Thomas Huth <thuth@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Commit: [21/21] cab945af05566d892459a7c8ea3f114310d6bb67
+
+Bugzilla: https://bugzilla.redhat.com/2209605
+
+commit 8af5d141713f5d20c4bc1719eb746ef8b1746bd6
+Author: Jared Rossi <jrossi@linux.ibm.com>
+Date:   Tue Feb 21 12:45:48 2023 -0500
+
+    pc-bios: Add support for List-Directed IPL from ECKD DASD
+
+    Check for a List Directed IPL Boot Record, which would supersede the CCW type
+    entries.  If the record is valid, proceed to use the new style pointers
+    and perform LD-IPL. Each block pointer is interpreted as either an LD-IPL
+    pointer or a legacy CCW pointer depending on the type of IPL initiated.
+
+    In either case CCW- or LD-IPL is transparent to the user and will boot the same
+    image regardless of which set of pointers is used. Because the interactive boot
+    menu is only written with the old style pointers, the menu will be disabled for
+    List Directed IPL from ECKD DASD.
+
+    If the LD-IPL fails, retry the IPL using the CCW type pointers.
+
+    If no LD-IPL boot record is found, simply perform CCW type IPL as usual.
+
+    Signed-off-by: Jared Rossi <jrossi@linux.ibm.com>
+    Message-Id: <20230221174548.1866861-2-jrossi@linux.ibm.com>
+    [thuth: Drop some superfluous parantheses]
+    Signed-off-by: Thomas Huth <thuth@redhat.com>
+
+Signed-off-by: Cédric Le Goater <clg@redhat.com>
+---
+ pc-bios/s390-ccw/bootmap.c | 157 ++++++++++++++++++++++++++++---------
+ pc-bios/s390-ccw/bootmap.h |  30 ++++++-
+ 2 files changed, 148 insertions(+), 39 deletions(-)
+
+diff --git a/pc-bios/s390-ccw/bootmap.c b/pc-bios/s390-ccw/bootmap.c
+index 994e59c0b0..a2137449dc 100644
+--- a/pc-bios/s390-ccw/bootmap.c
++++ b/pc-bios/s390-ccw/bootmap.c
+@@ -72,42 +72,74 @@ static inline void verify_boot_info(BootInfo *bip)
+                "Bad block size in zIPL section of the 1st record.");
+ }
+ 
+-static block_number_t eckd_block_num(EckdCHS *chs)
++static void eckd_format_chs(ExtEckdBlockPtr *ptr,  bool ldipl,
++                            uint64_t *c,
++                            uint64_t *h,
++                            uint64_t *s)
++{
++    if (ldipl) {
++        *c = ptr->ldptr.chs.cylinder;
++        *h = ptr->ldptr.chs.head;
++        *s = ptr->ldptr.chs.sector;
++    } else {
++        *c = ptr->bptr.chs.cylinder;
++        *h = ptr->bptr.chs.head;
++        *s = ptr->bptr.chs.sector;
++    }
++}
++
++static block_number_t eckd_chs_to_block(uint64_t c, uint64_t h, uint64_t s)
+ {
+     const uint64_t sectors = virtio_get_sectors();
+     const uint64_t heads = virtio_get_heads();
+-    const uint64_t cylinder = chs->cylinder
+-                            + ((chs->head & 0xfff0) << 12);
+-    const uint64_t head = chs->head & 0x000f;
++    const uint64_t cylinder = c + ((h & 0xfff0) << 12);
++    const uint64_t head = h & 0x000f;
+     const block_number_t block = sectors * heads * cylinder
+                                + sectors * head
+-                               + chs->sector
+-                               - 1; /* block nr starts with zero */
++                               + s - 1; /* block nr starts with zero */
+     return block;
+ }
+ 
+-static bool eckd_valid_address(BootMapPointer *p)
++static block_number_t eckd_block_num(EckdCHS *chs)
+ {
+-    const uint64_t head = p->eckd.chs.head & 0x000f;
++    return eckd_chs_to_block(chs->cylinder, chs->head, chs->sector);
++}
++
++static block_number_t gen_eckd_block_num(ExtEckdBlockPtr *ptr, bool ldipl)
++{
++    uint64_t cyl, head, sec;
++    eckd_format_chs(ptr, ldipl, &cyl, &head, &sec);
++    return eckd_chs_to_block(cyl, head, sec);
++}
+ 
++static bool eckd_valid_chs(uint64_t cyl, uint64_t head, uint64_t sector)
++{
+     if (head >= virtio_get_heads()
+-        ||  p->eckd.chs.sector > virtio_get_sectors()
+-        ||  p->eckd.chs.sector <= 0) {
++        || sector > virtio_get_sectors()
++        || sector <= 0) {
+         return false;
+     }
+ 
+     if (!virtio_guessed_disk_nature() &&
+-        eckd_block_num(&p->eckd.chs) >= virtio_get_blocks()) {
++        eckd_chs_to_block(cyl, head, sector) >= virtio_get_blocks()) {
+         return false;
+     }
+ 
+     return true;
+ }
+ 
+-static block_number_t load_eckd_segments(block_number_t blk, uint64_t *address)
++static bool eckd_valid_address(ExtEckdBlockPtr *ptr, bool ldipl)
++{
++    uint64_t cyl, head, sec;
++    eckd_format_chs(ptr, ldipl, &cyl, &head, &sec);
++    return eckd_valid_chs(cyl, head, sec);
++}
++
++static block_number_t load_eckd_segments(block_number_t blk, bool ldipl,
++                                         uint64_t *address)
+ {
+     block_number_t block_nr;
+-    int j, rc;
++    int j, rc, count;
+     BootMapPointer *bprs = (void *)_bprs;
+     bool more_data;
+ 
+@@ -117,7 +149,7 @@ static block_number_t load_eckd_segments(block_number_t blk, uint64_t *address)
+     do {
+         more_data = false;
+         for (j = 0;; j++) {
+-            block_nr = eckd_block_num(&bprs[j].xeckd.bptr.chs);
++            block_nr = gen_eckd_block_num(&bprs[j].xeckd, ldipl);
+             if (is_null_block_number(block_nr)) { /* end of chunk */
+                 break;
+             }
+@@ -129,11 +161,26 @@ static block_number_t load_eckd_segments(block_number_t blk, uint64_t *address)
+                 break;
+             }
+ 
+-            IPL_assert(block_size_ok(bprs[j].xeckd.bptr.size),
++            /* List directed pointer does not store block size */
++            IPL_assert(ldipl || block_size_ok(bprs[j].xeckd.bptr.size),
+                        "bad chunk block size");
+-            IPL_assert(eckd_valid_address(&bprs[j]), "bad chunk ECKD addr");
+ 
+-            if ((bprs[j].xeckd.bptr.count == 0) && unused_space(&(bprs[j+1]),
++            if (!eckd_valid_address(&bprs[j].xeckd, ldipl)) {
++                /*
++                 * If an invalid address is found during LD-IPL then break and
++                 * retry as CCW
++                 */
++                IPL_assert(ldipl, "bad chunk ECKD addr");
++                break;
++            }
++
++            if (ldipl) {
++                count = bprs[j].xeckd.ldptr.count;
++            } else {
++                count = bprs[j].xeckd.bptr.count;
++            }
++
++            if (count == 0 && unused_space(&bprs[j + 1],
+                 sizeof(EckdBlockPtr))) {
+                 /* This is a "continue" pointer.
+                  * This ptr should be the last one in the current
+@@ -149,11 +196,10 @@ static block_number_t load_eckd_segments(block_number_t blk, uint64_t *address)
+             /* Load (count+1) blocks of code at (block_nr)
+              * to memory (address).
+              */
+-            rc = virtio_read_many(block_nr, (void *)(*address),
+-                                  bprs[j].xeckd.bptr.count+1);
++            rc = virtio_read_many(block_nr, (void *)(*address), count + 1);
+             IPL_assert(rc == 0, "code chunk read failed");
+ 
+-            *address += (bprs[j].xeckd.bptr.count+1) * virtio_get_block_size();
++            *address += (count + 1) * virtio_get_block_size();
+         }
+     } while (more_data);
+     return block_nr;
+@@ -237,8 +283,10 @@ static void run_eckd_boot_script(block_number_t bmt_block_nr,
+     uint64_t address;
+     BootMapTable *bmt = (void *)sec;
+     BootMapScript *bms = (void *)sec;
++    /* The S1B block number is NULL_BLOCK_NR if and only if it's an LD-IPL */
++    bool ldipl = (s1b_block_nr == NULL_BLOCK_NR);
+ 
+-    if (menu_is_enabled_zipl()) {
++    if (menu_is_enabled_zipl() && !ldipl) {
+         loadparm = eckd_get_boot_menu_index(s1b_block_nr);
+     }
+ 
+@@ -249,7 +297,7 @@ static void run_eckd_boot_script(block_number_t bmt_block_nr,
+     memset(sec, FREE_SPACE_FILLER, sizeof(sec));
+     read_block(bmt_block_nr, sec, "Cannot read Boot Map Table");
+ 
+-    block_nr = eckd_block_num(&bmt->entry[loadparm].xeckd.bptr.chs);
++    block_nr = gen_eckd_block_num(&bmt->entry[loadparm].xeckd, ldipl);
+     IPL_assert(block_nr != -1, "Cannot find Boot Map Table Entry");
+ 
+     memset(sec, FREE_SPACE_FILLER, sizeof(sec));
+@@ -264,13 +312,18 @@ static void run_eckd_boot_script(block_number_t bmt_block_nr,
+         }
+ 
+         address = bms->entry[i].address.load_address;
+-        block_nr = eckd_block_num(&bms->entry[i].blkptr.xeckd.bptr.chs);
++        block_nr = gen_eckd_block_num(&bms->entry[i].blkptr.xeckd, ldipl);
+ 
+         do {
+-            block_nr = load_eckd_segments(block_nr, &address);
++            block_nr = load_eckd_segments(block_nr, ldipl, &address);
+         } while (block_nr != -1);
+     }
+ 
++    if (ldipl && bms->entry[i].type != BOOT_SCRIPT_EXEC) {
++        /* Abort LD-IPL and retry as CCW-IPL */
++        return;
++    }
++
+     IPL_assert(bms->entry[i].type == BOOT_SCRIPT_EXEC,
+                "Unknown script entry type");
+     write_reset_psw(bms->entry[i].address.load_address); /* no return */
+@@ -380,6 +433,23 @@ static void ipl_eckd_ldl(ECKD_IPL_mode_t mode)
+     /* no return */
+ }
+ 
++static block_number_t eckd_find_bmt(ExtEckdBlockPtr *ptr)
++{
++    block_number_t blockno;
++    uint8_t tmp_sec[MAX_SECTOR_SIZE];
++    BootRecord *br;
++
++    blockno = gen_eckd_block_num(ptr, 0);
++    read_block(blockno, tmp_sec, "Cannot read boot record");
++    br = (BootRecord *)tmp_sec;
++    if (!magic_match(br->magic, ZIPL_MAGIC)) {
++        /* If the boot record is invalid, return and try CCW-IPL instead */
++        return NULL_BLOCK_NR;
++    }
++
++    return gen_eckd_block_num(&br->pgt.xeckd, 1);
++}
++
+ static void print_eckd_msg(void)
+ {
+     char msg[] = "Using ECKD scheme (block size *****), ";
+@@ -401,28 +471,43 @@ static void print_eckd_msg(void)
+ 
+ static void ipl_eckd(void)
+ {
+-    XEckdMbr *mbr = (void *)sec;
+-    LDL_VTOC *vlbl = (void *)sec;
++    IplVolumeLabel *vlbl = (void *)sec;
++    LDL_VTOC *vtoc = (void *)sec;
++    block_number_t ldipl_bmt; /* Boot Map Table for List-Directed IPL */
+ 
+     print_eckd_msg();
+ 
+-    /* Grab the MBR again */
++    /* Block 2 can contain either the CDL VOL1 label or the LDL VTOC */
+     memset(sec, FREE_SPACE_FILLER, sizeof(sec));
+-    read_block(0, mbr, "Cannot read block 0 on DASD");
++    read_block(2, vlbl, "Cannot read block 2");
+ 
+-    if (magic_match(mbr->magic, IPL1_MAGIC)) {
+-        ipl_eckd_cdl();         /* only returns in case of error */
+-        return;
++    /*
++     * First check for a list-directed-format pointer which would
++     * supersede the CCW pointer.
++     */
++    if (eckd_valid_address((ExtEckdBlockPtr *)&vlbl->f.br, 0)) {
++        ldipl_bmt = eckd_find_bmt((ExtEckdBlockPtr *)&vlbl->f.br);
++        if (ldipl_bmt) {
++            sclp_print("List-Directed\n");
++            /* LD-IPL does not use the S1B bock, just make it NULL */
++            run_eckd_boot_script(ldipl_bmt, NULL_BLOCK_NR);
++            /* Only return in error, retry as CCW-IPL */
++            sclp_print("Retrying IPL ");
++            print_eckd_msg();
++        }
++        memset(sec, FREE_SPACE_FILLER, sizeof(sec));
++        read_block(2, vtoc, "Cannot read block 2");
+     }
+ 
+-    /* LDL/CMS? */
+-    memset(sec, FREE_SPACE_FILLER, sizeof(sec));
+-    read_block(2, vlbl, "Cannot read block 2");
++    /* Not list-directed */
++    if (magic_match(vtoc->magic, VOL1_MAGIC)) {
++        ipl_eckd_cdl(); /* may return in error */
++    }
+ 
+-    if (magic_match(vlbl->magic, CMS1_MAGIC)) {
++    if (magic_match(vtoc->magic, CMS1_MAGIC)) {
+         ipl_eckd_ldl(ECKD_CMS); /* no return */
+     }
+-    if (magic_match(vlbl->magic, LNX1_MAGIC)) {
++    if (magic_match(vtoc->magic, LNX1_MAGIC)) {
+         ipl_eckd_ldl(ECKD_LDL); /* no return */
+     }
+ 
+diff --git a/pc-bios/s390-ccw/bootmap.h b/pc-bios/s390-ccw/bootmap.h
+index 3946aa3f8d..d4690a88c2 100644
+--- a/pc-bios/s390-ccw/bootmap.h
++++ b/pc-bios/s390-ccw/bootmap.h
+@@ -45,9 +45,23 @@ typedef struct EckdBlockPtr {
+                     * it's 0 for TablePtr, ScriptPtr, and SectionPtr */
+ } __attribute__ ((packed)) EckdBlockPtr;
+ 
+-typedef struct ExtEckdBlockPtr {
++typedef struct LdEckdCHS {
++    uint32_t cylinder;
++    uint8_t head;
++    uint8_t sector;
++} __attribute__ ((packed)) LdEckdCHS;
++
++typedef struct LdEckdBlockPtr {
++    LdEckdCHS chs; /* cylinder/head/sector is an address of the block */
++    uint8_t reserved[4];
++    uint16_t count;
++    uint32_t pad;
++} __attribute__ ((packed)) LdEckdBlockPtr;
++
++/* bptr is used for CCW type IPL, while ldptr is for list-directed IPL */
++typedef union ExtEckdBlockPtr {
+     EckdBlockPtr bptr;
+-    uint8_t reserved[8];
++    LdEckdBlockPtr ldptr;
+ } __attribute__ ((packed)) ExtEckdBlockPtr;
+ 
+ typedef union BootMapPointer {
+@@ -57,6 +71,15 @@ typedef union BootMapPointer {
+     ExtEckdBlockPtr xeckd;
+ } __attribute__ ((packed)) BootMapPointer;
+ 
++typedef struct BootRecord {
++    uint8_t magic[4];
++    uint32_t version;
++    uint64_t res1;
++    BootMapPointer pgt;
++    uint8_t reserved[510 - 32];
++    uint16_t os_id;
++} __attribute__ ((packed)) BootRecord;
++
+ /* aka Program Table */
+ typedef struct BootMapTable {
+     uint8_t magic[4];
+@@ -292,7 +315,8 @@ typedef struct IplVolumeLabel {
+         struct {
+             unsigned char key[4]; /* == "VOL1" */
+             unsigned char volser[6];
+-            unsigned char reserved[6];
++            unsigned char reserved[64];
++            EckdCHS br; /* Location of Boot Record for list-directed IPL */
+         } f;
+     };
+ } __attribute__((packed)) IplVolumeLabel;
+-- 
+2.37.3
+

SOURCES/kvm-physmem-add-missing-memory-barrier.patch

@@ -0,0 +1,55 @@
+From 01c09f31978154f0d2fd699621ae958a8c3ea2a5 Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Thu, 9 Mar 2023 08:15:24 -0500
+Subject: [PATCH 08/13] physmem: add missing memory barrier
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw()
+RH-Bugzilla: 2168472
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Eric Auger <eric.auger@redhat.com>
+RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Commit: [8/10] f6a9659f7cf40b78de6e85e4a7c06842273aa770
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472
+
+commit 33828ca11da08436e1b32f3e79dabce3061a0427
+Author: Paolo Bonzini <pbonzini@redhat.com>
+Date:   Fri Mar 3 14:36:32 2023 +0100
+
+    physmem: add missing memory barrier
+
+    Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+    Reviewed-by: David Hildenbrand <david@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ softmmu/physmem.c | 3 +++
+ 1 file changed, 3 insertions(+)
+
+diff --git a/softmmu/physmem.c b/softmmu/physmem.c
+index 4d0ef5f92f..2b96fad302 100644
+--- a/softmmu/physmem.c
++++ b/softmmu/physmem.c
+@@ -3087,6 +3087,8 @@ void cpu_register_map_client(QEMUBH *bh)
+     qemu_mutex_lock(&map_client_list_lock);
+     client->bh = bh;
+     QLIST_INSERT_HEAD(&map_client_list, client, link);
++    /* Write map_client_list before reading in_use.  */
++    smp_mb();
+     if (!qatomic_read(&bounce.in_use)) {
+         cpu_notify_map_clients_locked();
+     }
+@@ -3279,6 +3281,7 @@ void address_space_unmap(AddressSpace *as, void *buffer, hwaddr len,
+     qemu_vfree(bounce.buffer);
+     bounce.buffer = NULL;
+     memory_region_unref(bounce.mr);
++    /* Clear in_use before reading map_client_list.  */
+     qatomic_mb_set(&bounce.in_use, false);
+     cpu_notify_map_clients();
+ }
+-- 
+2.37.3
+

SOURCES/kvm-qapi-i386-sev-Change-the-reduced-phys-bits-value-fro.patch

@@ -0,0 +1,55 @@
+From 57ee29fbb08f7b89ee1b7c75b749392c08af3b03 Mon Sep 17 00:00:00 2001
+From: Bandan Das <bsd@redhat.com>
+Date: Thu, 3 Aug 2023 15:23:54 -0400
+Subject: [PATCH 1/5] qapi, i386/sev: Change the reduced-phys-bits value from 5
+ to 1
+
+RH-Author: Bandan Das <None>
+RH-MergeRequest: 296: Updates to SEV reduced-phys-bits parameter
+RH-Bugzilla: 2214840
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+RH-Commit: [1/4] 4137cb3b57cbb175078bc908fb2301ea2b97fd17
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2214840
+
+commit 798a818f50a9bfc01e8b5943090de458863b897b
+Author: Tom Lendacky <thomas.lendacky@amd.com>
+Date:   Fri Sep 30 10:14:27 2022 -0500
+
+    qapi, i386/sev: Change the reduced-phys-bits value from 5 to 1
+
+    A guest only ever experiences, at most, 1 bit of reduced physical
+    addressing. Change the query-sev-capabilities json comment to use 1.
+
+    Fixes: 31dd67f684 ("sev/i386: qmp: add query-sev-capabilities command")
+    Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
+    Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+    Message-Id: <cb96d8e09154533af4b4e6988469bc0b32390b65.1664550870.git.thomas.lendacky@amd.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+RHEL Notes:
+     Conflicts: Context differences, since commit 811b4ec7f8eb<qapi, target/i386/sev: Add cpu0-id to query-sev-capabilities>
+     is missing
+
+Signed-off-by: Bandan Das <bsd@redhat.com>
+---
+ qapi/misc-target.json | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/qapi/misc-target.json b/qapi/misc-target.json
+index 4bc45d2474..ede9052440 100644
+--- a/qapi/misc-target.json
++++ b/qapi/misc-target.json
+@@ -205,7 +205,7 @@
+ #
+ # -> { "execute": "query-sev-capabilities" }
+ # <- { "return": { "pdh": "8CCDD8DDD", "cert-chain": "888CCCDDDEE",
+-#                  "cbitpos": 47, "reduced-phys-bits": 5}}
++#                  "cbitpos": 47, "reduced-phys-bits": 1}}
+ #
+ ##
+ { 'command': 'query-sev-capabilities', 'returns': 'SevCapability',
+-- 
+2.37.3
+

SOURCES/kvm-qatomic-add-smp_mb__before-after_rmw.patch

@@ -0,0 +1,177 @@
+From e7d0e29d1962092af58d0445439671a6e1d91f71 Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Thu, 9 Mar 2023 08:10:33 -0500
+Subject: [PATCH 02/13] qatomic: add smp_mb__before/after_rmw()
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw()
+RH-Bugzilla: 2168472
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Eric Auger <eric.auger@redhat.com>
+RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Commit: [2/10] 1f87eb3157abcf23f020881cedce42f76497f348
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472
+
+commit ff00bed1897c3d27adc5b0cec6f6eeb5a7d13176
+Author: Paolo Bonzini <pbonzini@redhat.com>
+Date:   Thu Mar 2 11:10:56 2023 +0100
+
+    qatomic: add smp_mb__before/after_rmw()
+
+    On ARM, seqcst loads and stores (which QEMU does not use) are compiled
+    respectively as LDAR and STLR instructions.  Even though LDAR is
+    also used for load-acquire operations, it also waits for all STLRs to
+    leave the store buffer.  Thus, LDAR and STLR alone are load-acquire
+    and store-release operations, but LDAR also provides store-against-load
+    ordering as long as the previous store is a STLR.
+
+    Compare this to ARMv7, where store-release is DMB+STR and load-acquire
+    is LDR+DMB, but an additional DMB is needed between store-seqcst and
+    load-seqcst (e.g. DMB+STR+DMB+LDR+DMB); or with x86, where MOV provides
+    load-acquire and store-release semantics and the two can be reordered.
+
+    Likewise, on ARM sequentially consistent read-modify-write operations only
+    need to use LDAXR and STLXR respectively for the load and the store, while
+    on x86 they need to use the stronger LOCK prefix.
+
+    In a strange twist of events, however, the _stronger_ semantics
+    of the ARM instructions can end up causing bugs on ARM, not on x86.
+    The problems occur when seqcst atomics are mixed with relaxed atomics.
+
+    QEMU's atomics try to bridge the Linux API (that most of the developers
+    are familiar with) and the C11 API, and the two have a substantial
+    difference:
+
+    - in Linux, strongly-ordered atomics such as atomic_add_return() affect
+      the global ordering of _all_ memory operations, including for example
+      READ_ONCE()/WRITE_ONCE()
+
+    - in C11, sequentially consistent atomics (except for seq-cst fences)
+      only affect the ordering of sequentially consistent operations.
+      In particular, since relaxed loads are done with LDR on ARM, they are
+      not ordered against seqcst stores (which are done with STLR).
+
+    QEMU implements high-level synchronization primitives with the idea that
+    the primitives contain the necessary memory barriers, and the callers can
+    use relaxed atomics (qatomic_read/qatomic_set) or even regular accesses.
+    This is very much incompatible with the C11 view that seqcst accesses
+    are only ordered against other seqcst accesses, and requires using seqcst
+    fences as in the following example:
+
+       qatomic_set(&y, 1);            qatomic_set(&x, 1);
+       smp_mb();                      smp_mb();
+       ... qatomic_read(&x) ...       ... qatomic_read(&y) ...
+
+    When a qatomic_*() read-modify write operation is used instead of one
+    or both stores, developers that are more familiar with the Linux API may
+    be tempted to omit the smp_mb(), which will work on x86 but not on ARM.
+
+    This nasty difference between Linux and C11 read-modify-write operations
+    has already caused issues in util/async.c and more are being found.
+    Provide something similar to Linux smp_mb__before/after_atomic(); this
+    has the double function of documenting clearly why there is a memory
+    barrier, and avoiding a double barrier on x86 and s390x systems.
+
+    The new macro can already be put to use in qatomic_mb_set().
+
+    Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+    Reviewed-by: David Hildenbrand <david@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ docs/devel/atomics.rst | 26 +++++++++++++++++++++-----
+ include/qemu/atomic.h  | 17 ++++++++++++++++-
+ 2 files changed, 37 insertions(+), 6 deletions(-)
+
+diff --git a/docs/devel/atomics.rst b/docs/devel/atomics.rst
+index 52baa0736d..10fbfc58bb 100644
+--- a/docs/devel/atomics.rst
++++ b/docs/devel/atomics.rst
+@@ -25,7 +25,8 @@ provides macros that fall in three camps:
+ 
+ - weak atomic access and manual memory barriers: ``qatomic_read()``,
+   ``qatomic_set()``, ``smp_rmb()``, ``smp_wmb()``, ``smp_mb()``,
+-  ``smp_mb_acquire()``, ``smp_mb_release()``, ``smp_read_barrier_depends()``;
++  ``smp_mb_acquire()``, ``smp_mb_release()``, ``smp_read_barrier_depends()``,
++  ``smp_mb__before_rmw()``, ``smp_mb__after_rmw()``;
+ 
+ - sequentially consistent atomic access: everything else.
+ 
+@@ -470,7 +471,7 @@ and memory barriers, and the equivalents in QEMU:
+   sequential consistency.
+ 
+ - in QEMU, ``qatomic_read()`` and ``qatomic_set()`` do not participate in
+-  the total ordering enforced by sequentially-consistent operations.
++  the ordering enforced by read-modify-write operations.
+   This is because QEMU uses the C11 memory model.  The following example
+   is correct in Linux but not in QEMU:
+ 
+@@ -486,9 +487,24 @@ and memory barriers, and the equivalents in QEMU:
+   because the read of ``y`` can be moved (by either the processor or the
+   compiler) before the write of ``x``.
+ 
+-  Fixing this requires an ``smp_mb()`` memory barrier between the write
+-  of ``x`` and the read of ``y``.  In the common case where only one thread
+-  writes ``x``, it is also possible to write it like this:
++  Fixing this requires a full memory barrier between the write of ``x`` and
++  the read of ``y``.  QEMU provides ``smp_mb__before_rmw()`` and
++  ``smp_mb__after_rmw()``; they act both as an optimization,
++  avoiding the memory barrier on processors where it is unnecessary,
++  and as a clarification of this corner case of the C11 memory model:
++
++      +--------------------------------+
++      | QEMU (correct)                 |
++      +================================+
++      | ::                             |
++      |                                |
++      |   a = qatomic_fetch_add(&x, 2);|
++      |   smp_mb__after_rmw();         |
++      |   b = qatomic_read(&y);        |
++      +--------------------------------+
++
++  In the common case where only one thread writes ``x``, it is also possible
++  to write it like this:
+ 
+       +--------------------------------+
+       | QEMU (correct)                 |
+diff --git a/include/qemu/atomic.h b/include/qemu/atomic.h
+index 112a29910b..7855443cab 100644
+--- a/include/qemu/atomic.h
++++ b/include/qemu/atomic.h
+@@ -243,6 +243,20 @@
+ #define smp_wmb()   smp_mb_release()
+ #define smp_rmb()   smp_mb_acquire()
+ 
++/*
++ * SEQ_CST is weaker than the older __sync_* builtins and Linux
++ * kernel read-modify-write atomics.  Provide a macro to obtain
++ * the same semantics.
++ */
++#if !defined(QEMU_SANITIZE_THREAD) && \
++    (defined(__i386__) || defined(__x86_64__) || defined(__s390x__))
++# define smp_mb__before_rmw() signal_barrier()
++# define smp_mb__after_rmw() signal_barrier()
++#else
++# define smp_mb__before_rmw() smp_mb()
++# define smp_mb__after_rmw() smp_mb()
++#endif
++
+ /* qatomic_mb_read/set semantics map Java volatile variables. They are
+  * less expensive on some platforms (notably POWER) than fully
+  * sequentially consistent operations.
+@@ -257,7 +271,8 @@
+ #if !defined(__SANITIZE_THREAD__) && \
+     (defined(__i386__) || defined(__x86_64__) || defined(__s390x__))
+ /* This is more efficient than a store plus a fence.  */
+-# define qatomic_mb_set(ptr, i)  ((void)qatomic_xchg(ptr, i))
++# define qatomic_mb_set(ptr, i) \
++    ({ (void)qatomic_xchg(ptr, i); smp_mb__after_rmw(); })
+ #else
+ # define qatomic_mb_set(ptr, i) \
+    ({ qatomic_store_release(ptr, i); smp_mb(); })
+-- 
+2.37.3
+

SOURCES/kvm-qcow2-Fix-theoretical-corruption-in-store_bitmap-err.patch

@@ -0,0 +1,67 @@
+From 06c73c4b57dd1f47f819d719a63eb39fbe799304 Mon Sep 17 00:00:00 2001
+From: Kevin Wolf <kwolf@redhat.com>
+Date: Thu, 12 Jan 2023 20:14:51 +0100
+Subject: [PATCH 1/4] qcow2: Fix theoretical corruption in store_bitmap() error
+ path
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Kevin Wolf <kwolf@redhat.com>
+RH-MergeRequest: 251: qemu-img: Fix exit code for errors closing the image
+RH-Bugzilla: 2147617
+RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Commit: [1/4] d0a26bed7b16db41e7baee1f8f2b3ae54e52dd52
+
+In order to write the bitmap table to the image file, it is converted to
+big endian. If the write fails, it is passed to clear_bitmap_table() to
+free all of the clusters it had allocated before. However, if we don't
+convert it back to native endianness first, we'll free things at a wrong
+offset.
+
+In practical terms, the offsets will be so high that we won't actually
+free any allocated clusters, but just run into an error, but in theory
+this can cause image corruption.
+
+Cc: qemu-stable@nongnu.org
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+Message-Id: <20230112191454.169353-2-kwolf@redhat.com>
+Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit b03dd9613bcf8fe948581b2b3585510cb525c382)
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+---
+ block/qcow2-bitmap.c | 5 +++--
+ 1 file changed, 3 insertions(+), 2 deletions(-)
+
+diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c
+index 8fb4731551..869069415c 100644
+--- a/block/qcow2-bitmap.c
++++ b/block/qcow2-bitmap.c
+@@ -115,7 +115,7 @@ static int update_header_sync(BlockDriverState *bs)
+     return bdrv_flush(bs->file->bs);
+ }
+ 
+-static inline void bitmap_table_to_be(uint64_t *bitmap_table, size_t size)
++static inline void bitmap_table_bswap_be(uint64_t *bitmap_table, size_t size)
+ {
+     size_t i;
+ 
+@@ -1401,9 +1401,10 @@ static int store_bitmap(BlockDriverState *bs, Qcow2Bitmap *bm, Error **errp)
+         goto fail;
+     }
+ 
+-    bitmap_table_to_be(tb, tb_size);
++    bitmap_table_bswap_be(tb, tb_size);
+     ret = bdrv_pwrite(bs->file, tb_offset, tb, tb_size * sizeof(tb[0]));
+     if (ret < 0) {
++        bitmap_table_bswap_be(tb, tb_size);
+         error_setg_errno(errp, -ret, "Failed to write bitmap '%s' to file",
+                          bm_name);
+         goto fail;
+-- 
+2.37.3
+

SOURCES/kvm-qemu-coroutine-lock-add-smp_mb__after_rmw.patch

@@ -0,0 +1,75 @@
+From 2f03293910f3ac559f37d45c95325ae29638003a Mon Sep 17 00:00:00 2001
+From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+Date: Thu, 9 Mar 2023 08:15:14 -0500
+Subject: [PATCH 07/13] qemu-coroutine-lock: add smp_mb__after_rmw()
+
+RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-MergeRequest: 263: qatomic: add smp_mb__before/after_rmw()
+RH-Bugzilla: 2168472
+RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
+RH-Acked-by: Eric Auger <eric.auger@redhat.com>
+RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+RH-Acked-by: David Hildenbrand <david@redhat.com>
+RH-Commit: [7/10] 9cf1b6d3b0dd154489e75ad54a3000ea58983960
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2168472
+
+commit e3a3b6ec8169eab2feb241b4982585001512cd55
+Author: Paolo Bonzini <pbonzini@redhat.com>
+Date:   Fri Mar 3 10:52:59 2023 +0100
+
+    qemu-coroutine-lock: add smp_mb__after_rmw()
+
+    mutex->from_push and mutex->handoff in qemu-coroutine-lock implement
+    the familiar pattern:
+
+       write a                                  write b
+       smp_mb()                                 smp_mb()
+       read b                                   read a
+
+    The memory barrier is required by the C memory model even after a
+    SEQ_CST read-modify-write operation such as QSLIST_INSERT_HEAD_ATOMIC.
+    Add it and avoid the unclear qatomic_mb_read() operation.
+
+    Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
+    Reviewed-by: David Hildenbrand <david@redhat.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+---
+ util/qemu-coroutine-lock.c | 9 ++++++++-
+ 1 file changed, 8 insertions(+), 1 deletion(-)
+
+diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c
+index 2669403839..a03ed0e664 100644
+--- a/util/qemu-coroutine-lock.c
++++ b/util/qemu-coroutine-lock.c
+@@ -206,10 +206,16 @@ static void coroutine_fn qemu_co_mutex_lock_slowpath(AioContext *ctx,
+     trace_qemu_co_mutex_lock_entry(mutex, self);
+     push_waiter(mutex, &w);
+ 
++    /*
++     * Add waiter before reading mutex->handoff.  Pairs with qatomic_mb_set
++     * in qemu_co_mutex_unlock.
++     */
++    smp_mb__after_rmw();
++
+     /* This is the "Responsibility Hand-Off" protocol; a lock() picks from
+      * a concurrent unlock() the responsibility of waking somebody up.
+      */
+-    old_handoff = qatomic_mb_read(&mutex->handoff);
++    old_handoff = qatomic_read(&mutex->handoff);
+     if (old_handoff &&
+         has_waiters(mutex) &&
+         qatomic_cmpxchg(&mutex->handoff, old_handoff, 0) == old_handoff) {
+@@ -308,6 +314,7 @@ void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex)
+         }
+ 
+         our_handoff = mutex->sequence;
++        /* Set handoff before checking for waiters.  */
+         qatomic_mb_set(&mutex->handoff, our_handoff);
+         if (!has_waiters(mutex)) {
+             /* The concurrent lock has not added itself yet, so it
+-- 
+2.37.3
+

SOURCES/kvm-qemu-img-bitmap-Report-errors-while-closing-the-imag.patch

@@ -0,0 +1,70 @@
+From 648193b48d8aeaded90fd657e3610d8040f505fc Mon Sep 17 00:00:00 2001
+From: Kevin Wolf <kwolf@redhat.com>
+Date: Thu, 12 Jan 2023 20:14:53 +0100
+Subject: [PATCH 3/4] qemu-img bitmap: Report errors while closing the image
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+RH-Author: Kevin Wolf <kwolf@redhat.com>
+RH-MergeRequest: 251: qemu-img: Fix exit code for errors closing the image
+RH-Bugzilla: 2147617
+RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Commit: [3/4] 8e13e09564718a0badd03af84f036246a46a0eba
+
+blk_unref() can't report any errors that happen while closing the image.
+For example, if qcow2 hits an -ENOSPC error while writing out dirty
+bitmaps when it's closed, it prints error messages to stderr, but
+'qemu-img bitmap' won't see any error return value and will therefore
+look successful with exit code 0.
+
+In order to fix this, manually inactivate the image first before calling
+blk_unref(). This already performs the operations that would be most
+likely to fail while closing the image, but it can still return errors.
+
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1330
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+Message-Id: <20230112191454.169353-4-kwolf@redhat.com>
+Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
+Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit c5e477110dcb8ef4642dce399777c3dee68fa96c)
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+---
+ qemu-img.c | 11 +++++++++++
+ 1 file changed, 11 insertions(+)
+
+diff --git a/qemu-img.c b/qemu-img.c
+index 18833f7d69..7d035c0c7f 100644
+--- a/qemu-img.c
++++ b/qemu-img.c
+@@ -4622,6 +4622,7 @@ static int img_bitmap(int argc, char **argv)
+     QSIMPLEQ_HEAD(, ImgBitmapAction) actions;
+     ImgBitmapAction *act, *act_next;
+     const char *op;
++    int inactivate_ret;
+ 
+     QSIMPLEQ_INIT(&actions);
+ 
+@@ -4806,6 +4807,16 @@ static int img_bitmap(int argc, char **argv)
+     ret = 0;
+ 
+  out:
++    /*
++     * Manually inactivate the images first because this way we can know whether
++     * an error occurred. blk_unref() doesn't tell us about failures.
++     */
++    inactivate_ret = bdrv_inactivate_all();
++    if (inactivate_ret < 0) {
++        error_report("Error while closing the image: %s", strerror(-inactivate_ret));
++        ret = 1;
++    }
++
+     blk_unref(src);
+     blk_unref(blk);
+     qemu_opts_del(opts);
+-- 
+2.37.3
+

SOURCES/kvm-qemu-img-commit-Report-errors-while-closing-the-imag.patch

@@ -0,0 +1,67 @@
+From 2396df7fe527567e8e78761ef24ea1057ef6fa48 Mon Sep 17 00:00:00 2001
+From: Kevin Wolf <kwolf@redhat.com>
+Date: Thu, 12 Jan 2023 20:14:52 +0100
+Subject: [PATCH 2/4] qemu-img commit: Report errors while closing the image
+
+RH-Author: Kevin Wolf <kwolf@redhat.com>
+RH-MergeRequest: 251: qemu-img: Fix exit code for errors closing the image
+RH-Bugzilla: 2147617
+RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Commit: [2/4] 28f95bf76d1d63e2b0bed0c2ba5206bd3e5ea4f8
+
+blk_unref() can't report any errors that happen while closing the image.
+For example, if qcow2 hits an -ENOSPC error while writing out dirty
+bitmaps when it's closed, it prints error messages to stderr, but
+'qemu-img commit' won't see any error return value and will therefore
+look successful with exit code 0.
+
+In order to fix this, manually inactivate the image first before calling
+blk_unref(). This already performs the operations that would be most
+likely to fail while closing the image, but it can still return errors.
+
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+Message-Id: <20230112191454.169353-3-kwolf@redhat.com>
+Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit 44efba2d713aca076c411594d0c1a2b99155eeb3)
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+---
+ qemu-img.c | 13 +++++++++++++
+ 1 file changed, 13 insertions(+)
+
+diff --git a/qemu-img.c b/qemu-img.c
+index f036a1d428..18833f7d69 100644
+--- a/qemu-img.c
++++ b/qemu-img.c
+@@ -443,6 +443,11 @@ static BlockBackend *img_open(bool image_opts,
+         blk = img_open_file(filename, NULL, fmt, flags, writethrough, quiet,
+                             force_share);
+     }
++
++    if (blk) {
++        blk_set_force_allow_inactivate(blk);
++    }
++
+     return blk;
+ }
+ 
+@@ -1110,6 +1115,14 @@ unref_backing:
+ done:
+     qemu_progress_end();
+ 
++    /*
++     * Manually inactivate the image first because this way we can know whether
++     * an error occurred. blk_unref() doesn't tell us about failures.
++     */
++    ret = bdrv_inactivate_all();
++    if (ret < 0 && !local_err) {
++        error_setg_errno(&local_err, -ret, "Error while closing the image");
++    }
+     blk_unref(blk);
+ 
+     if (local_err) {
+-- 
+2.37.3
+

SOURCES/kvm-qemu-iotests-Test-qemu-img-bitmap-commit-exit-code-o.patch

@@ -0,0 +1,166 @@
+From 7c6faae20638f58681df223e0ca44e0a6cb60d2d Mon Sep 17 00:00:00 2001
+From: Kevin Wolf <kwolf@redhat.com>
+Date: Thu, 12 Jan 2023 20:14:54 +0100
+Subject: [PATCH 4/4] qemu-iotests: Test qemu-img bitmap/commit exit code on
+ error
+
+RH-Author: Kevin Wolf <kwolf@redhat.com>
+RH-MergeRequest: 251: qemu-img: Fix exit code for errors closing the image
+RH-Bugzilla: 2147617
+RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
+RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
+RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
+RH-Commit: [4/4] fb2f9de98ddd2ee1d745119e4f15272ef44e0aae
+
+This tests that when an error happens while writing back bitmaps to the
+image file in qcow2_inactivate(), 'qemu-img bitmap/commit' actually
+return an error value in their exit code instead of making the operation
+look successful to scripts.
+
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+Message-Id: <20230112191454.169353-5-kwolf@redhat.com>
+Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+(cherry picked from commit 07a4e1f8e5418f36424cd57d5d061b090a238c65)
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+---
+ .../qemu-iotests/tests/qemu-img-close-errors  | 96 +++++++++++++++++++
+ .../tests/qemu-img-close-errors.out           | 23 +++++
+ 2 files changed, 119 insertions(+)
+ create mode 100755 tests/qemu-iotests/tests/qemu-img-close-errors
+ create mode 100644 tests/qemu-iotests/tests/qemu-img-close-errors.out
+
+diff --git a/tests/qemu-iotests/tests/qemu-img-close-errors b/tests/qemu-iotests/tests/qemu-img-close-errors
+new file mode 100755
+index 0000000000..50bfb6cfa2
+--- /dev/null
++++ b/tests/qemu-iotests/tests/qemu-img-close-errors
+@@ -0,0 +1,96 @@
++#!/usr/bin/env bash
++# group: rw auto quick
++#
++# Check that errors while closing the image, in particular writing back dirty
++# bitmaps, is correctly reported with a failing qemu-img exit code.
++#
++# Copyright (C) 2023 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=kwolf@redhat.com
++
++seq="$(basename $0)"
++echo "QA output created by $seq"
++
++status=1	# failure is the default!
++
++_cleanup()
++{
++    _cleanup_test_img
++}
++trap "_cleanup; exit \$status" 0 1 2 3 15
++
++# get standard environment, filters and checks
++cd ..
++. ./common.rc
++. ./common.filter
++
++_supported_fmt qcow2
++_supported_proto file
++_supported_os Linux
++
++size=1G
++
++# The error we are going to use is ENOSPC. Depending on how many bitmaps we
++# create in the backing file (and therefore increase the used up space), we get
++# failures in different places. With a low number, only merging the bitmap
++# fails, whereas with a higher number, already 'qemu-img commit' fails.
++for max_bitmap in 6 7; do
++    echo
++    echo "=== Test with $max_bitmap bitmaps ==="
++
++    TEST_IMG="$TEST_IMG.base" _make_test_img -q $size
++    for i in $(seq 1 $max_bitmap); do
++        $QEMU_IMG bitmap --add "$TEST_IMG.base" "stale-bitmap-$i"
++    done
++
++    # Simulate a block device of 128 MB by resizing the image file accordingly
++    # and then enforcing the size with the raw driver
++    $QEMU_IO -f raw -c "truncate 128M" "$TEST_IMG.base"
++    BASE_JSON='json:{
++        "driver": "qcow2",
++        "file": {
++            "driver": "raw",
++            "size": 134217728,
++            "file": {
++                "driver": "file",
++                "filename":"'"$TEST_IMG.base"'"
++            }
++        }
++    }'
++
++    _make_test_img -q -b "$BASE_JSON" -F $IMGFMT
++    $QEMU_IMG bitmap --add "$TEST_IMG" "good-bitmap"
++
++    $QEMU_IO -c 'write 0 126m' "$TEST_IMG" | _filter_qemu_io
++
++    $QEMU_IMG commit -d "$TEST_IMG" 2>&1 | _filter_generated_node_ids
++    echo "qemu-img commit exit code: ${PIPESTATUS[0]}"
++
++    $QEMU_IMG bitmap --add "$BASE_JSON" "good-bitmap"
++    echo "qemu-img bitmap --add exit code: $?"
++
++    $QEMU_IMG bitmap --merge "good-bitmap" -b "$TEST_IMG" "$BASE_JSON" \
++        "good-bitmap" 2>&1 | _filter_generated_node_ids
++    echo "qemu-img bitmap --merge exit code:  ${PIPESTATUS[0]}"
++done
++
++# success, all done
++echo "*** done"
++rm -f $seq.full
++status=0
++
+diff --git a/tests/qemu-iotests/tests/qemu-img-close-errors.out b/tests/qemu-iotests/tests/qemu-img-close-errors.out
+new file mode 100644
+index 0000000000..1bfe88f176
+--- /dev/null
++++ b/tests/qemu-iotests/tests/qemu-img-close-errors.out
+@@ -0,0 +1,23 @@
++QA output created by qemu-img-close-errors
++
++=== Test with 6 bitmaps ===
++wrote 132120576/132120576 bytes at offset 0
++126 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++Image committed.
++qemu-img commit exit code: 0
++qemu-img bitmap --add exit code: 0
++qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'good-bitmap' to file: No space left on device
++qemu-img: Error while closing the image: Invalid argument
++qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'good-bitmap' to file: No space left on device
++qemu-img bitmap --merge exit code:  1
++
++=== Test with 7 bitmaps ===
++wrote 132120576/132120576 bytes at offset 0
++126 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
++qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'stale-bitmap-7' to file: No space left on device
++qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'stale-bitmap-7' to file: No space left on device
++qemu-img: Error while closing the image: Invalid argument
++qemu-img commit exit code: 1
++qemu-img bitmap --add exit code: 0
++qemu-img bitmap --merge exit code:  0
++*** done
+-- 
+2.37.3
+

SOURCES/kvm-qemu-options.hx-Update-the-reduced-phys-bits-documen.patch

@@ -0,0 +1,61 @@
+From 095811c08557b0a2ad1a433d28699ead1e5ef664 Mon Sep 17 00:00:00 2001
+From: Bandan Das <bsd@redhat.com>
+Date: Thu, 3 Aug 2023 15:12:15 -0400
+Subject: [PATCH 2/5] qemu-options.hx: Update the reduced-phys-bits
+ documentation
+
+RH-Author: Bandan Das <None>
+RH-MergeRequest: 296: Updates to SEV reduced-phys-bits parameter
+RH-Bugzilla: 2214840
+RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
+RH-Commit: [2/4] f8e8f5aeff449a34ce90c6e55e2a51873a6e6a87
+
+Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2214840
+
+commit 326e3015c4c6f3197157ea0bb00826ae740e2fad
+Author: Tom Lendacky <thomas.lendacky@amd.com>
+Date:   Fri Sep 30 10:14:28 2022 -0500
+
+    qemu-options.hx: Update the reduced-phys-bits documentation
+
+    A guest only ever experiences, at most, 1 bit of reduced physical
+    addressing. Update the documentation to reflect this as well as change
+    the example value on the reduced-phys-bits option.
+
+    Fixes: a9b4942f48 ("target/i386: add Secure Encrypted Virtualization (SEV) object")
+    Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
+    Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
+    Message-Id: <13a62ced1808546c1d398e2025cf85f4c94ae123.1664550870.git.thomas.lendacky@amd.com>
+    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+
+Signed-off-by: Bandan Das <bsd@redhat.com>
+---
+ qemu-options.hx | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/qemu-options.hx b/qemu-options.hx
+index 4b7798088b..981248e283 100644
+--- a/qemu-options.hx
++++ b/qemu-options.hx
+@@ -5204,7 +5204,7 @@ SRST
+         physical address space. The ``reduced-phys-bits`` is used to
+         provide the number of bits we loose in physical address space.
+         Similar to C-bit, the value is Host family dependent. On EPYC,
+-        the value should be 5.
++        a guest will lose a maximum of 1 bit, so the value should be 1.
+ 
+         The ``sev-device`` provides the device file to use for
+         communicating with the SEV firmware running inside AMD Secure
+@@ -5239,7 +5239,7 @@ SRST
+ 
+              # |qemu_system_x86| \\
+                  ...... \\
+-                 -object sev-guest,id=sev0,cbitpos=47,reduced-phys-bits=5 \\
++                 -object sev-guest,id=sev0,cbitpos=47,reduced-phys-bits=1 \\
+                  -machine ...,memory-encryption=sev0 \\
+                  .....
+ 
+-- 
+2.37.3
+