From 798d76c68ace9b778e4026def208e8d2972f33a0 Mon Sep 17 00:00:00 2001 From: eabdullin Date: Thu, 13 Jun 2024 13:02:00 +0300 Subject: [PATCH] - kvm: error out of kvm_irqchip_add_msi_route() in case of full route table - virtio-pci: fix use of a released vector --- ...of-kvm_irqchip_add_msi_route-in-case.patch | 66 ++++++++ ...tio-pci-fix-use-of-a-released-vector.patch | 150 ++++++++++++++++++ SPECS/qemu-kvm.spec | 13 +- 3 files changed, 228 insertions(+), 1 deletion(-) create mode 100644 SOURCES/kvm-error-out-of-kvm_irqchip_add_msi_route-in-case.patch create mode 100644 SOURCES/virtio-pci-fix-use-of-a-released-vector.patch diff --git a/SOURCES/kvm-error-out-of-kvm_irqchip_add_msi_route-in-case.patch b/SOURCES/kvm-error-out-of-kvm_irqchip_add_msi_route-in-case.patch new file mode 100644 index 0000000..9f72b99 --- /dev/null +++ b/SOURCES/kvm-error-out-of-kvm_irqchip_add_msi_route-in-case.patch @@ -0,0 +1,66 @@ +From e34f4d87e8d47b0a65cb663aaf7bef60c2112d36 Mon Sep 17 00:00:00 2001 +From: Igor Mammedov +Date: Mon, 8 Apr 2024 13:09:56 +0200 +Subject: [PATCH] kvm: error out of kvm_irqchip_add_msi_route() in case of full + route table + +subj is calling kvm_add_routing_entry() which simply extends + KVMState::irq_routes::entries[] +but doesn't check if number of routes goes beyond limit the kernel +is willing to accept. Which later leads toi the assert + + qemu-kvm: ../accel/kvm/kvm-all.c:1833: kvm_irqchip_commit_routes: Assertion `ret == 0' failed + +typically it happens during guest boot for large enough guest + +Reproduced with: + ./qemu --enable-kvm -m 8G -smp 64 -machine pc \ + `for b in {1..2}; do echo -n "-device pci-bridge,id=pci$b,chassis_nr=$b "; + for i in {0..31}; do touch /tmp/vblk$b$i; + echo -n "-drive file=/tmp/vblk$b$i,if=none,id=drive$b$i,format=raw + -device virtio-blk-pci,drive=drive$b$i,bus=pci$b "; + done; done` + +While crash at boot time is bad, the same might happen at hotplug time +which is unacceptable. +So instead calling kvm_add_routing_entry() unconditionally, check first +that number of routes won't exceed KVM_CAP_IRQ_ROUTING. This way virtio +device insteads killin qemu, will gracefully fail to initialize device +as expected with following warnings on console: + virtio-blk failed to set guest notifier (-28), ensure -accel kvm is set. + virtio_bus_start_ioeventfd: failed. Fallback to userspace (slower). + +Signed-off-by: Igor Mammedov +Message-ID: <20240408110956.451558-1-imammedo@redhat.com> +Signed-off-by: Paolo Bonzini +--- + accel/kvm/kvm-all.c | 15 ++++++++++----- + 1 file changed, 10 insertions(+), 5 deletions(-) + +diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c +index a8cecd040ebc..931f74256e8a 100644 +--- a/accel/kvm/kvm-all.c ++++ b/accel/kvm/kvm-all.c +@@ -1999,12 +1999,17 @@ int kvm_irqchip_add_msi_route(KVMRouteChange *c, int vector, PCIDevice *dev) + return -EINVAL; + } + +- trace_kvm_irqchip_add_msi_route(dev ? dev->name : (char *)"N/A", +- vector, virq); ++ if (s->irq_routes->nr < s->gsi_count) { ++ trace_kvm_irqchip_add_msi_route(dev ? dev->name : (char *)"N/A", ++ vector, virq); + +- kvm_add_routing_entry(s, &kroute); +- kvm_arch_add_msi_route_post(&kroute, vector, dev); +- c->changes++; ++ kvm_add_routing_entry(s, &kroute); ++ kvm_arch_add_msi_route_post(&kroute, vector, dev); ++ c->changes++; ++ } else { ++ kvm_irqchip_release_virq(s, virq); ++ return -ENOSPC; ++ } + + return virq; + } diff --git a/SOURCES/virtio-pci-fix-use-of-a-released-vector.patch b/SOURCES/virtio-pci-fix-use-of-a-released-vector.patch new file mode 100644 index 0000000..8507c34 --- /dev/null +++ b/SOURCES/virtio-pci-fix-use-of-a-released-vector.patch @@ -0,0 +1,150 @@ +From 2ce6cff94df2650c460f809e5ad263f1d22507c0 Mon Sep 17 00:00:00 2001 +From: Cindy Lu +Date: Fri, 12 Apr 2024 14:26:55 +0800 +Subject: [PATCH] virtio-pci: fix use of a released vector +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +During the booting process of the non-standard image, the behavior of the +called function in qemu is as follows: + +1. vhost_net_stop() was triggered by guest image. This will call the function +virtio_pci_set_guest_notifiers() with assgin= false, +virtio_pci_set_guest_notifiers(） will release the irqfd for vector 0 + +2. virtio_reset() was triggered, this will set configure vector to VIRTIO_NO_VECTOR + +3.vhost_net_start() was called (at this time, the configure vector is +still VIRTIO_NO_VECTOR) and then call virtio_pci_set_guest_notifiers() with +assgin=true, so the irqfd for vector 0 is still not "init" during this process + +4. The system continues to boot and sets the vector back to 0. After that +msix_fire_vector_notifier() was triggered to unmask the vector 0 and meet the crash + +To fix the issue, we need to support changing the vector after VIRTIO_CONFIG_S_DRIVER_OK is set. + +(gdb) bt +0 __pthread_kill_implementation (threadid=, signo=signo@entry=6, no_tid=no_tid@entry=0) + at pthread_kill.c:44 +1 0x00007fc87148ec53 in __pthread_kill_internal (signo=6, threadid=) at pthread_kill.c:78 +2 0x00007fc87143e956 in __GI_raise (sig=sig@entry=6) at ../sysdeps/posix/raise.c:26 +3 0x00007fc8714287f4 in __GI_abort () at abort.c:79 +4 0x00007fc87142871b in __assert_fail_base + (fmt=0x7fc8715bbde0 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n", assertion=0x5606413efd53 "ret == 0", file=0x5606413ef87d "../accel/kvm/kvm-all.c", line=1837, function=) at assert.c:92 +5 0x00007fc871437536 in __GI___assert_fail + (assertion=0x5606413efd53 "ret == 0", file=0x5606413ef87d "../accel/kvm/kvm-all.c", line=1837, function=0x5606413f06f0 <__PRETTY_FUNCTION__.19> "kvm_irqchip_commit_routes") at assert.c:101 +6 0x0000560640f884b5 in kvm_irqchip_commit_routes (s=0x560642cae1f0) at ../accel/kvm/kvm-all.c:1837 +7 0x0000560640c98f8e in virtio_pci_one_vector_unmask + (proxy=0x560643c65f00, queue_no=4294967295, vector=0, msg=..., n=0x560643c6e4c8) + at ../hw/virtio/virtio-pci.c:1005 +8 0x0000560640c99201 in virtio_pci_vector_unmask (dev=0x560643c65f00, vector=0, msg=...) + at ../hw/virtio/virtio-pci.c:1070 +9 0x0000560640bc402e in msix_fire_vector_notifier (dev=0x560643c65f00, vector=0, is_masked=false) + at ../hw/pci/msix.c:120 +10 0x0000560640bc40f1 in msix_handle_mask_update (dev=0x560643c65f00, vector=0, was_masked=true) + at ../hw/pci/msix.c:140 +11 0x0000560640bc4503 in msix_table_mmio_write (opaque=0x560643c65f00, addr=12, val=0, size=4) + at ../hw/pci/msix.c:231 +12 0x0000560640f26d83 in memory_region_write_accessor + (mr=0x560643c66540, addr=12, value=0x7fc86b7bc628, size=4, shift=0, mask=4294967295, attrs=...) + at ../system/memory.c:497 +13 0x0000560640f270a6 in access_with_adjusted_size + + (addr=12, value=0x7fc86b7bc628, size=4, access_size_min=1, access_size_max=4, access_fn=0x560640f26c8d , mr=0x560643c66540, attrs=...) at ../system/memory.c:573 +14 0x0000560640f2a2b5 in memory_region_dispatch_write (mr=0x560643c66540, addr=12, data=0, op=MO_32, attrs=...) + at ../system/memory.c:1521 +15 0x0000560640f37bac in flatview_write_continue + (fv=0x7fc65805e0b0, addr=4273803276, attrs=..., ptr=0x7fc871e9c028, len=4, addr1=12, l=4, mr=0x560643c66540) + at ../system/physmem.c:2714 +16 0x0000560640f37d0f in flatview_write + (fv=0x7fc65805e0b0, addr=4273803276, attrs=..., buf=0x7fc871e9c028, len=4) at ../system/physmem.c:2756 +17 0x0000560640f380bf in address_space_write + (as=0x560642161ae0 , addr=4273803276, attrs=..., buf=0x7fc871e9c028, len=4) + at ../system/physmem.c:2863 +18 0x0000560640f3812c in address_space_rw + (as=0x560642161ae0 , addr=4273803276, attrs=..., buf=0x7fc871e9c028, len=4, is_write=true) at ../system/physmem.c:2873 +--Type for more, q to quit, c to continue without paging-- +19 0x0000560640f8aa55 in kvm_cpu_exec (cpu=0x560642f205e0) at ../accel/kvm/kvm-all.c:2915 +20 0x0000560640f8d731 in kvm_vcpu_thread_fn (arg=0x560642f205e0) at ../accel/kvm/kvm-accel-ops.c:51 +21 0x00005606411949f4 in qemu_thread_start (args=0x560642f292b0) at ../util/qemu-thread-posix.c:541 +22 0x00007fc87148cdcd in start_thread (arg=) at pthread_create.c:442 +23 0x00007fc871512630 in clone3 () at ../sysdeps/unix/sysv/linux/x86_64/clone3.S:81 +(gdb) + +MST: coding style and typo fixups + +Fixes: f9a09ca3ea ("vhost: add support for configure interrupt") +Cc: qemu-stable@nongnu.org +Signed-off-by: Cindy Lu +Message-ID: <2321ade5f601367efe7380c04e3f61379c59b48f.1713173550.git.mst@redhat.com> +Cc: Lei Yang +Cc: Jason Wang +Signed-off-by: Michael S. Tsirkin +Tested-by: Cindy Lu +--- + hw/virtio/virtio-pci.c | 37 +++++++++++++++++++++++++++++++++++-- + 1 file changed, 35 insertions(+), 2 deletions(-) + +diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c +index cb6940fc0e92..cb159fd0785c 100644 +--- a/hw/virtio/virtio-pci.c ++++ b/hw/virtio/virtio-pci.c +@@ -1424,6 +1424,38 @@ static int virtio_pci_add_mem_cap(VirtIOPCIProxy *proxy, + return offset; + } + ++static void virtio_pci_set_vector(VirtIODevice *vdev, ++ VirtIOPCIProxy *proxy, ++ int queue_no, uint16_t old_vector, ++ uint16_t new_vector) ++{ ++ bool kvm_irqfd = (vdev->status & VIRTIO_CONFIG_S_DRIVER_OK) && ++ msix_enabled(&proxy->pci_dev) && kvm_msi_via_irqfd_enabled(); ++ ++ if (new_vector == old_vector) { ++ return; ++ } ++ ++ /* ++ * If the device uses irqfd and the vector changes after DRIVER_OK is ++ * set, we need to release the old vector and set up the new one. ++ * Otherwise just need to set the new vector on the device. ++ */ ++ if (kvm_irqfd && old_vector != VIRTIO_NO_VECTOR) { ++ kvm_virtio_pci_vector_release_one(proxy, queue_no); ++ } ++ /* Set the new vector on the device. */ ++ if (queue_no == VIRTIO_CONFIG_IRQ_IDX) { ++ vdev->config_vector = new_vector; ++ } else { ++ virtio_queue_set_vector(vdev, queue_no, new_vector); ++ } ++ /* If the new vector changed need to set it up. */ ++ if (kvm_irqfd && new_vector != VIRTIO_NO_VECTOR) { ++ kvm_virtio_pci_vector_use_one(proxy, queue_no); ++ } ++} ++ + int virtio_pci_add_shm_cap(VirtIOPCIProxy *proxy, + uint8_t bar, uint64_t offset, uint64_t length, + uint8_t id) +@@ -1570,7 +1602,8 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr, + } else { + val = VIRTIO_NO_VECTOR; + } +- vdev->config_vector = val; ++ virtio_pci_set_vector(vdev, proxy, VIRTIO_CONFIG_IRQ_IDX, ++ vdev->config_vector, val); + break; + case VIRTIO_PCI_COMMON_STATUS: + if (!(val & VIRTIO_CONFIG_S_DRIVER_OK)) { +@@ -1610,7 +1643,7 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr, + } else { + val = VIRTIO_NO_VECTOR; + } +- virtio_queue_set_vector(vdev, vdev->queue_sel, val); ++ virtio_pci_set_vector(vdev, proxy, vdev->queue_sel, vector, val); + break; + case VIRTIO_PCI_COMMON_Q_ENABLE: + if (val == 1) { diff --git a/SPECS/qemu-kvm.spec b/SPECS/qemu-kvm.spec index 973e9a2..a0cf412 100644 --- a/SPECS/qemu-kvm.spec +++ b/SPECS/qemu-kvm.spec @@ -149,7 +149,7 @@ Obsoletes: %{name}-block-ssh <= %{epoch}:%{version} \ Summary: QEMU is a machine emulator and virtualizer Name: qemu-kvm Version: 8.2.0 -Release: 11%{?rcrel}%{?dist}%{?cc_suffix} +Release: 11%{?rcrel}%{?dist}%{?cc_suffix}.2.alma.1 # Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped # Epoch 15 used for RHEL 8 # Epoch 17 used for RHEL 9 (due to release versioning offset in RHEL 8.5) @@ -611,6 +611,12 @@ Patch176: kvm-coroutine-cap-per-thread-local-pool-size.patch # For RHEL-28947 - Qemu crashing with "failed to set up stack guard page: Cannot allocate memory" Patch177: kvm-coroutine-reserve-5-000-mappings.patch +# Patches were taken from: +# https://github.com/qemu/qemu/commit/e34f4d87e8d47b0a65cb663aaf7bef60c2112d36 +Patch178: kvm-error-out-of-kvm_irqchip_add_msi_route-in-case.patch +# https://github.com/qemu/qemu/commit/2ce6cff94df2650c460f809e5ad263f1d22507c0 +Patch179: virtio-pci-fix-use-of-a-released-vector.patch + %if %{have_clang} BuildRequires: clang %if %{have_safe_stack} @@ -1671,6 +1677,11 @@ useradd -r -u 107 -g qemu -G kvm -d / -s /sbin/nologin \ %endif %changelog +* Thu Jun 13 2024 Eduard Abdullin - 8.2.0-11.2.alma.1 +- kvm: error out of kvm_irqchip_add_msi_route() in case of full + route table +- virtio-pci: fix use of a released vector + * Tue Mar 26 2024 Miroslav Rezanina - 8.2.0-11 - kvm-coroutine-cap-per-thread-local-pool-size.patch [RHEL-28947] - kvm-coroutine-reserve-5-000-mappings.patch [RHEL-28947]