From: Alex Williamson <alex.williamson@redhat.com> To: qemu-devel@nongnu.org Cc: eric.auger@redhat.com, peterx@redhat.com, kvm@vger.kernel.org Subject: [PATCH v2 4/4] vfio/quirks: Enable ioeventfd quirks to be handled by vfio directly Date: Tue, 01 May 2018 10:43:46 -0600 [thread overview] Message-ID: <20180501164346.28940.93328.stgit@gimli.home> (raw) In-Reply-To: <20180501162901.28940.1075.stgit@gimli.home> With vfio ioeventfd support, we can program vfio-pci to perform a specified BAR write when an eventfd is triggered. This allows the KVM ioeventfd to be wired directly to vfio-pci, entirely avoiding userspace handling for these events. On the same micro-benchmark where the ioeventfd got us to almost 90% of performance versus disabling the GeForce quirks, this gets us to within 95%. Signed-off-by: Alex Williamson <alex.williamson@redhat.com> --- hw/vfio/pci-quirks.c | 50 +++++++++++++++++++++++++++++++++++++++++++------- hw/vfio/pci.c | 2 ++ hw/vfio/pci.h | 2 ++ hw/vfio/trace-events | 2 +- 4 files changed, 48 insertions(+), 8 deletions(-) diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c index 4cedc733bc0a..94be27dd0a3b 100644 --- a/hw/vfio/pci-quirks.c +++ b/hw/vfio/pci-quirks.c @@ -16,6 +16,7 @@ #include "qemu/range.h" #include "qapi/error.h" #include "qapi/visitor.h" +#include <sys/ioctl.h> #include "hw/nvram/fw_cfg.h" #include "pci.h" #include "trace.h" @@ -287,13 +288,31 @@ static VFIOQuirk *vfio_quirk_alloc(int nr_mem) return quirk; } -static void vfio_ioeventfd_exit(VFIOIOEventFD *ioeventfd) +static void vfio_ioeventfd_exit(VFIOPCIDevice *vdev, VFIOIOEventFD *ioeventfd) { QLIST_REMOVE(ioeventfd, next); + memory_region_del_eventfd(ioeventfd->mr, ioeventfd->addr, ioeventfd->size, ioeventfd->match_data, ioeventfd->data, &ioeventfd->e); - qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), NULL, NULL, NULL); + + if (ioeventfd->vfio) { + struct vfio_device_ioeventfd vfio_ioeventfd; + + vfio_ioeventfd.argsz = sizeof(vfio_ioeventfd); + vfio_ioeventfd.flags = ioeventfd->size; + vfio_ioeventfd.data = ioeventfd->data; + vfio_ioeventfd.offset = ioeventfd->region->fd_offset + + ioeventfd->region_addr; + vfio_ioeventfd.fd = -1; + + ioctl(vdev->vbasedev.fd, VFIO_DEVICE_IOEVENTFD, &vfio_ioeventfd); + + } else { + qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), + NULL, NULL, NULL); + } + event_notifier_cleanup(&ioeventfd->e); trace_vfio_ioeventfd_exit(memory_region_name(ioeventfd->mr), (uint64_t)ioeventfd->addr, ioeventfd->size, @@ -307,7 +326,7 @@ static void vfio_drop_dynamic_eventfds(VFIOPCIDevice *vdev, VFIOQuirk *quirk) QLIST_FOREACH_SAFE(ioeventfd, &quirk->ioeventfds, next, tmp) { if (ioeventfd->dynamic) { - vfio_ioeventfd_exit(ioeventfd); + vfio_ioeventfd_exit(vdev, ioeventfd); } } } @@ -361,13 +380,30 @@ static VFIOIOEventFD *vfio_ioeventfd_init(VFIOPCIDevice *vdev, ioeventfd->region = region; ioeventfd->region_addr = region_addr; - qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), - vfio_ioeventfd_handler, NULL, ioeventfd); + if (!vdev->no_vfio_ioeventfd) { + struct vfio_device_ioeventfd vfio_ioeventfd; + + vfio_ioeventfd.argsz = sizeof(vfio_ioeventfd); + vfio_ioeventfd.flags = ioeventfd->size; + vfio_ioeventfd.data = ioeventfd->data; + vfio_ioeventfd.offset = ioeventfd->region->fd_offset + + ioeventfd->region_addr; + vfio_ioeventfd.fd = event_notifier_get_fd(&ioeventfd->e); + + ioeventfd->vfio = !ioctl(vdev->vbasedev.fd, + VFIO_DEVICE_IOEVENTFD, &vfio_ioeventfd); + } + + if (!ioeventfd->vfio) { + qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), + vfio_ioeventfd_handler, NULL, ioeventfd); + } + memory_region_add_eventfd(ioeventfd->mr, ioeventfd->addr, ioeventfd->size, ioeventfd->match_data, ioeventfd->data, &ioeventfd->e); trace_vfio_ioeventfd_init(memory_region_name(mr), (uint64_t)addr, - size, data); + size, data, ioeventfd->vfio); return ioeventfd; } @@ -1835,7 +1871,7 @@ void vfio_bar_quirk_exit(VFIOPCIDevice *vdev, int nr) QLIST_FOREACH(quirk, &bar->quirks, next) { while (!QLIST_EMPTY(&quirk->ioeventfds)) { - vfio_ioeventfd_exit(QLIST_FIRST(&quirk->ioeventfds)); + vfio_ioeventfd_exit(vdev, QLIST_FIRST(&quirk->ioeventfds)); } for (i = 0; i < quirk->nr_mem; i++) { diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index ba1239551115..84e27c7bb2d1 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -3177,6 +3177,8 @@ static Property vfio_pci_dev_properties[] = { no_geforce_quirks, false), DEFINE_PROP_BOOL("x-no-kvm-ioeventfd", VFIOPCIDevice, no_kvm_ioeventfd, false), + DEFINE_PROP_BOOL("x-no-vfio-ioeventfd", VFIOPCIDevice, no_vfio_ioeventfd, + false), DEFINE_PROP_UINT32("x-pci-vendor-id", VFIOPCIDevice, vendor_id, PCI_ANY_ID), DEFINE_PROP_UINT32("x-pci-device-id", VFIOPCIDevice, device_id, PCI_ANY_ID), DEFINE_PROP_UINT32("x-pci-sub-vendor-id", VFIOPCIDevice, diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h index dbb3aca9b3d2..dbb3932b50ef 100644 --- a/hw/vfio/pci.h +++ b/hw/vfio/pci.h @@ -35,6 +35,7 @@ typedef struct VFIOIOEventFD { hwaddr region_addr; bool match_data; bool dynamic; + bool vfio; } VFIOIOEventFD; typedef struct VFIOQuirk { @@ -164,6 +165,7 @@ typedef struct VFIOPCIDevice { bool no_kvm_msix; bool no_geforce_quirks; bool no_kvm_ioeventfd; + bool no_vfio_ioeventfd; VFIODisplay *dpy; } VFIOPCIDevice; diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index f8f97d1ff90c..d2a74952e389 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -79,7 +79,7 @@ vfio_quirk_ati_bonaire_reset_done(const char *name) "%s" vfio_quirk_ati_bonaire_reset(const char *name) "%s" vfio_ioeventfd_exit(const char *name, uint64_t addr, unsigned size, uint64_t data) "%s+0x%"PRIx64"[%d]:0x%"PRIx64 vfio_ioeventfd_handler(const char *name, uint64_t addr, unsigned size, uint64_t data) "%s+0x%"PRIx64"[%d] -> 0x%"PRIx64 -vfio_ioeventfd_init(const char *name, uint64_t addr, unsigned size, uint64_t data) "%s+0x%"PRIx64"[%d]:0x%"PRIx64 +vfio_ioeventfd_init(const char *name, uint64_t addr, unsigned size, uint64_t data, bool vfio) "%s+0x%"PRIx64"[%d]:0x%"PRIx64" vfio:%d" vfio_pci_igd_bar4_write(const char *name, uint32_t index, uint32_t data, uint32_t base) "%s [0x%03x] 0x%08x -> 0x%08x" vfio_pci_igd_bdsm_enabled(const char *name, int size) "%s %dMB" vfio_pci_igd_opregion_enabled(const char *name) "%s"
WARNING: multiple messages have this Message-ID (diff)
From: Alex Williamson <alex.williamson@redhat.com> To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, eric.auger@redhat.com, peterx@redhat.com Subject: [Qemu-devel] [PATCH v2 4/4] vfio/quirks: Enable ioeventfd quirks to be handled by vfio directly Date: Tue, 01 May 2018 10:43:46 -0600 [thread overview] Message-ID: <20180501164346.28940.93328.stgit@gimli.home> (raw) In-Reply-To: <20180501162901.28940.1075.stgit@gimli.home> With vfio ioeventfd support, we can program vfio-pci to perform a specified BAR write when an eventfd is triggered. This allows the KVM ioeventfd to be wired directly to vfio-pci, entirely avoiding userspace handling for these events. On the same micro-benchmark where the ioeventfd got us to almost 90% of performance versus disabling the GeForce quirks, this gets us to within 95%. Signed-off-by: Alex Williamson <alex.williamson@redhat.com> --- hw/vfio/pci-quirks.c | 50 +++++++++++++++++++++++++++++++++++++++++++------- hw/vfio/pci.c | 2 ++ hw/vfio/pci.h | 2 ++ hw/vfio/trace-events | 2 +- 4 files changed, 48 insertions(+), 8 deletions(-) diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c index 4cedc733bc0a..94be27dd0a3b 100644 --- a/hw/vfio/pci-quirks.c +++ b/hw/vfio/pci-quirks.c @@ -16,6 +16,7 @@ #include "qemu/range.h" #include "qapi/error.h" #include "qapi/visitor.h" +#include <sys/ioctl.h> #include "hw/nvram/fw_cfg.h" #include "pci.h" #include "trace.h" @@ -287,13 +288,31 @@ static VFIOQuirk *vfio_quirk_alloc(int nr_mem) return quirk; } -static void vfio_ioeventfd_exit(VFIOIOEventFD *ioeventfd) +static void vfio_ioeventfd_exit(VFIOPCIDevice *vdev, VFIOIOEventFD *ioeventfd) { QLIST_REMOVE(ioeventfd, next); + memory_region_del_eventfd(ioeventfd->mr, ioeventfd->addr, ioeventfd->size, ioeventfd->match_data, ioeventfd->data, &ioeventfd->e); - qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), NULL, NULL, NULL); + + if (ioeventfd->vfio) { + struct vfio_device_ioeventfd vfio_ioeventfd; + + vfio_ioeventfd.argsz = sizeof(vfio_ioeventfd); + vfio_ioeventfd.flags = ioeventfd->size; + vfio_ioeventfd.data = ioeventfd->data; + vfio_ioeventfd.offset = ioeventfd->region->fd_offset + + ioeventfd->region_addr; + vfio_ioeventfd.fd = -1; + + ioctl(vdev->vbasedev.fd, VFIO_DEVICE_IOEVENTFD, &vfio_ioeventfd); + + } else { + qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), + NULL, NULL, NULL); + } + event_notifier_cleanup(&ioeventfd->e); trace_vfio_ioeventfd_exit(memory_region_name(ioeventfd->mr), (uint64_t)ioeventfd->addr, ioeventfd->size, @@ -307,7 +326,7 @@ static void vfio_drop_dynamic_eventfds(VFIOPCIDevice *vdev, VFIOQuirk *quirk) QLIST_FOREACH_SAFE(ioeventfd, &quirk->ioeventfds, next, tmp) { if (ioeventfd->dynamic) { - vfio_ioeventfd_exit(ioeventfd); + vfio_ioeventfd_exit(vdev, ioeventfd); } } } @@ -361,13 +380,30 @@ static VFIOIOEventFD *vfio_ioeventfd_init(VFIOPCIDevice *vdev, ioeventfd->region = region; ioeventfd->region_addr = region_addr; - qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), - vfio_ioeventfd_handler, NULL, ioeventfd); + if (!vdev->no_vfio_ioeventfd) { + struct vfio_device_ioeventfd vfio_ioeventfd; + + vfio_ioeventfd.argsz = sizeof(vfio_ioeventfd); + vfio_ioeventfd.flags = ioeventfd->size; + vfio_ioeventfd.data = ioeventfd->data; + vfio_ioeventfd.offset = ioeventfd->region->fd_offset + + ioeventfd->region_addr; + vfio_ioeventfd.fd = event_notifier_get_fd(&ioeventfd->e); + + ioeventfd->vfio = !ioctl(vdev->vbasedev.fd, + VFIO_DEVICE_IOEVENTFD, &vfio_ioeventfd); + } + + if (!ioeventfd->vfio) { + qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), + vfio_ioeventfd_handler, NULL, ioeventfd); + } + memory_region_add_eventfd(ioeventfd->mr, ioeventfd->addr, ioeventfd->size, ioeventfd->match_data, ioeventfd->data, &ioeventfd->e); trace_vfio_ioeventfd_init(memory_region_name(mr), (uint64_t)addr, - size, data); + size, data, ioeventfd->vfio); return ioeventfd; } @@ -1835,7 +1871,7 @@ void vfio_bar_quirk_exit(VFIOPCIDevice *vdev, int nr) QLIST_FOREACH(quirk, &bar->quirks, next) { while (!QLIST_EMPTY(&quirk->ioeventfds)) { - vfio_ioeventfd_exit(QLIST_FIRST(&quirk->ioeventfds)); + vfio_ioeventfd_exit(vdev, QLIST_FIRST(&quirk->ioeventfds)); } for (i = 0; i < quirk->nr_mem; i++) { diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index ba1239551115..84e27c7bb2d1 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -3177,6 +3177,8 @@ static Property vfio_pci_dev_properties[] = { no_geforce_quirks, false), DEFINE_PROP_BOOL("x-no-kvm-ioeventfd", VFIOPCIDevice, no_kvm_ioeventfd, false), + DEFINE_PROP_BOOL("x-no-vfio-ioeventfd", VFIOPCIDevice, no_vfio_ioeventfd, + false), DEFINE_PROP_UINT32("x-pci-vendor-id", VFIOPCIDevice, vendor_id, PCI_ANY_ID), DEFINE_PROP_UINT32("x-pci-device-id", VFIOPCIDevice, device_id, PCI_ANY_ID), DEFINE_PROP_UINT32("x-pci-sub-vendor-id", VFIOPCIDevice, diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h index dbb3aca9b3d2..dbb3932b50ef 100644 --- a/hw/vfio/pci.h +++ b/hw/vfio/pci.h @@ -35,6 +35,7 @@ typedef struct VFIOIOEventFD { hwaddr region_addr; bool match_data; bool dynamic; + bool vfio; } VFIOIOEventFD; typedef struct VFIOQuirk { @@ -164,6 +165,7 @@ typedef struct VFIOPCIDevice { bool no_kvm_msix; bool no_geforce_quirks; bool no_kvm_ioeventfd; + bool no_vfio_ioeventfd; VFIODisplay *dpy; } VFIOPCIDevice; diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index f8f97d1ff90c..d2a74952e389 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -79,7 +79,7 @@ vfio_quirk_ati_bonaire_reset_done(const char *name) "%s" vfio_quirk_ati_bonaire_reset(const char *name) "%s" vfio_ioeventfd_exit(const char *name, uint64_t addr, unsigned size, uint64_t data) "%s+0x%"PRIx64"[%d]:0x%"PRIx64 vfio_ioeventfd_handler(const char *name, uint64_t addr, unsigned size, uint64_t data) "%s+0x%"PRIx64"[%d] -> 0x%"PRIx64 -vfio_ioeventfd_init(const char *name, uint64_t addr, unsigned size, uint64_t data) "%s+0x%"PRIx64"[%d]:0x%"PRIx64 +vfio_ioeventfd_init(const char *name, uint64_t addr, unsigned size, uint64_t data, bool vfio) "%s+0x%"PRIx64"[%d]:0x%"PRIx64" vfio:%d" vfio_pci_igd_bar4_write(const char *name, uint32_t index, uint32_t data, uint32_t base) "%s [0x%03x] 0x%08x -> 0x%08x" vfio_pci_igd_bdsm_enabled(const char *name, int size) "%s %dMB" vfio_pci_igd_opregion_enabled(const char *name) "%s"
next prev parent reply other threads:[~2018-05-01 16:43 UTC|newest] Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-05-01 16:42 [PATCH v2 0/4] vfio/quirks: ioeventfd support Alex Williamson 2018-05-01 16:42 ` [Qemu-devel] " Alex Williamson 2018-05-01 16:43 ` [PATCH v2 1/4] vfio/quirks: Add common quirk alloc helper Alex Williamson 2018-05-01 16:43 ` [Qemu-devel] " Alex Williamson 2018-05-01 16:43 ` [PATCH v2 2/4] vfio/quirks: Add quirk reset callback Alex Williamson 2018-05-01 16:43 ` [Qemu-devel] " Alex Williamson 2018-05-01 16:43 ` [PATCH v2 3/4] vfio/quirks: ioeventfd quirk acceleration Alex Williamson 2018-05-01 16:43 ` [Qemu-devel] " Alex Williamson 2018-05-03 3:36 ` Peter Xu 2018-05-03 3:36 ` [Qemu-devel] " Peter Xu 2018-05-03 4:20 ` Alex Williamson 2018-05-03 4:20 ` [Qemu-devel] " Alex Williamson 2018-05-03 14:33 ` Auger Eric 2018-05-03 14:33 ` [Qemu-devel] " Auger Eric 2018-05-03 14:48 ` Alex Williamson 2018-05-03 14:48 ` [Qemu-devel] " Alex Williamson 2018-05-01 16:43 ` Alex Williamson [this message] 2018-05-01 16:43 ` [Qemu-devel] [PATCH v2 4/4] vfio/quirks: Enable ioeventfd quirks to be handled by vfio directly Alex Williamson 2018-05-03 4:56 ` Peter Xu 2018-05-03 4:56 ` [Qemu-devel] " Peter Xu 2018-05-03 16:29 ` Alex Williamson 2018-05-03 16:29 ` [Qemu-devel] " Alex Williamson 2018-05-04 2:16 ` Peter Xu 2018-05-04 2:16 ` [Qemu-devel] " Peter Xu 2018-05-04 7:38 ` Auger Eric 2018-05-04 7:38 ` [Qemu-devel] " Auger Eric 2018-05-03 15:20 ` Auger Eric 2018-05-03 15:20 ` [Qemu-devel] " Auger Eric 2018-05-03 16:30 ` Alex Williamson 2018-05-03 16:30 ` [Qemu-devel] " Alex Williamson 2018-05-01 16:56 ` [PATCH v2 0/4] vfio/quirks: ioeventfd support no-reply 2018-05-01 16:56 ` [Qemu-devel] " no-reply 2018-05-01 17:05 ` Alex Williamson 2018-05-01 17:05 ` [Qemu-devel] " Alex Williamson 2018-05-01 16:56 ` no-reply 2018-05-01 16:56 ` [Qemu-devel] " no-reply
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20180501164346.28940.93328.stgit@gimli.home \ --to=alex.williamson@redhat.com \ --cc=eric.auger@redhat.com \ --cc=kvm@vger.kernel.org \ --cc=peterx@redhat.com \ --cc=qemu-devel@nongnu.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.