From a6f5770fb2b22cb219a684469c8224ebec74ca2e Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Sat, 26 Mar 2022 14:02:22 +0800 Subject: [PATCH 01/11] vfio: simplify the conditional statements in vfio_msi_enable It's unnecessary to test against the specific return value of VFIO_DEVICE_SET_IRQS, since any positive return is an error indicating the number of vectors we should retry with. Signed-off-by: Longpeng(Mike) Link: https://lore.kernel.org/r/20220326060226.1892-2-longpeng2@huawei.com Signed-off-by: Alex Williamson --- hw/vfio/pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 9fd9faee1d..cab1a6ef57 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -653,7 +653,7 @@ retry: if (ret) { if (ret < 0) { error_report("vfio: Error: Failed to setup MSI fds: %m"); - } else if (ret != vdev->nr_vectors) { + } else { error_report("vfio: Error: Failed to enable %d " "MSI vectors, retry with %d", vdev->nr_vectors, ret); } @@ -671,7 +671,7 @@ retry: g_free(vdev->msi_vectors); vdev->msi_vectors = NULL; - if (ret > 0 && ret != vdev->nr_vectors) { + if (ret > 0) { vdev->nr_vectors = ret; goto retry; } From be4a46eccfe97069fd62f967f6660407c9aa2a03 Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Sat, 26 Mar 2022 14:02:23 +0800 Subject: [PATCH 02/11] vfio: move re-enabling INTX out of the common helper Move re-enabling INTX out, and the callers should decide to re-enable it or not. Signed-off-by: Longpeng(Mike) Link: https://lore.kernel.org/r/20220326060226.1892-3-longpeng2@huawei.com Signed-off-by: Alex Williamson --- hw/vfio/pci.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index cab1a6ef57..b3c27c22aa 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -693,7 +693,6 @@ retry: static void vfio_msi_disable_common(VFIOPCIDevice *vdev) { - Error *err = NULL; int i; for (i = 0; i < vdev->nr_vectors; i++) { @@ -712,15 +711,11 @@ static void vfio_msi_disable_common(VFIOPCIDevice *vdev) vdev->msi_vectors = NULL; vdev->nr_vectors = 0; vdev->interrupt = VFIO_INT_NONE; - - vfio_intx_enable(vdev, &err); - if (err) { - error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name); - } } static void vfio_msix_disable(VFIOPCIDevice *vdev) { + Error *err = NULL; int i; msix_unset_vector_notifiers(&vdev->pdev); @@ -741,6 +736,10 @@ static void vfio_msix_disable(VFIOPCIDevice *vdev) } vfio_msi_disable_common(vdev); + vfio_intx_enable(vdev, &err); + if (err) { + error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name); + } memset(vdev->msix->pending, 0, BITS_TO_LONGS(vdev->msix->entries) * sizeof(unsigned long)); @@ -750,8 +749,14 @@ static void vfio_msix_disable(VFIOPCIDevice *vdev) static void vfio_msi_disable(VFIOPCIDevice *vdev) { + Error *err = NULL; + vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSI_IRQ_INDEX); vfio_msi_disable_common(vdev); + vfio_intx_enable(vdev, &err); + if (err) { + error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name); + } trace_vfio_msi_disable(vdev->vbasedev.name); } From 8ab217d5d34275ee471a3b085ec90728b8f06d80 Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Sat, 26 Mar 2022 14:02:24 +0800 Subject: [PATCH 03/11] vfio: simplify the failure path in vfio_msi_enable Use vfio_msi_disable_common to simplify the error handling in vfio_msi_enable. Signed-off-by: Longpeng(Mike) Link: https://lore.kernel.org/r/20220326060226.1892-4-longpeng2@huawei.com Signed-off-by: Alex Williamson --- hw/vfio/pci.c | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index b3c27c22aa..50562629ea 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -47,6 +47,7 @@ static void vfio_disable_interrupts(VFIOPCIDevice *vdev); static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled); +static void vfio_msi_disable_common(VFIOPCIDevice *vdev); /* * Disabling BAR mmaping can be slow, but toggling it around INTx can @@ -658,24 +659,12 @@ retry: "MSI vectors, retry with %d", vdev->nr_vectors, ret); } - for (i = 0; i < vdev->nr_vectors; i++) { - VFIOMSIVector *vector = &vdev->msi_vectors[i]; - if (vector->virq >= 0) { - vfio_remove_kvm_msi_virq(vector); - } - qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt), - NULL, NULL, NULL); - event_notifier_cleanup(&vector->interrupt); - } - - g_free(vdev->msi_vectors); - vdev->msi_vectors = NULL; + vfio_msi_disable_common(vdev); if (ret > 0) { vdev->nr_vectors = ret; goto retry; } - vdev->nr_vectors = 0; /* * Failing to setup MSI doesn't really fall within any specification. @@ -683,7 +672,6 @@ retry: * out to fall back to INTx for this device. */ error_report("vfio: Error: Failed to enable MSI"); - vdev->interrupt = VFIO_INT_NONE; return; } From 75d546fc18023d36779c687b948128c1a4666a96 Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Sat, 26 Mar 2022 14:02:25 +0800 Subject: [PATCH 04/11] Revert "vfio: Avoid disabling and enabling vectors repeatedly in VFIO migration" Commit ecebe53fe993 ("vfio: Avoid disabling and enabling vectors repeatedly in VFIO migration") avoids inefficiently disabling and enabling vectors repeatedly and lets the unmasked vectors be enabled one by one. But we want to batch multiple routes and defer the commit, and only commit once outside the loop of setting vector notifiers, so we cannot enable the vectors one by one in the loop now. Revert that commit and we will take another way in the next patch, it can not only avoid disabling/enabling vectors repeatedly, but also satisfy our requirement of defer to commit. Signed-off-by: Longpeng(Mike) Link: https://lore.kernel.org/r/20220326060226.1892-5-longpeng2@huawei.com Signed-off-by: Alex Williamson --- hw/vfio/pci.c | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 50562629ea..8bc36f081a 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -572,9 +572,6 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) static void vfio_msix_enable(VFIOPCIDevice *vdev) { - PCIDevice *pdev = &vdev->pdev; - unsigned int nr, max_vec = 0; - vfio_disable_interrupts(vdev); vdev->msi_vectors = g_new0(VFIOMSIVector, vdev->msix->entries); @@ -593,22 +590,11 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev) * triggering to userspace, then immediately release the vector, leaving * the physical device with no vectors enabled, but MSI-X enabled, just * like the guest view. - * If there are already unmasked vectors (in migration resume phase and - * some guest startups) which will be enabled soon, we can allocate all - * of them here to avoid inefficiently disabling and enabling vectors - * repeatedly later. */ - if (!pdev->msix_function_masked) { - for (nr = 0; nr < msix_nr_vectors_allocated(pdev); nr++) { - if (!msix_is_masked(pdev, nr)) { - max_vec = nr; - } - } - } - vfio_msix_vector_do_use(pdev, max_vec, NULL, NULL); - vfio_msix_vector_release(pdev, max_vec); + vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL); + vfio_msix_vector_release(&vdev->pdev, 0); - if (msix_set_vector_notifiers(pdev, vfio_msix_vector_use, + if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use, vfio_msix_vector_release, NULL)) { error_report("vfio: msix_set_vector_notifiers failed"); } From dc580d51f7dd3e02134957be2b771636ac59e868 Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Sat, 26 Mar 2022 14:02:26 +0800 Subject: [PATCH 05/11] vfio: defer to commit kvm irq routing when enable msi/msix In migration resume phase, all unmasked msix vectors need to be setup when loading the VF state. However, the setup operation would take longer if the VM has more VFs and each VF has more unmasked vectors. The hot spot is kvm_irqchip_commit_routes, it'll scan and update all irqfds that are already assigned each invocation, so more vectors means need more time to process them. vfio_pci_load_config vfio_msix_enable msix_set_vector_notifiers for (vector = 0; vector < dev->msix_entries_nr; vector++) { vfio_msix_vector_do_use vfio_add_kvm_msi_virq kvm_irqchip_commit_routes <-- expensive } We can reduce the cost by only committing once outside the loop. The routes are cached in kvm_state, we commit them first and then bind irqfd for each vector. The test VM has 128 vcpus and 8 VF (each one has 65 vectors), we measure the cost of the vfio_msix_enable for each VF, and we can see 90+% costs can be reduce. VF Count of irqfds[*] Original With this patch 1st 65 8 2 2nd 130 15 2 3rd 195 22 2 4th 260 24 3 5th 325 36 2 6th 390 44 3 7th 455 51 3 8th 520 58 4 Total 258ms 21ms [*] Count of irqfds How many irqfds that already assigned and need to process in this round. The optimization can be applied to msi type too. Signed-off-by: Longpeng(Mike) Link: https://lore.kernel.org/r/20220326060226.1892-6-longpeng2@huawei.com Signed-off-by: Alex Williamson --- hw/vfio/pci.c | 130 +++++++++++++++++++++++++++++++++++++------------- hw/vfio/pci.h | 2 + 2 files changed, 99 insertions(+), 33 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 8bc36f081a..ef9d7bf326 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -45,6 +45,9 @@ #define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" +/* Protected by BQL */ +static KVMRouteChange vfio_route_change; + static void vfio_disable_interrupts(VFIOPCIDevice *vdev); static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled); static void vfio_msi_disable_common(VFIOPCIDevice *vdev); @@ -413,33 +416,36 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix) static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector, int vector_n, bool msix) { - KVMRouteChange c; - int virq; - if ((msix && vdev->no_kvm_msix) || (!msix && vdev->no_kvm_msi)) { return; } - if (event_notifier_init(&vector->kvm_interrupt, 0)) { + vector->virq = kvm_irqchip_add_msi_route(&vfio_route_change, + vector_n, &vdev->pdev); +} + +static void vfio_connect_kvm_msi_virq(VFIOMSIVector *vector) +{ + if (vector->virq < 0) { return; } - c = kvm_irqchip_begin_route_changes(kvm_state); - virq = kvm_irqchip_add_msi_route(&c, vector_n, &vdev->pdev); - if (virq < 0) { - event_notifier_cleanup(&vector->kvm_interrupt); - return; + if (event_notifier_init(&vector->kvm_interrupt, 0)) { + goto fail_notifier; } - kvm_irqchip_commit_route_changes(&c); if (kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &vector->kvm_interrupt, - NULL, virq) < 0) { - kvm_irqchip_release_virq(kvm_state, virq); - event_notifier_cleanup(&vector->kvm_interrupt); - return; + NULL, vector->virq) < 0) { + goto fail_kvm; } - vector->virq = virq; + return; + +fail_kvm: + event_notifier_cleanup(&vector->kvm_interrupt); +fail_notifier: + kvm_irqchip_release_virq(kvm_state, vector->virq); + vector->virq = -1; } static void vfio_remove_kvm_msi_virq(VFIOMSIVector *vector) @@ -494,7 +500,14 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } else { if (msg) { - vfio_add_kvm_msi_virq(vdev, vector, nr, true); + if (vdev->defer_kvm_irq_routing) { + vfio_add_kvm_msi_virq(vdev, vector, nr, true); + } else { + vfio_route_change = kvm_irqchip_begin_route_changes(kvm_state); + vfio_add_kvm_msi_virq(vdev, vector, nr, true); + kvm_irqchip_commit_route_changes(&vfio_route_change); + vfio_connect_kvm_msi_virq(vector); + } } } @@ -504,11 +517,13 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, * increase them as needed. */ if (vdev->nr_vectors < nr + 1) { - vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX); vdev->nr_vectors = nr + 1; - ret = vfio_enable_vectors(vdev, true); - if (ret) { - error_report("vfio: failed to enable vectors, %d", ret); + if (!vdev->defer_kvm_irq_routing) { + vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX); + ret = vfio_enable_vectors(vdev, true); + if (ret) { + error_report("vfio: failed to enable vectors, %d", ret); + } } } else { Error *err = NULL; @@ -570,6 +585,27 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) } } +static void vfio_prepare_kvm_msi_virq_batch(VFIOPCIDevice *vdev) +{ + assert(!vdev->defer_kvm_irq_routing); + vdev->defer_kvm_irq_routing = true; + vfio_route_change = kvm_irqchip_begin_route_changes(kvm_state); +} + +static void vfio_commit_kvm_msi_virq_batch(VFIOPCIDevice *vdev) +{ + int i; + + assert(vdev->defer_kvm_irq_routing); + vdev->defer_kvm_irq_routing = false; + + kvm_irqchip_commit_route_changes(&vfio_route_change); + + for (i = 0; i < vdev->nr_vectors; i++) { + vfio_connect_kvm_msi_virq(&vdev->msi_vectors[i]); + } +} + static void vfio_msix_enable(VFIOPCIDevice *vdev) { vfio_disable_interrupts(vdev); @@ -579,26 +615,45 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev) vdev->interrupt = VFIO_INT_MSIX; /* - * Some communication channels between VF & PF or PF & fw rely on the - * physical state of the device and expect that enabling MSI-X from the - * guest enables the same on the host. When our guest is Linux, the - * guest driver call to pci_enable_msix() sets the enabling bit in the - * MSI-X capability, but leaves the vector table masked. We therefore - * can't rely on a vector_use callback (from request_irq() in the guest) - * to switch the physical device into MSI-X mode because that may come a - * long time after pci_enable_msix(). This code enables vector 0 with - * triggering to userspace, then immediately release the vector, leaving - * the physical device with no vectors enabled, but MSI-X enabled, just - * like the guest view. + * Setting vector notifiers triggers synchronous vector-use + * callbacks for each active vector. Deferring to commit the KVM + * routes once rather than per vector provides a substantial + * performance improvement. */ - vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL); - vfio_msix_vector_release(&vdev->pdev, 0); + vfio_prepare_kvm_msi_virq_batch(vdev); if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use, vfio_msix_vector_release, NULL)) { error_report("vfio: msix_set_vector_notifiers failed"); } + vfio_commit_kvm_msi_virq_batch(vdev); + + if (vdev->nr_vectors) { + int ret; + + ret = vfio_enable_vectors(vdev, true); + if (ret) { + error_report("vfio: failed to enable vectors, %d", ret); + } + } else { + /* + * Some communication channels between VF & PF or PF & fw rely on the + * physical state of the device and expect that enabling MSI-X from the + * guest enables the same on the host. When our guest is Linux, the + * guest driver call to pci_enable_msix() sets the enabling bit in the + * MSI-X capability, but leaves the vector table masked. We therefore + * can't rely on a vector_use callback (from request_irq() in the guest) + * to switch the physical device into MSI-X mode because that may come a + * long time after pci_enable_msix(). This code enables vector 0 with + * triggering to userspace, then immediately release the vector, leaving + * the physical device with no vectors enabled, but MSI-X enabled, just + * like the guest view. + */ + vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL); + vfio_msix_vector_release(&vdev->pdev, 0); + } + trace_vfio_msix_enable(vdev->vbasedev.name); } @@ -608,6 +663,13 @@ static void vfio_msi_enable(VFIOPCIDevice *vdev) vfio_disable_interrupts(vdev); + /* + * Setting vector notifiers needs to enable route for each vector. + * Deferring to commit the KVM routes once rather than per vector + * provides a substantial performance improvement. + */ + vfio_prepare_kvm_msi_virq_batch(vdev); + vdev->nr_vectors = msi_nr_vectors_allocated(&vdev->pdev); retry: vdev->msi_vectors = g_new0(VFIOMSIVector, vdev->nr_vectors); @@ -633,6 +695,8 @@ retry: vfio_add_kvm_msi_virq(vdev, vector, i, false); } + vfio_commit_kvm_msi_virq_batch(vdev); + /* Set interrupt type prior to possible interrupts */ vdev->interrupt = VFIO_INT_MSI; diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h index 64777516d1..7c236a52f4 100644 --- a/hw/vfio/pci.h +++ b/hw/vfio/pci.h @@ -19,6 +19,7 @@ #include "qemu/queue.h" #include "qemu/timer.h" #include "qom/object.h" +#include "sysemu/kvm.h" #define PCI_ANY_ID (~0) @@ -171,6 +172,7 @@ struct VFIOPCIDevice { bool no_kvm_ioeventfd; bool no_vfio_ioeventfd; bool enable_ramfb; + bool defer_kvm_irq_routing; VFIODisplay *dpy; Notifier irqchip_change_notifier; }; From 99510d271b173f21a7a1e8a238b5f35d9e88a147 Mon Sep 17 00:00:00 2001 From: Xiang Chen Date: Sat, 16 Apr 2022 17:08:24 +0800 Subject: [PATCH 06/11] vfio/common: Fix a small boundary issue of a trace It uses [offset, offset + size - 1] to indicate that the length of range is size in most places in vfio trace code (such as trace_vfio_region_region_mmap()) execpt trace_vfio_region_sparse_mmap_entry(). So change it for trace_vfio_region_sparse_mmap_entry(), but if size is zero, the trace will be weird with an underflow, so move the trace and trace it only if size is not zero. Signed-off-by: Xiang Chen Link: https://lore.kernel.org/r/1650100104-130737-1-git-send-email-chenxiang66@hisilicon.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 2b1f78fdfa..6065834717 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1544,11 +1544,10 @@ static int vfio_setup_region_sparse_mmaps(VFIORegion *region, region->mmaps = g_new0(VFIOMmap, sparse->nr_areas); for (i = 0, j = 0; i < sparse->nr_areas; i++) { - trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset, - sparse->areas[i].offset + - sparse->areas[i].size); - if (sparse->areas[i].size) { + trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset, + sparse->areas[i].offset + + sparse->areas[i].size - 1); region->mmaps[j].offset = sparse->areas[i].offset; region->mmaps[j].size = sparse->areas[i].size; j++; From 4168cdad398843ed53d650a27651868b4d3e21c9 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 6 May 2022 15:25:09 +0200 Subject: [PATCH 07/11] sysemu: tpm: Add a stub function for TPM_IS_CRB In a subsequent patch, VFIO will need to recognize if a memory region owner is a TPM CRB device. Hence VFIO needs to use TPM_IS_CRB() even if CONFIG_TPM is unset. So let's add a stub function. Signed-off-by: Eric Auger Suggested-by: Cornelia Huck Reviewed-by: Stefan Berger Link: https://lore.kernel.org/r/20220506132510.1847942-2-eric.auger@redhat.com Signed-off-by: Alex Williamson --- include/sysemu/tpm.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/include/sysemu/tpm.h b/include/sysemu/tpm.h index 68b2206463..fb40e30ff6 100644 --- a/include/sysemu/tpm.h +++ b/include/sysemu/tpm.h @@ -80,6 +80,12 @@ static inline TPMVersion tpm_get_version(TPMIf *ti) #define tpm_init() (0) #define tpm_cleanup() +/* needed for an alignment check in non-tpm code */ +static inline Object *TPM_IS_CRB(Object *obj) +{ + return NULL; +} + #endif /* CONFIG_TPM */ #endif /* QEMU_TPM_H */ From 851d6d1a0ff29a87ec588205842edf6b86d99b5c Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 6 May 2022 15:25:10 +0200 Subject: [PATCH 08/11] vfio/common: remove spurious tpm-crb-cmd misalignment warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CRB command buffer currently is a RAM MemoryRegion and given its base address alignment, it causes an error report on vfio_listener_region_add(). This region could have been a RAM device region, easing the detection of such safe situation but this option was not well received. So let's add a helper function that uses the memory region owner type to detect the situation is safe wrt the assignment. Other device types can be checked here if such kind of problem occurs again. Signed-off-by: Eric Auger Reviewed-by: Philippe Mathieu-Daudé Acked-by: Stefan Berger Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/r/20220506132510.1847942-3-eric.auger@redhat.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 27 ++++++++++++++++++++++++++- hw/vfio/trace-events | 1 + 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 6065834717..cfcb71974a 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -40,6 +40,7 @@ #include "trace.h" #include "qapi/error.h" #include "migration/migration.h" +#include "sysemu/tpm.h" VFIOGroupList vfio_group_list = QLIST_HEAD_INITIALIZER(vfio_group_list); @@ -861,6 +862,22 @@ static void vfio_unregister_ram_discard_listener(VFIOContainer *container, g_free(vrdl); } +static bool vfio_known_safe_misalignment(MemoryRegionSection *section) +{ + MemoryRegion *mr = section->mr; + + if (!TPM_IS_CRB(mr->owner)) { + return false; + } + + /* this is a known safe misaligned region, just trace for debug purpose */ + trace_vfio_known_safe_misalignment(memory_region_name(mr), + section->offset_within_address_space, + section->offset_within_region, + qemu_real_host_page_size()); + return true; +} + static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { @@ -884,7 +901,15 @@ static void vfio_listener_region_add(MemoryListener *listener, if (unlikely((section->offset_within_address_space & ~qemu_real_host_page_mask()) != (section->offset_within_region & ~qemu_real_host_page_mask()))) { - error_report("%s received unaligned region", __func__); + if (!vfio_known_safe_misalignment(section)) { + error_report("%s received unaligned region %s iova=0x%"PRIx64 + " offset_within_region=0x%"PRIx64 + " qemu_real_host_page_size=0x%"PRIxPTR, + __func__, memory_region_name(section->mr), + section->offset_within_address_space, + section->offset_within_region, + qemu_real_host_page_size()); + } return; } diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 0ef1b5f4a6..582882db91 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -100,6 +100,7 @@ vfio_listener_region_add_skip(uint64_t start, uint64_t end) "SKIPPING region_add vfio_spapr_group_attach(int groupfd, int tablefd) "Attached groupfd %d to liobn fd %d" vfio_listener_region_add_iommu(uint64_t start, uint64_t end) "region_add [iommu] 0x%"PRIx64" - 0x%"PRIx64 vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr) "region_add [ram] 0x%"PRIx64" - 0x%"PRIx64" [%p]" +vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_within_region, uintptr_t page_size) "Region \"%s\" iova=0x%"PRIx64" offset_within_region=0x%"PRIx64" qemu_real_host_page_size=0x%"PRIxPTR ": cannot be mapped for DMA" vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA" vfio_listener_region_del_skip(uint64_t start, uint64_t end) "SKIPPING region_del 0x%"PRIx64" - 0x%"PRIx64 vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" - 0x%"PRIx64 From 9d38ffc5d82839cdc9effb2e9ee84a6941a25e1a Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Mon, 2 May 2022 02:42:21 -0700 Subject: [PATCH 09/11] hw/vfio/pci: fix vfio_pci_hot_reset_result trace point "%m" format specifier is not interpreted by the trace infrastructure and thus "%m" is output instead of the actual errno string. Fix it by outputting strerror(errno). Signed-off-by: Eric Auger Signed-off-by: Yi Liu Link: https://lore.kernel.org/r/20220502094223.36384-2-yi.l.liu@intel.com [aw: replace commit log as provided by Eric] Signed-off-by: Alex Williamson --- hw/vfio/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index ef9d7bf326..cb912bd3f4 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2380,7 +2380,7 @@ static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single) g_free(reset); trace_vfio_pci_hot_reset_result(vdev->vbasedev.name, - ret ? "%m" : "Success"); + ret ? strerror(errno) : "Success"); out: /* Re-enable INTx on affected devices */ From 0d570a2572395cca79b83002e589aeb24fcd1732 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Mon, 2 May 2022 02:42:22 -0700 Subject: [PATCH 10/11] vfio/pci: Use vbasedev local variable in vfio_realize() Using a VFIODevice handle local variable to improve the code readability. no functional change intended Signed-off-by: Eric Auger Signed-off-by: Yi Liu Link: https://lore.kernel.org/r/20220502094223.36384-3-yi.l.liu@intel.com Signed-off-by: Alex Williamson --- hw/vfio/pci.c | 49 +++++++++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 24 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index cb912bd3f4..939dcc3d4a 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2846,6 +2846,7 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev) static void vfio_realize(PCIDevice *pdev, Error **errp) { VFIOPCIDevice *vdev = VFIO_PCI(pdev); + VFIODevice *vbasedev = &vdev->vbasedev; VFIODevice *vbasedev_iter; VFIOGroup *group; char *tmp, *subsys, group_path[PATH_MAX], *group_name; @@ -2856,7 +2857,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) int i, ret; bool is_mdev; - if (!vdev->vbasedev.sysfsdev) { + if (!vbasedev->sysfsdev) { if (!(~vdev->host.domain || ~vdev->host.bus || ~vdev->host.slot || ~vdev->host.function)) { error_setg(errp, "No provided host device"); @@ -2864,24 +2865,24 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) "or -device vfio-pci,sysfsdev=PATH_TO_DEVICE\n"); return; } - vdev->vbasedev.sysfsdev = + vbasedev->sysfsdev = g_strdup_printf("/sys/bus/pci/devices/%04x:%02x:%02x.%01x", vdev->host.domain, vdev->host.bus, vdev->host.slot, vdev->host.function); } - if (stat(vdev->vbasedev.sysfsdev, &st) < 0) { + if (stat(vbasedev->sysfsdev, &st) < 0) { error_setg_errno(errp, errno, "no such host device"); - error_prepend(errp, VFIO_MSG_PREFIX, vdev->vbasedev.sysfsdev); + error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->sysfsdev); return; } - vdev->vbasedev.name = g_path_get_basename(vdev->vbasedev.sysfsdev); - vdev->vbasedev.ops = &vfio_pci_ops; - vdev->vbasedev.type = VFIO_DEVICE_TYPE_PCI; - vdev->vbasedev.dev = DEVICE(vdev); + vbasedev->name = g_path_get_basename(vbasedev->sysfsdev); + vbasedev->ops = &vfio_pci_ops; + vbasedev->type = VFIO_DEVICE_TYPE_PCI; + vbasedev->dev = DEVICE(vdev); - tmp = g_strdup_printf("%s/iommu_group", vdev->vbasedev.sysfsdev); + tmp = g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); len = readlink(tmp, group_path, sizeof(group_path)); g_free(tmp); @@ -2899,7 +2900,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) goto error; } - trace_vfio_realize(vdev->vbasedev.name, groupid); + trace_vfio_realize(vbasedev->name, groupid); group = vfio_get_group(groupid, pci_device_iommu_address_space(pdev), errp); if (!group) { @@ -2907,7 +2908,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (strcmp(vbasedev_iter->name, vdev->vbasedev.name) == 0) { + if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) { error_setg(errp, "device is already attached"); vfio_put_group(group); goto error; @@ -2920,22 +2921,22 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) * stays in sync with the active working set of the guest driver. Prevent * the x-balloon-allowed option unless this is minimally an mdev device. */ - tmp = g_strdup_printf("%s/subsystem", vdev->vbasedev.sysfsdev); + tmp = g_strdup_printf("%s/subsystem", vbasedev->sysfsdev); subsys = realpath(tmp, NULL); g_free(tmp); is_mdev = subsys && (strcmp(subsys, "/sys/bus/mdev") == 0); free(subsys); - trace_vfio_mdev(vdev->vbasedev.name, is_mdev); + trace_vfio_mdev(vbasedev->name, is_mdev); - if (vdev->vbasedev.ram_block_discard_allowed && !is_mdev) { + if (vbasedev->ram_block_discard_allowed && !is_mdev) { error_setg(errp, "x-balloon-allowed only potentially compatible " "with mdev devices"); vfio_put_group(group); goto error; } - ret = vfio_get_device(group, vdev->vbasedev.name, &vdev->vbasedev, errp); + ret = vfio_get_device(group, vbasedev->name, vbasedev, errp); if (ret) { vfio_put_group(group); goto error; @@ -2948,7 +2949,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } /* Get a copy of config space */ - ret = pread(vdev->vbasedev.fd, vdev->pdev.config, + ret = pread(vbasedev->fd, vdev->pdev.config, MIN(pci_config_size(&vdev->pdev), vdev->config_size), vdev->config_offset); if (ret < (int)MIN(pci_config_size(&vdev->pdev), vdev->config_size)) { @@ -2976,7 +2977,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) goto error; } vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0); - trace_vfio_pci_emulated_vendor_id(vdev->vbasedev.name, vdev->vendor_id); + trace_vfio_pci_emulated_vendor_id(vbasedev->name, vdev->vendor_id); } else { vdev->vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID); } @@ -2987,7 +2988,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) goto error; } vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0); - trace_vfio_pci_emulated_device_id(vdev->vbasedev.name, vdev->device_id); + trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id); } else { vdev->device_id = pci_get_word(pdev->config + PCI_DEVICE_ID); } @@ -2999,7 +3000,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID, vdev->sub_vendor_id, ~0); - trace_vfio_pci_emulated_sub_vendor_id(vdev->vbasedev.name, + trace_vfio_pci_emulated_sub_vendor_id(vbasedev->name, vdev->sub_vendor_id); } @@ -3009,7 +3010,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) goto error; } vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id, ~0); - trace_vfio_pci_emulated_sub_device_id(vdev->vbasedev.name, + trace_vfio_pci_emulated_sub_device_id(vbasedev->name, vdev->sub_device_id); } @@ -3068,7 +3069,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) goto out_teardown; } - ret = vfio_get_dev_region_info(&vdev->vbasedev, + ret = vfio_get_dev_region_info(vbasedev, VFIO_REGION_TYPE_PCI_VENDOR_TYPE | PCI_VENDOR_ID_INTEL, VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION, &opregion); if (ret) { @@ -3144,9 +3145,9 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } if (!pdev->failover_pair_id) { - ret = vfio_migration_probe(&vdev->vbasedev, errp); + ret = vfio_migration_probe(vbasedev, errp); if (ret) { - error_report("%s: Migration disabled", vdev->vbasedev.name); + error_report("%s: Migration disabled", vbasedev->name); } } @@ -3163,7 +3164,7 @@ out_teardown: vfio_teardown_msi(vdev); vfio_bars_exit(vdev); error: - error_prepend(errp, VFIO_MSG_PREFIX, vdev->vbasedev.name); + error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name); } static void vfio_instance_finalize(Object *obj) From 44ee6aaae0c937abb631e57a9853c2cdef2bc9bb Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Mon, 2 May 2022 02:42:23 -0700 Subject: [PATCH 11/11] vfio/common: Rename VFIOGuestIOMMU::iommu into ::iommu_mr Rename VFIOGuestIOMMU iommu field into iommu_mr. Then it becomes clearer it is an IOMMU memory region. no functional change intended Signed-off-by: Yi Liu Link: https://lore.kernel.org/r/20220502094223.36384-4-yi.l.liu@intel.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 16 ++++++++-------- include/hw/vfio/vfio-common.h | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index cfcb71974a..159f910421 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1017,7 +1017,7 @@ static void vfio_listener_region_add(MemoryListener *listener, * device emulation the VFIO iommu handles to use). */ giommu = g_malloc0(sizeof(*giommu)); - giommu->iommu = iommu_mr; + giommu->iommu_mr = iommu_mr; giommu->iommu_offset = section->offset_within_address_space - section->offset_within_region; giommu->container = container; @@ -1032,7 +1032,7 @@ static void vfio_listener_region_add(MemoryListener *listener, int128_get64(llend), iommu_idx); - ret = memory_region_iommu_set_page_size_mask(giommu->iommu, + ret = memory_region_iommu_set_page_size_mask(giommu->iommu_mr, container->pgsizes, &err); if (ret) { @@ -1047,7 +1047,7 @@ static void vfio_listener_region_add(MemoryListener *listener, goto fail; } QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next); - memory_region_iommu_replay(giommu->iommu, &giommu->n); + memory_region_iommu_replay(giommu->iommu_mr, &giommu->n); return; } @@ -1153,7 +1153,7 @@ static void vfio_listener_region_del(MemoryListener *listener, VFIOGuestIOMMU *giommu; QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) { - if (MEMORY_REGION(giommu->iommu) == section->mr && + if (MEMORY_REGION(giommu->iommu_mr) == section->mr && giommu->n.start == section->offset_within_region) { memory_region_unregister_iommu_notifier(section->mr, &giommu->n); @@ -1418,11 +1418,11 @@ static int vfio_sync_dirty_bitmap(VFIOContainer *container, VFIOGuestIOMMU *giommu; QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) { - if (MEMORY_REGION(giommu->iommu) == section->mr && + if (MEMORY_REGION(giommu->iommu_mr) == section->mr && giommu->n.start == section->offset_within_region) { Int128 llend; vfio_giommu_dirty_notifier gdn = { .giommu = giommu }; - int idx = memory_region_iommu_attrs_to_index(giommu->iommu, + int idx = memory_region_iommu_attrs_to_index(giommu->iommu_mr, MEMTXATTRS_UNSPECIFIED); llend = int128_add(int128_make64(section->offset_within_region), @@ -1435,7 +1435,7 @@ static int vfio_sync_dirty_bitmap(VFIOContainer *container, section->offset_within_region, int128_get64(llend), idx); - memory_region_iommu_replay(giommu->iommu, &gdn.n); + memory_region_iommu_replay(giommu->iommu_mr, &gdn.n); break; } } @@ -2270,7 +2270,7 @@ static void vfio_disconnect_container(VFIOGroup *group) QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) { memory_region_unregister_iommu_notifier( - MEMORY_REGION(giommu->iommu), &giommu->n); + MEMORY_REGION(giommu->iommu_mr), &giommu->n); QLIST_REMOVE(giommu, giommu_next); g_free(giommu); } diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 8af11b0a76..e573f5a9f1 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -98,7 +98,7 @@ typedef struct VFIOContainer { typedef struct VFIOGuestIOMMU { VFIOContainer *container; - IOMMUMemoryRegion *iommu; + IOMMUMemoryRegion *iommu_mr; hwaddr iommu_offset; IOMMUNotifier n; QLIST_ENTRY(VFIOGuestIOMMU) giommu_next;