From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:50588) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cUcfa-0006sq-UJ for qemu-devel@nongnu.org; Fri, 20 Jan 2017 12:08:15 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cUcfY-0001MX-Ny for qemu-devel@nongnu.org; Fri, 20 Jan 2017 12:08:10 -0500 Received: from mx1.redhat.com ([209.132.183.28]:45886) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1cUcfY-0001MB-G1 for qemu-devel@nongnu.org; Fri, 20 Jan 2017 12:08:08 -0500 Received: from int-mx13.intmail.prod.int.phx2.redhat.com (int-mx13.intmail.prod.int.phx2.redhat.com [10.5.11.26]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id BD2797FB68 for ; Fri, 20 Jan 2017 17:08:08 +0000 (UTC) From: Paolo Bonzini Date: Fri, 20 Jan 2017 18:07:57 +0100 Message-Id: <20170120170757.30308-8-pbonzini@redhat.com> In-Reply-To: <20170120170757.30308-1-pbonzini@redhat.com> References: <20170120170757.30308-1-pbonzini@redhat.com> Subject: [Qemu-devel] [PATCH 7/7] virtio: use VRingMemoryRegionCaches for avail and used rings List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: mst@redhat.com, stefanha@redhat.com The virtio-net change is necessary because it uses virtqueue_fill and virtqueue_flush instead of the more convenient virtqueue_push. Signed-off-by: Paolo Bonzini --- hw/net/virtio-net.c | 14 +++++- hw/virtio/virtio.c | 138 +++++++++++++++++++++++++++++++++++++--------------- 2 files changed, 112 insertions(+), 40 deletions(-) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 7b3ad4a..6f0e397 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -1130,7 +1130,8 @@ static int receive_filter(VirtIONet *n, const uint8_t *buf, int size) return 0; } -static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t size) +static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, + size_t size) { VirtIONet *n = qemu_get_nic_opaque(nc); VirtIONetQueue *q = virtio_net_get_subqueue(nc); @@ -1233,6 +1234,17 @@ static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t return size; } +static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, + size_t size) +{ + ssize_t r; + + rcu_read_lock(); + r = virtio_net_receive_rcu(nc, buf, size); + rcu_read_unlock(); + return r; +} + static int32_t virtio_net_flush_tx(VirtIONetQueue *q); static void virtio_net_tx_complete(NetClientState *nc, ssize_t len) diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 668a97f..fbee9b2 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -168,6 +168,7 @@ void virtio_queue_update_rings(VirtIODevice *vdev, int n) virtio_init_region_cache(vdev, n); } +/* Called within rcu_read_lock(). */ static void vring_desc_read(VirtIODevice *vdev, VRingDesc *desc, MemoryRegionCache *cache, int i) { @@ -179,88 +180,110 @@ static void vring_desc_read(VirtIODevice *vdev, VRingDesc *desc, virtio_tswap16s(vdev, &desc->next); } +/* Called within rcu_read_lock(). */ static inline uint16_t vring_avail_flags(VirtQueue *vq) { - hwaddr pa; - pa = vq->vring.avail + offsetof(VRingAvail, flags); - return virtio_lduw_phys(vq->vdev, pa); + VRingMemoryRegionCaches *caches = atomic_rcu_read(&vq->vring.caches); + hwaddr pa = offsetof(VRingAvail, flags); + return virtio_lduw_phys_cached(vq->vdev, &caches->avail, pa); } +/* Called within rcu_read_lock(). */ static inline uint16_t vring_avail_idx(VirtQueue *vq) { - hwaddr pa; - pa = vq->vring.avail + offsetof(VRingAvail, idx); - vq->shadow_avail_idx = virtio_lduw_phys(vq->vdev, pa); + VRingMemoryRegionCaches *caches = atomic_rcu_read(&vq->vring.caches); + hwaddr pa = offsetof(VRingAvail, idx); + vq->shadow_avail_idx = virtio_lduw_phys_cached(vq->vdev, &caches->avail, pa); return vq->shadow_avail_idx; } +/* Called within rcu_read_lock(). */ static inline uint16_t vring_avail_ring(VirtQueue *vq, int i) { - hwaddr pa; - pa = vq->vring.avail + offsetof(VRingAvail, ring[i]); - return virtio_lduw_phys(vq->vdev, pa); + VRingMemoryRegionCaches *caches = atomic_rcu_read(&vq->vring.caches); + hwaddr pa = offsetof(VRingAvail, ring[i]); + return virtio_lduw_phys_cached(vq->vdev, &caches->avail, pa); } +/* Called within rcu_read_lock(). */ static inline uint16_t vring_get_used_event(VirtQueue *vq) { return vring_avail_ring(vq, vq->vring.num); } +/* Called within rcu_read_lock(). */ static inline void vring_used_write(VirtQueue *vq, VRingUsedElem *uelem, int i) { - hwaddr pa; + VRingMemoryRegionCaches *caches = atomic_rcu_read(&vq->vring.caches); + hwaddr pa = offsetof(VRingUsed, ring[i]); virtio_tswap32s(vq->vdev, &uelem->id); virtio_tswap32s(vq->vdev, &uelem->len); - pa = vq->vring.used + offsetof(VRingUsed, ring[i]); - address_space_write(vq->vdev->dma_as, pa, MEMTXATTRS_UNSPECIFIED, - (void *)uelem, sizeof(VRingUsedElem)); + address_space_write_cached(&caches->used, pa, uelem, sizeof(VRingUsedElem)); + address_space_cache_invalidate(&caches->used, pa, sizeof(VRingUsedElem)); } +/* Called within rcu_read_lock(). */ static uint16_t vring_used_idx(VirtQueue *vq) { - hwaddr pa; - pa = vq->vring.used + offsetof(VRingUsed, idx); - return virtio_lduw_phys(vq->vdev, pa); + VRingMemoryRegionCaches *caches = atomic_rcu_read(&vq->vring.caches); + hwaddr pa = vq->vring.used + offsetof(VRingUsed, idx); + return virtio_lduw_phys_cached(vq->vdev, &caches->used, pa); } +/* Called within rcu_read_lock(). */ static inline void vring_used_idx_set(VirtQueue *vq, uint16_t val) { - hwaddr pa; - pa = vq->vring.used + offsetof(VRingUsed, idx); - virtio_stw_phys(vq->vdev, pa, val); + VRingMemoryRegionCaches *caches = atomic_rcu_read(&vq->vring.caches); + hwaddr pa = offsetof(VRingUsed, idx); + virtio_stw_phys_cached(vq->vdev, &caches->used, pa, val); + address_space_cache_invalidate(&caches->used, pa, sizeof(val)); vq->used_idx = val; } +/* Called within rcu_read_lock(). */ static inline void vring_used_flags_set_bit(VirtQueue *vq, int mask) { + VRingMemoryRegionCaches *caches = atomic_rcu_read(&vq->vring.caches); VirtIODevice *vdev = vq->vdev; - hwaddr pa; - pa = vq->vring.used + offsetof(VRingUsed, flags); - virtio_stw_phys(vdev, pa, virtio_lduw_phys(vdev, pa) | mask); + hwaddr pa = offsetof(VRingUsed, flags); + uint16_t flags = virtio_lduw_phys_cached(vq->vdev, &caches->used, pa); + + virtio_stw_phys_cached(vdev, &caches->used, pa, flags | mask); + address_space_cache_invalidate(&caches->used, pa, sizeof(flags)); } +/* Called within rcu_read_lock(). */ static inline void vring_used_flags_unset_bit(VirtQueue *vq, int mask) { + VRingMemoryRegionCaches *caches = atomic_rcu_read(&vq->vring.caches); VirtIODevice *vdev = vq->vdev; - hwaddr pa; - pa = vq->vring.used + offsetof(VRingUsed, flags); - virtio_stw_phys(vdev, pa, virtio_lduw_phys(vdev, pa) & ~mask); + hwaddr pa = offsetof(VRingUsed, flags); + uint16_t flags = virtio_lduw_phys_cached(vq->vdev, &caches->used, pa); + + virtio_stw_phys_cached(vdev, &caches->used, pa, flags & ~mask); + address_space_cache_invalidate(&caches->used, pa, sizeof(flags)); } +/* Called within rcu_read_lock(). */ static inline void vring_set_avail_event(VirtQueue *vq, uint16_t val) { + VRingMemoryRegionCaches *caches; hwaddr pa; if (!vq->notification) { return; } - pa = vq->vring.used + offsetof(VRingUsed, ring[vq->vring.num]); - virtio_stw_phys(vq->vdev, pa, val); + + caches = atomic_rcu_read(&vq->vring.caches); + pa = offsetof(VRingUsed, ring[vq->vring.num]); + virtio_stw_phys_cached(vq->vdev, &caches->used, pa, val); } void virtio_queue_set_notification(VirtQueue *vq, int enable) { vq->notification = enable; + + rcu_read_lock(); if (virtio_vdev_has_feature(vq->vdev, VIRTIO_RING_F_EVENT_IDX)) { vring_set_avail_event(vq, vring_avail_idx(vq)); } else if (enable) { @@ -272,6 +295,7 @@ void virtio_queue_set_notification(VirtQueue *vq, int enable) /* Expose avail event/used flags before caller checks the avail idx. */ smp_mb(); } + rcu_read_unlock(); } int virtio_queue_ready(VirtQueue *vq) @@ -280,8 +304,9 @@ int virtio_queue_ready(VirtQueue *vq) } /* Fetch avail_idx from VQ memory only when we really need to know if - * guest has added some buffers. */ -int virtio_queue_empty(VirtQueue *vq) + * guest has added some buffers. + * Called within rcu_read_lock(). */ +static int virtio_queue_empty_rcu(VirtQueue *vq) { if (vq->shadow_avail_idx != vq->last_avail_idx) { return 0; @@ -290,6 +315,20 @@ int virtio_queue_empty(VirtQueue *vq) return vring_avail_idx(vq) == vq->last_avail_idx; } +int virtio_queue_empty(VirtQueue *vq) +{ + bool empty; + + if (vq->shadow_avail_idx != vq->last_avail_idx) { + return 0; + } + + rcu_read_lock(); + empty = vring_avail_idx(vq) == vq->last_avail_idx; + rcu_read_unlock(); + return empty; +} + static void virtqueue_unmap_sg(VirtQueue *vq, const VirtQueueElement *elem, unsigned int len) { @@ -368,6 +407,7 @@ bool virtqueue_rewind(VirtQueue *vq, unsigned int num) return true; } +/* Called within rcu_read_lock(). */ void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem, unsigned int len, unsigned int idx) { @@ -388,6 +428,7 @@ void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem, vring_used_write(vq, &uelem, idx); } +/* Called within rcu_read_lock(). */ void virtqueue_flush(VirtQueue *vq, unsigned int count) { uint16_t old, new; @@ -411,10 +452,13 @@ void virtqueue_flush(VirtQueue *vq, unsigned int count) void virtqueue_push(VirtQueue *vq, const VirtQueueElement *elem, unsigned int len) { + rcu_read_lock(); virtqueue_fill(vq, elem, len, 0); virtqueue_flush(vq, 1); + rcu_read_unlock(); } +/* Called within rcu_read_lock(). */ static int virtqueue_num_heads(VirtQueue *vq, unsigned int idx) { uint16_t num_heads = vring_avail_idx(vq) - idx; @@ -434,6 +478,7 @@ static int virtqueue_num_heads(VirtQueue *vq, unsigned int idx) return num_heads; } +/* Called within rcu_read_lock(). */ static bool virtqueue_get_head(VirtQueue *vq, unsigned int idx, unsigned int *head) { @@ -734,8 +779,9 @@ void *virtqueue_pop(VirtQueue *vq, size_t sz) if (unlikely(vdev->broken)) { return NULL; } - if (virtio_queue_empty(vq)) { - return NULL; + rcu_read_lock(); + if (virtio_queue_empty_rcu(vq)) { + goto out_rcu; } /* Needed after virtio_queue_empty(), see comment in * virtqueue_num_heads(). */ @@ -748,11 +794,11 @@ void *virtqueue_pop(VirtQueue *vq, size_t sz) if (vq->inuse >= vq->vring.num) { virtio_error(vdev, "Virtqueue size exceeded"); - return NULL; + goto out_rcu; } if (!virtqueue_get_head(vq, vq->last_avail_idx++, &head)) { - return NULL; + goto out_rcu; } if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { @@ -765,7 +811,7 @@ void *virtqueue_pop(VirtQueue *vq, size_t sz) caches = atomic_rcu_read(&vq->vring.caches); if (caches->desc.len < max * sizeof(VRingDesc)) { virtio_error(vdev, "Cannot map descriptor ring"); - return NULL; + goto out_rcu; } desc_cache = &caches->desc; @@ -773,7 +819,7 @@ void *virtqueue_pop(VirtQueue *vq, size_t sz) if (desc.flags & VRING_DESC_F_INDIRECT) { if (desc.len % sizeof(VRingDesc)) { virtio_error(vdev, "Invalid size for indirect buffer table"); - return NULL; + goto out_rcu; } /* loop over the indirect descriptor table */ @@ -782,7 +828,7 @@ void *virtqueue_pop(VirtQueue *vq, size_t sz) desc_cache = &indirect_desc_cache; if (len < desc.len) { virtio_error(vdev, "Cannot map indirect buffer"); - return NULL; + goto out_rcu; } max = desc.len / sizeof(VRingDesc); @@ -844,12 +890,13 @@ done: if (desc_cache == &indirect_desc_cache) { address_space_cache_destroy(&indirect_desc_cache); } - rcu_read_unlock(); + rcu_read_unlock(); return elem; err_undo_map: virtqueue_undo_map_desc(out_num, in_num, iov); +out_rcu: elem = NULL; goto done; } @@ -1478,6 +1525,7 @@ static void virtio_set_isr(VirtIODevice *vdev, int value) } } +/* Called within rcu_read_lock(). */ static bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq) { uint16_t old, new; @@ -1503,7 +1551,12 @@ static bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq) void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq) { - if (!virtio_should_notify(vdev, vq)) { + bool should_notify; + rcu_read_lock(); + should_notify = virtio_should_notify(vdev, vq); + rcu_read_unlock(); + + if (!should_notify) { return; } @@ -1530,7 +1583,12 @@ void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq) void virtio_notify(VirtIODevice *vdev, VirtQueue *vq) { - if (!virtio_should_notify(vdev, vq)) { + bool should_notify; + rcu_read_lock(); + should_notify = virtio_should_notify(vdev, vq); + rcu_read_unlock(); + + if (!should_notify) { return; } @@ -1984,6 +2042,7 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) } } + rcu_read_lock(); for (i = 0; i < num; i++) { if (vdev->vq[i].vring.desc) { uint16_t nheads; @@ -2018,6 +2077,7 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) } } } + rcu_read_unlock(); return 0; } -- 2.9.3