From 7b21e34fd1c272e3a8c3846168f2f6287a4cd72b Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 12 Jan 2012 15:44:42 +1030 Subject: virtio: harsher barriers for rpmsg. We were cheating with our barriers; using the smp ones rather than the real device ones. That was fine, until rpmsg came along, which is used to talk to a real device (a non-SMP CPU). Unfortunately, just putting back the real barriers (reverting d57ed95d) causes a performance regression on virtio-pci. In particular, Amos reports netbench's TCP_RR over virtio_net CPU utilization increased up to 35% while throughput went down by up to 14%. By comparison, this branch is in the noise. Reference: https://lkml.org/lkml/2011/12/11/22 Signed-off-by: Rusty Russell --- drivers/lguest/lguest_device.c | 8 +++++--- drivers/s390/kvm/kvm_virtio.c | 2 +- drivers/virtio/virtio_mmio.c | 4 ++-- drivers/virtio/virtio_pci.c | 4 ++-- drivers/virtio/virtio_ring.c | 34 +++++++++++++++++++++------------- include/linux/virtio_ring.h | 1 + tools/virtio/linux/virtio.h | 1 + tools/virtio/virtio_test.c | 3 ++- 8 files changed, 35 insertions(+), 22 deletions(-) diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c index 595d7319701..6a1d6447b86 100644 --- a/drivers/lguest/lguest_device.c +++ b/drivers/lguest/lguest_device.c @@ -292,10 +292,12 @@ static struct virtqueue *lg_find_vq(struct virtio_device *vdev, /* * OK, tell virtio_ring.c to set up a virtqueue now we know its size - * and we've got a pointer to its pages. + * and we've got a pointer to its pages. Note that we set weak_barriers + * to 'true': the host just a(nother) SMP CPU, so we only need inter-cpu + * barriers. */ - vq = vring_new_virtqueue(lvq->config.num, LGUEST_VRING_ALIGN, - vdev, lvq->pages, lg_notify, callback, name); + vq = vring_new_virtqueue(lvq->config.num, LGUEST_VRING_ALIGN, vdev, + true, lvq->pages, lg_notify, callback, name); if (!vq) { err = -ENOMEM; goto unmap; diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c index 8af868bab20..7bc1955337e 100644 --- a/drivers/s390/kvm/kvm_virtio.c +++ b/drivers/s390/kvm/kvm_virtio.c @@ -198,7 +198,7 @@ static struct virtqueue *kvm_find_vq(struct virtio_device *vdev, goto out; vq = vring_new_virtqueue(config->num, KVM_S390_VIRTIO_RING_ALIGN, - vdev, (void *) config->address, + vdev, true, (void *) config->address, kvm_notify, callback, name); if (!vq) { err = -ENOMEM; diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 0269717436a..01d6dc250d5 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -310,8 +310,8 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN); /* Create the vring */ - vq = vring_new_virtqueue(info->num, VIRTIO_MMIO_VRING_ALIGN, - vdev, info->queue, vm_notify, callback, name); + vq = vring_new_virtqueue(info->num, VIRTIO_MMIO_VRING_ALIGN, vdev, + true, info->queue, vm_notify, callback, name); if (!vq) { err = -ENOMEM; goto error_new_virtqueue; diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c index baabb7937ec..688b42d28da 100644 --- a/drivers/virtio/virtio_pci.c +++ b/drivers/virtio/virtio_pci.c @@ -414,8 +414,8 @@ static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN); /* create the vring */ - vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN, - vdev, info->queue, vp_notify, callback, name); + vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN, vdev, + true, info->queue, vp_notify, callback, name); if (!vq) { err = -ENOMEM; goto out_activate_queue; diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index c7a2c208f6e..50da9204609 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -28,17 +28,20 @@ #ifdef CONFIG_SMP /* Where possible, use SMP barriers which are more lightweight than mandatory * barriers, because mandatory barriers control MMIO effects on accesses - * through relaxed memory I/O windows (which virtio does not use). */ -#define virtio_mb() smp_mb() -#define virtio_rmb() smp_rmb() -#define virtio_wmb() smp_wmb() + * through relaxed memory I/O windows (which virtio-pci does not use). */ +#define virtio_mb(vq) \ + do { if ((vq)->weak_barriers) smp_mb(); else mb(); } while(0) +#define virtio_rmb(vq) \ + do { if ((vq)->weak_barriers) smp_rmb(); else rmb(); } while(0) +#define virtio_wmb(vq) \ + do { if ((vq)->weak_barriers) smp_rmb(); else rmb(); } while(0) #else /* We must force memory ordering even if guest is UP since host could be * running on another CPU, but SMP barriers are defined to barrier() in that * configuration. So fall back to mandatory barriers instead. */ -#define virtio_mb() mb() -#define virtio_rmb() rmb() -#define virtio_wmb() wmb() +#define virtio_mb(vq) mb() +#define virtio_rmb(vq) rmb() +#define virtio_wmb(vq) wmb() #endif #ifdef DEBUG @@ -77,6 +80,9 @@ struct vring_virtqueue /* Actual memory layout for this queue */ struct vring vring; + /* Can we use weak barriers? */ + bool weak_barriers; + /* Other side has made a mess, don't try any more. */ bool broken; @@ -245,14 +251,14 @@ void virtqueue_kick(struct virtqueue *_vq) START_USE(vq); /* Descriptors and available array need to be set before we expose the * new available array entries. */ - virtio_wmb(); + virtio_wmb(vq); old = vq->vring.avail->idx; new = vq->vring.avail->idx = old + vq->num_added; vq->num_added = 0; /* Need to update avail index before checking if we should notify */ - virtio_mb(); + virtio_mb(vq); if (vq->event ? vring_need_event(vring_avail_event(&vq->vring), new, old) : @@ -314,7 +320,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) } /* Only get used array entries after they have been exposed by host. */ - virtio_rmb(); + virtio_rmb(vq); i = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].id; *len = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].len; @@ -337,7 +343,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) * the read in the next get_buf call. */ if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) { vring_used_event(&vq->vring) = vq->last_used_idx; - virtio_mb(); + virtio_mb(vq); } END_USE(vq); @@ -366,7 +372,7 @@ bool virtqueue_enable_cb(struct virtqueue *_vq) * entry. Always do both to keep code simple. */ vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT; vring_used_event(&vq->vring) = vq->last_used_idx; - virtio_mb(); + virtio_mb(vq); if (unlikely(more_used(vq))) { END_USE(vq); return false; @@ -393,7 +399,7 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) /* TODO: tune this threshold */ bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4; vring_used_event(&vq->vring) = vq->last_used_idx + bufs; - virtio_mb(); + virtio_mb(vq); if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) { END_USE(vq); return false; @@ -453,6 +459,7 @@ EXPORT_SYMBOL_GPL(vring_interrupt); struct virtqueue *vring_new_virtqueue(unsigned int num, unsigned int vring_align, struct virtio_device *vdev, + bool weak_barriers, void *pages, void (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), @@ -476,6 +483,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int num, vq->vq.vdev = vdev; vq->vq.name = name; vq->notify = notify; + vq->weak_barriers = weak_barriers; vq->broken = false; vq->last_used_idx = 0; vq->num_added = 0; diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 36be0f6e18a..e338730c266 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -168,6 +168,7 @@ struct virtqueue; struct virtqueue *vring_new_virtqueue(unsigned int num, unsigned int vring_align, struct virtio_device *vdev, + bool weak_barriers, void *pages, void (*notify)(struct virtqueue *vq), void (*callback)(struct virtqueue *vq), diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index 669bcdd4580..953db2abf6b 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -214,6 +214,7 @@ void *virtqueue_detach_unused_buf(struct virtqueue *vq); struct virtqueue *vring_new_virtqueue(unsigned int num, unsigned int vring_align, struct virtio_device *vdev, + bool weak_barriers, void *pages, void (*notify)(struct virtqueue *vq), void (*callback)(struct virtqueue *vq), diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index 74d3331bdaf..0740284396c 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -92,7 +92,8 @@ static void vq_info_add(struct vdev_info *dev, int num) assert(r >= 0); memset(info->ring, 0, vring_size(num, 4096)); vring_init(&info->vring, num, info->ring, 4096); - info->vq = vring_new_virtqueue(info->vring.num, 4096, &dev->vdev, info->ring, + info->vq = vring_new_virtqueue(info->vring.num, 4096, &dev->vdev, + true, info->ring, vq_notify, vq_callback, "test"); assert(info->vq); info->vq->priv = info; -- cgit v1.2.3-18-g5258 From 1e214a5c1a7e901fc8e98ad6ef84f11005f9ee9d Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 3 Nov 2011 10:20:04 +0200 Subject: virtio-balloon: Trivial cleanups Trivial changes to remove forgotten junk, format comments, and correct names. Cc: Rusty Russell Cc: "Michael S. Tsirkin" Cc: virtualization@lists.linux-foundation.org Signed-off-by: Sasha Levin Signed-off-by: Rusty Russell --- drivers/virtio/virtio_balloon.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 94fd738a774..f64ff185b8b 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -1,4 +1,5 @@ -/* Virtio balloon implementation, inspired by Dor Loar and Marcelo +/* + * Virtio balloon implementation, inspired by Dor Laor and Marcelo * Tosatti's implementations. * * Copyright 2008 Rusty Russell IBM Corporation @@ -17,7 +18,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ -//#define DEBUG + #include #include #include @@ -149,7 +150,6 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num) vb->num_pages--; } - /* * Note that if * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST); -- cgit v1.2.3-18-g5258 From 5dfc17628d57f9e62043ed0cba03a6e3eb019a78 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 12 Jan 2012 15:44:42 +1030 Subject: virtio: document functions better. The old documentation is left over from when we used a structure with strategy pointers. And move the documentation to the C file as per kernel practice. Though I disagree... Signed-off-by: Rusty Russell Reviewed-by: Christoph Hellwig --- drivers/virtio/virtio_ring.c | 92 +++++++++++++++++++++++++++++++++++++++++++- include/linux/virtio.h | 47 ---------------------- 2 files changed, 91 insertions(+), 48 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 50da9204609..fe50486341a 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -166,6 +166,23 @@ static int vring_add_indirect(struct vring_virtqueue *vq, return head; } +/** + * virtqueue_add_buf_gfp - expose buffer to other end + * @vq: the struct virtqueue we're talking about. + * @sg: the description of the buffer(s). + * @out_num: the number of sg readable by other side + * @in_num: the number of sg which are writable (after readable ones) + * @data: the token identifying the buffer. + * @gfp: how to do memory allocations (if necessary). + * + * Caller must ensure we don't call this with other virtqueue operations + * at the same time (except where noted). + * + * Returns remaining capacity of queue or a negative error + * (ie. ENOSPC). Note that it only really makes sense to treat all + * positive return values as "available": indirect buffers mean that + * we can put an entire sg[] array inside a single queue entry. + */ int virtqueue_add_buf_gfp(struct virtqueue *_vq, struct scatterlist sg[], unsigned int out, @@ -244,6 +261,16 @@ add_head: } EXPORT_SYMBOL_GPL(virtqueue_add_buf_gfp); +/** + * virtqueue_kick - update after add_buf + * @vq: the struct virtqueue + * + * After one or more virtqueue_add_buf_gfp calls, invoke this to kick + * the other side. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + */ void virtqueue_kick(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); @@ -300,6 +327,22 @@ static inline bool more_used(const struct vring_virtqueue *vq) return vq->last_used_idx != vq->vring.used->idx; } +/** + * virtqueue_get_buf - get the next used buffer + * @vq: the struct virtqueue we're talking about. + * @len: the length written into the buffer + * + * If the driver wrote data into the buffer, @len will be set to the + * amount written. This means you don't need to clear the buffer + * beforehand to ensure there's no data leakage in the case of short + * writes. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + * + * Returns NULL if there are no used buffers, or the "data" token + * handed to virtqueue_add_buf_gfp(). + */ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) { struct vring_virtqueue *vq = to_vvq(_vq); @@ -351,6 +394,15 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) } EXPORT_SYMBOL_GPL(virtqueue_get_buf); +/** + * virtqueue_disable_cb - disable callbacks + * @vq: the struct virtqueue we're talking about. + * + * Note that this is not necessarily synchronous, hence unreliable and only + * useful as an optimization. + * + * Unlike other operations, this need not be serialized. + */ void virtqueue_disable_cb(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); @@ -359,6 +411,17 @@ void virtqueue_disable_cb(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(virtqueue_disable_cb); +/** + * virtqueue_enable_cb - restart callbacks after disable_cb. + * @vq: the struct virtqueue we're talking about. + * + * This re-enables callbacks; it returns "false" if there are pending + * buffers in the queue, to detect a possible race between the driver + * checking for more work, and enabling callbacks. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + */ bool virtqueue_enable_cb(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); @@ -383,6 +446,19 @@ bool virtqueue_enable_cb(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(virtqueue_enable_cb); +/** + * virtqueue_enable_cb_delayed - restart callbacks after disable_cb. + * @vq: the struct virtqueue we're talking about. + * + * This re-enables callbacks but hints to the other side to delay + * interrupts until most of the available buffers have been processed; + * it returns "false" if there are many pending buffers in the queue, + * to detect a possible race between the driver checking for more work, + * and enabling callbacks. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + */ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); @@ -410,6 +486,14 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed); +/** + * virtqueue_detach_unused_buf - detach first unused buffer + * @vq: the struct virtqueue we're talking about. + * + * Returns NULL or the "data" token handed to virtqueue_add_buf_gfp(). + * This is not valid on an active queue; it is useful only for device + * shutdown. + */ void *virtqueue_detach_unused_buf(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); @@ -538,7 +622,13 @@ void vring_transport_features(struct virtio_device *vdev) } EXPORT_SYMBOL_GPL(vring_transport_features); -/* return the size of the vring within the virtqueue */ +/** + * virtqueue_get_vring_size - return the size of the virtqueue's vring + * @vq: the struct virtqueue containing the vring of interest. + * + * Returns the size of the vring. This is mainly used for boasting to + * userspace. Unlike other operations, this need not be serialized. + */ unsigned int virtqueue_get_vring_size(struct virtqueue *_vq) { diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 4c069d8bd74..73ad7243128 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -25,53 +25,6 @@ struct virtqueue { void *priv; }; -/** - * operations for virtqueue - * virtqueue_add_buf: expose buffer to other end - * vq: the struct virtqueue we're talking about. - * sg: the description of the buffer(s). - * out_num: the number of sg readable by other side - * in_num: the number of sg which are writable (after readable ones) - * data: the token identifying the buffer. - * gfp: how to do memory allocations (if necessary). - * Returns remaining capacity of queue (sg segments) or a negative error. - * virtqueue_kick: update after add_buf - * vq: the struct virtqueue - * After one or more add_buf calls, invoke this to kick the other side. - * virtqueue_get_buf: get the next used buffer - * vq: the struct virtqueue we're talking about. - * len: the length written into the buffer - * Returns NULL or the "data" token handed to add_buf. - * virtqueue_disable_cb: disable callbacks - * vq: the struct virtqueue we're talking about. - * Note that this is not necessarily synchronous, hence unreliable and only - * useful as an optimization. - * virtqueue_enable_cb: restart callbacks after disable_cb. - * vq: the struct virtqueue we're talking about. - * This re-enables callbacks; it returns "false" if there are pending - * buffers in the queue, to detect a possible race between the driver - * checking for more work, and enabling callbacks. - * virtqueue_enable_cb_delayed: restart callbacks after disable_cb. - * vq: the struct virtqueue we're talking about. - * This re-enables callbacks but hints to the other side to delay - * interrupts until most of the available buffers have been processed; - * it returns "false" if there are many pending buffers in the queue, - * to detect a possible race between the driver checking for more work, - * and enabling callbacks. - * virtqueue_detach_unused_buf: detach first unused buffer - * vq: the struct virtqueue we're talking about. - * Returns NULL or the "data" token handed to add_buf - * virtqueue_get_vring_size: return the size of the virtqueue's vring - * vq: the struct virtqueue containing the vring of interest. - * Returns the size of the vring. - * - * Locking rules are straightforward: the driver is responsible for - * locking. No two operations may be invoked simultaneously, with the exception - * of virtqueue_disable_cb. - * - * All operations can be called in any context. - */ - int virtqueue_add_buf_gfp(struct virtqueue *vq, struct scatterlist sg[], unsigned int out_num, -- cgit v1.2.3-18-g5258 From f96fde41f7f9af6cf20f6a1919f5d9670f84d574 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 12 Jan 2012 15:44:42 +1030 Subject: virtio: rename virtqueue_add_buf_gfp to virtqueue_add_buf Remove wrapper functions. This makes the allocation type explicit in all callers; I used GPF_KERNEL where it seemed obvious, left it at GFP_ATOMIC otherwise. Signed-off-by: Rusty Russell Reviewed-by: Christoph Hellwig --- drivers/block/virtio_blk.c | 2 +- drivers/char/hw_random/virtio-rng.c | 2 +- drivers/char/virtio_console.c | 6 +++--- drivers/net/virtio_net.c | 12 ++++++------ drivers/virtio/virtio_balloon.c | 7 ++++--- drivers/virtio/virtio_ring.c | 22 +++++++++++----------- include/linux/virtio.h | 21 ++++++--------------- net/9p/trans_virtio.c | 6 ++++-- tools/virtio/linux/virtio.h | 21 ++++++--------------- tools/virtio/virtio_test.c | 3 ++- 10 files changed, 44 insertions(+), 58 deletions(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 4d0b70adf5f..a345e40e1bc 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -172,7 +172,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk, } } - if (virtqueue_add_buf(vblk->vq, vblk->sg, out, in, vbr) < 0) { + if (virtqueue_add_buf(vblk->vq, vblk->sg, out, in, vbr, GFP_ATOMIC)<0) { mempool_free(vbr, vblk->pool); return false; } diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index fd699ccecf5..723725bbb96 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -47,7 +47,7 @@ static void register_buffer(u8 *buf, size_t size) sg_init_one(&sg, buf, size); /* There should always be room for one buffer. */ - if (virtqueue_add_buf(vq, &sg, 0, 1, buf) < 0) + if (virtqueue_add_buf(vq, &sg, 0, 1, buf, GFP_KERNEL) < 0) BUG(); virtqueue_kick(vq); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 8e3c46d67cb..d1ae1492ee7 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -392,7 +392,7 @@ static int add_inbuf(struct virtqueue *vq, struct port_buffer *buf) sg_init_one(sg, buf->buf, buf->size); - ret = virtqueue_add_buf(vq, sg, 0, 1, buf); + ret = virtqueue_add_buf(vq, sg, 0, 1, buf, GFP_ATOMIC); virtqueue_kick(vq); return ret; } @@ -457,7 +457,7 @@ static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id, vq = portdev->c_ovq; sg_init_one(sg, &cpkt, sizeof(cpkt)); - if (virtqueue_add_buf(vq, sg, 1, 0, &cpkt) >= 0) { + if (virtqueue_add_buf(vq, sg, 1, 0, &cpkt, GFP_ATOMIC) >= 0) { virtqueue_kick(vq); while (!virtqueue_get_buf(vq, &len)) cpu_relax(); @@ -506,7 +506,7 @@ static ssize_t send_buf(struct port *port, void *in_buf, size_t in_count, reclaim_consumed_buffers(port); sg_init_one(sg, in_buf, in_count); - ret = virtqueue_add_buf(out_vq, sg, 1, 0, in_buf); + ret = virtqueue_add_buf(out_vq, sg, 1, 0, in_buf, GFP_ATOMIC); /* Tell Host to go! */ virtqueue_kick(out_vq); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 76fe14efb2b..6345a52194f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -370,7 +370,7 @@ static int add_recvbuf_small(struct virtnet_info *vi, gfp_t gfp) skb_to_sgvec(skb, vi->rx_sg + 1, 0, skb->len); - err = virtqueue_add_buf_gfp(vi->rvq, vi->rx_sg, 0, 2, skb, gfp); + err = virtqueue_add_buf(vi->rvq, vi->rx_sg, 0, 2, skb, gfp); if (err < 0) dev_kfree_skb(skb); @@ -415,8 +415,8 @@ static int add_recvbuf_big(struct virtnet_info *vi, gfp_t gfp) /* chain first in list head */ first->private = (unsigned long)list; - err = virtqueue_add_buf_gfp(vi->rvq, vi->rx_sg, 0, MAX_SKB_FRAGS + 2, - first, gfp); + err = virtqueue_add_buf(vi->rvq, vi->rx_sg, 0, MAX_SKB_FRAGS + 2, + first, gfp); if (err < 0) give_pages(vi, first); @@ -434,7 +434,7 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi, gfp_t gfp) sg_init_one(vi->rx_sg, page_address(page), PAGE_SIZE); - err = virtqueue_add_buf_gfp(vi->rvq, vi->rx_sg, 0, 1, page, gfp); + err = virtqueue_add_buf(vi->rvq, vi->rx_sg, 0, 1, page, gfp); if (err < 0) give_pages(vi, page); @@ -609,7 +609,7 @@ static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb) hdr->num_sg = skb_to_sgvec(skb, vi->tx_sg + 1, 0, skb->len) + 1; return virtqueue_add_buf(vi->svq, vi->tx_sg, hdr->num_sg, - 0, skb); + 0, skb, GFP_ATOMIC); } static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) @@ -767,7 +767,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, sg_set_buf(&sg[i + 1], sg_virt(s), s->length); sg_set_buf(&sg[out + in - 1], &status, sizeof(status)); - BUG_ON(virtqueue_add_buf(vi->cvq, sg, out, in, vi) < 0); + BUG_ON(virtqueue_add_buf(vi->cvq, sg, out, in, vi, GFP_ATOMIC) < 0); virtqueue_kick(vi->cvq); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index f64ff185b8b..0a6425aadf9 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -88,7 +88,7 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) init_completion(&vb->acked); /* We should always be able to add one buffer to an empty queue. */ - if (virtqueue_add_buf(vq, &sg, 1, 0, vb) < 0) + if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0) BUG(); virtqueue_kick(vq); @@ -220,7 +220,7 @@ static void stats_handle_request(struct virtio_balloon *vb) vq = vb->stats_vq; sg_init_one(&sg, vb->stats, sizeof(vb->stats)); - if (virtqueue_add_buf(vq, &sg, 1, 0, vb) < 0) + if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0) BUG(); virtqueue_kick(vq); } @@ -313,7 +313,8 @@ static int virtballoon_probe(struct virtio_device *vdev) * use it to signal us later. */ sg_init_one(&sg, vb->stats, sizeof vb->stats); - if (virtqueue_add_buf(vb->stats_vq, &sg, 1, 0, vb) < 0) + if (virtqueue_add_buf(vb->stats_vq, &sg, 1, 0, vb, GFP_KERNEL) + < 0) BUG(); virtqueue_kick(vb->stats_vq); } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index fe50486341a..6ea92a6d113 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -167,7 +167,7 @@ static int vring_add_indirect(struct vring_virtqueue *vq, } /** - * virtqueue_add_buf_gfp - expose buffer to other end + * virtqueue_add_buf - expose buffer to other end * @vq: the struct virtqueue we're talking about. * @sg: the description of the buffer(s). * @out_num: the number of sg readable by other side @@ -183,12 +183,12 @@ static int vring_add_indirect(struct vring_virtqueue *vq, * positive return values as "available": indirect buffers mean that * we can put an entire sg[] array inside a single queue entry. */ -int virtqueue_add_buf_gfp(struct virtqueue *_vq, - struct scatterlist sg[], - unsigned int out, - unsigned int in, - void *data, - gfp_t gfp) +int virtqueue_add_buf(struct virtqueue *_vq, + struct scatterlist sg[], + unsigned int out, + unsigned int in, + void *data, + gfp_t gfp) { struct vring_virtqueue *vq = to_vvq(_vq); unsigned int i, avail, uninitialized_var(prev); @@ -259,13 +259,13 @@ add_head: return vq->num_free; } -EXPORT_SYMBOL_GPL(virtqueue_add_buf_gfp); +EXPORT_SYMBOL_GPL(virtqueue_add_buf); /** * virtqueue_kick - update after add_buf * @vq: the struct virtqueue * - * After one or more virtqueue_add_buf_gfp calls, invoke this to kick + * After one or more virtqueue_add_buf calls, invoke this to kick * the other side. * * Caller must ensure we don't call this with other virtqueue @@ -341,7 +341,7 @@ static inline bool more_used(const struct vring_virtqueue *vq) * operations at the same time (except where noted). * * Returns NULL if there are no used buffers, or the "data" token - * handed to virtqueue_add_buf_gfp(). + * handed to virtqueue_add_buf(). */ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) { @@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed); * virtqueue_detach_unused_buf - detach first unused buffer * @vq: the struct virtqueue we're talking about. * - * Returns NULL or the "data" token handed to virtqueue_add_buf_gfp(). + * Returns NULL or the "data" token handed to virtqueue_add_buf(). * This is not valid on an active queue; it is useful only for device * shutdown. */ diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 73ad7243128..ec1706e7df5 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -25,21 +25,12 @@ struct virtqueue { void *priv; }; -int virtqueue_add_buf_gfp(struct virtqueue *vq, - struct scatterlist sg[], - unsigned int out_num, - unsigned int in_num, - void *data, - gfp_t gfp); - -static inline int virtqueue_add_buf(struct virtqueue *vq, - struct scatterlist sg[], - unsigned int out_num, - unsigned int in_num, - void *data) -{ - return virtqueue_add_buf_gfp(vq, sg, out_num, in_num, data, GFP_ATOMIC); -} +int virtqueue_add_buf(struct virtqueue *vq, + struct scatterlist sg[], + unsigned int out_num, + unsigned int in_num, + void *data, + gfp_t gfp); void virtqueue_kick(struct virtqueue *vq); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 330421e5471..3d432068f62 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -272,7 +272,8 @@ req_retry: in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity); - err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc); + err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc, + GFP_ATOMIC); if (err < 0) { if (err == -ENOSPC) { chan->ring_bufs_avail = 0; @@ -414,7 +415,8 @@ req_retry_pinned: in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM, in_pages, in_nr_pages, uidata, inlen); - err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc); + err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc, + GFP_ATOMIC); if (err < 0) { if (err == -ENOSPC) { chan->ring_bufs_avail = 0; diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index 953db2abf6b..b4fbc91c41b 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -186,21 +186,12 @@ struct virtqueue { #endif /* Interfaces exported by virtio_ring. */ -int virtqueue_add_buf_gfp(struct virtqueue *vq, - struct scatterlist sg[], - unsigned int out_num, - unsigned int in_num, - void *data, - gfp_t gfp); - -static inline int virtqueue_add_buf(struct virtqueue *vq, - struct scatterlist sg[], - unsigned int out_num, - unsigned int in_num, - void *data) -{ - return virtqueue_add_buf_gfp(vq, sg, out_num, in_num, data, GFP_ATOMIC); -} +int virtqueue_add_buf(struct virtqueue *vq, + struct scatterlist sg[], + unsigned int out_num, + unsigned int in_num, + void *data, + gfp_t gfp); void virtqueue_kick(struct virtqueue *vq); diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index 0740284396c..6bf95f99536 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -161,7 +161,8 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq, int bufs) if (started < bufs) { sg_init_one(&sl, dev->buf, dev->buf_size); r = virtqueue_add_buf(vq->vq, &sl, 1, 0, - dev->buf + started); + dev->buf + started, + GFP_ATOMIC); if (likely(r >= 0)) { ++started; virtqueue_kick(vq->vq); -- cgit v1.2.3-18-g5258 From 41f0377f73039ca6fe97a469d1941a89cd9757f1 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 12 Jan 2012 15:44:43 +1030 Subject: virtio: support unlocked queue kick Based on patch by Christoph for virtio_blk speedup: Split virtqueue_kick to be able to do the actual notification outside the lock protecting the virtqueue. This patch was originally done by Stefan Hajnoczi, but I can't find the original one anymore and had to recreated it from memory. Pointers to the original or corrections for the commit message are welcome. Stefan's patch was here: https://github.com/stefanha/linux/commit/a6d06644e3a58e57a774e77d7dc34c4a5a2e7496 http://www.spinics.net/lists/linux-virtualization/msg14616.html Third time's the charm! Signed-off-by: Rusty Russell --- drivers/virtio/virtio_ring.c | 60 +++++++++++++++++++++++++++++++++++--------- include/linux/virtio.h | 4 +++ 2 files changed, 52 insertions(+), 12 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 6ea92a6d113..c56bbe79924 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -262,19 +262,22 @@ add_head: EXPORT_SYMBOL_GPL(virtqueue_add_buf); /** - * virtqueue_kick - update after add_buf + * virtqueue_kick_prepare - first half of split virtqueue_kick call. * @vq: the struct virtqueue * - * After one or more virtqueue_add_buf calls, invoke this to kick - * the other side. + * Instead of virtqueue_kick(), you can do: + * if (virtqueue_kick_prepare(vq)) + * virtqueue_notify(vq); * - * Caller must ensure we don't call this with other virtqueue - * operations at the same time (except where noted). + * This is sometimes useful because the virtqueue_kick_prepare() needs + * to be serialized, but the actual virtqueue_notify() call does not. */ -void virtqueue_kick(struct virtqueue *_vq) +bool virtqueue_kick_prepare(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 new, old; + bool needs_kick; + START_USE(vq); /* Descriptors and available array need to be set before we expose the * new available array entries. */ @@ -287,13 +290,46 @@ void virtqueue_kick(struct virtqueue *_vq) /* Need to update avail index before checking if we should notify */ virtio_mb(vq); - if (vq->event ? - vring_need_event(vring_avail_event(&vq->vring), new, old) : - !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY)) - /* Prod other side to tell it about changes. */ - vq->notify(&vq->vq); - + if (vq->event) { + needs_kick = vring_need_event(vring_avail_event(&vq->vring), + new, old); + } else { + needs_kick = !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY); + } END_USE(vq); + return needs_kick; +} +EXPORT_SYMBOL_GPL(virtqueue_kick_prepare); + +/** + * virtqueue_notify - second half of split virtqueue_kick call. + * @vq: the struct virtqueue + * + * This does not need to be serialized. + */ +void virtqueue_notify(struct virtqueue *_vq) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + + /* Prod other side to tell it about changes. */ + vq->notify(_vq); +} +EXPORT_SYMBOL_GPL(virtqueue_notify); + +/** + * virtqueue_kick - update after add_buf + * @vq: the struct virtqueue + * + * After one or more virtqueue_add_buf calls, invoke this to kick + * the other side. + * + * Caller must ensure we don't call this with other virtqueue + * operations at the same time (except where noted). + */ +void virtqueue_kick(struct virtqueue *vq) +{ + if (virtqueue_kick_prepare(vq)) + virtqueue_notify(vq); } EXPORT_SYMBOL_GPL(virtqueue_kick); diff --git a/include/linux/virtio.h b/include/linux/virtio.h index ec1706e7df5..31fe3a62874 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -34,6 +34,10 @@ int virtqueue_add_buf(struct virtqueue *vq, void virtqueue_kick(struct virtqueue *vq); +bool virtqueue_kick_prepare(struct virtqueue *vq); + +void virtqueue_notify(struct virtqueue *vq); + void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len); void virtqueue_disable_cb(struct virtqueue *vq); -- cgit v1.2.3-18-g5258 From 3b720b8c865098c49c1570b6b5c7832bcfa6e6c2 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 12 Jan 2012 15:44:43 +1030 Subject: virtio: avoid modulus operation. Since we know vq->vring.num is a power of 2, modulus is lazy (it's asserted in vring_new_virtqueue()). Signed-off-by: Rusty Russell --- drivers/virtio/virtio_ring.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index c56bbe79924..99dc9480f3f 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -250,8 +250,8 @@ add_head: vq->data[head] = data; /* Put entry in available array (but don't update avail->idx until they - * do sync). FIXME: avoid modulus here? */ - avail = (vq->vring.avail->idx + vq->num_added++) % vq->vring.num; + * do sync). */ + avail = ((vq->vring.avail->idx + vq->num_added++) & (vq->vring.num-1)); vq->vring.avail->ring[avail] = head; pr_debug("Added buffer head %i to %p\n", head, vq); @@ -384,6 +384,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) struct vring_virtqueue *vq = to_vvq(_vq); void *ret; unsigned int i; + u16 last_used; START_USE(vq); @@ -401,8 +402,9 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) /* Only get used array entries after they have been exposed by host. */ virtio_rmb(vq); - i = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].id; - *len = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].len; + last_used = (vq->last_used_idx & (vq->vring.num - 1)); + i = vq->vring.used->ring[last_used].id; + *len = vq->vring.used->ring[last_used].len; if (unlikely(i >= vq->vring.num)) { BAD_RING(vq, "id %u out of range\n", i); -- cgit v1.2.3-18-g5258 From ee7cd8981e15bcb365fc762afe3fc47b8242f630 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 12 Jan 2012 15:44:43 +1030 Subject: virtio: expose added descriptors immediately. A virtio driver does virtqueue_add_buf() multiple times before finally calling virtqueue_kick(); previously we only exposed the added buffers in the virtqueue_kick() call. This means we don't need a memory barrier in virtqueue_add_buf(), but it reduces concurrency as the device (ie. host) can't see the buffers until the kick. In the unusual (but now possible) case where a driver does add_buf() and get_buf() without doing a kick, we do need to insert one before our counter wraps. Otherwise we could wrap num_added, and later on not realize that we have passed the marker where we should have kicked. Signed-off-by: Rusty Russell --- drivers/virtio/virtio_ring.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 99dc9480f3f..36bb6a61372 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -251,9 +251,20 @@ add_head: /* Put entry in available array (but don't update avail->idx until they * do sync). */ - avail = ((vq->vring.avail->idx + vq->num_added++) & (vq->vring.num-1)); + avail = (vq->vring.avail->idx & (vq->vring.num-1)); vq->vring.avail->ring[avail] = head; + /* Descriptors and available array need to be set before we expose the + * new available array entries. */ + virtio_wmb(vq); + vq->vring.avail->idx++; + vq->num_added++; + + /* This is very unlikely, but theoretically possible. Kick + * just in case. */ + if (unlikely(vq->num_added == (1 << 16) - 1)) + virtqueue_kick(_vq); + pr_debug("Added buffer head %i to %p\n", head, vq); END_USE(vq); @@ -283,13 +294,10 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq) * new available array entries. */ virtio_wmb(vq); - old = vq->vring.avail->idx; - new = vq->vring.avail->idx = old + vq->num_added; + old = vq->vring.avail->idx - vq->num_added; + new = vq->vring.avail->idx; vq->num_added = 0; - /* Need to update avail index before checking if we should notify */ - virtio_mb(vq); - if (vq->event) { needs_kick = vring_need_event(vring_avail_event(&vq->vring), new, old); -- cgit v1.2.3-18-g5258 From e93300b1afc7cd4fe1e741ceaf06714d060e88b8 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 12 Jan 2012 15:44:43 +1030 Subject: virtio: add debugging if driver doesn't kick. Under the existing #ifdef DEBUG, check that they don't have more than 1/10 of a second between an add_buf() and a virtqueue_notify()/virtqueue_kick_prepare() call. We could get false positives on a really busy system, but good for development. Signed-off-by: Rusty Russell --- drivers/virtio/virtio_ring.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 36bb6a61372..79e1b292c03 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -22,6 +22,7 @@ #include #include #include +#include /* virtio guest is communicating with a virtual "device" that actually runs on * a host processor. Memory barriers are used to control SMP effects. */ @@ -108,6 +109,10 @@ struct vring_virtqueue #ifdef DEBUG /* They're supposed to lock for us. */ unsigned int in_use; + + /* Figure out if their kicks are too delayed. */ + bool last_add_time_valid; + ktime_t last_add_time; #endif /* Tokens for callbacks. */ @@ -198,6 +203,19 @@ int virtqueue_add_buf(struct virtqueue *_vq, BUG_ON(data == NULL); +#ifdef DEBUG + { + ktime_t now = ktime_get(); + + /* No kick or get, with .1 second between? Warn. */ + if (vq->last_add_time_valid) + WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time)) + > 100); + vq->last_add_time = now; + vq->last_add_time_valid = true; + } +#endif + /* If the host supports indirect descriptor tables, and we have multiple * buffers, then go indirect. FIXME: tune this threshold */ if (vq->indirect && (out + in) > 1 && vq->num_free) { @@ -298,6 +316,14 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq) new = vq->vring.avail->idx; vq->num_added = 0; +#ifdef DEBUG + if (vq->last_add_time_valid) { + WARN_ON(ktime_to_ms(ktime_sub(ktime_get(), + vq->last_add_time)) > 100); + } + vq->last_add_time_valid = false; +#endif + if (vq->event) { needs_kick = vring_need_event(vring_avail_event(&vq->vring), new, old); @@ -435,6 +461,10 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) virtio_mb(vq); } +#ifdef DEBUG + vq->last_add_time_valid = false; +#endif + END_USE(vq); return ret; } @@ -620,6 +650,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int num, list_add_tail(&vq->vq.list, &vdev->vqs); #ifdef DEBUG vq->in_use = false; + vq->last_add_time_valid = false; #endif vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC); -- cgit v1.2.3-18-g5258 From 4678d6f970c2f7c0cbfefc0cc666432d153b321b Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 12 Jan 2012 15:44:44 +1030 Subject: virtio_blk: fix config handler race Fix a theoretical race related to config work handler: a config interrupt might happen after we flush config work but before we reset the device. It will then cause the config work to run during or after reset. Two problems with this: - if this runs after device is gone we will get use after free - access of config while reset is in progress is racy (as layout is changing). As a solution 1. flush after reset when we know there will be no more interrupts 2. add a flag to disable config access before reset Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- drivers/block/virtio_blk.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index a345e40e1bc..ba73661fb9f 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -36,6 +37,12 @@ struct virtio_blk /* Process context for config space updates */ struct work_struct config_work; + /* Lock for config space updates */ + struct mutex config_lock; + + /* enable config space updates */ + bool config_enable; + /* What host tells us, plus 2 for header & tailer. */ unsigned int sg_elems; @@ -318,6 +325,10 @@ static void virtblk_config_changed_work(struct work_struct *work) char cap_str_2[10], cap_str_10[10]; u64 capacity, size; + mutex_lock(&vblk->config_lock); + if (!vblk->config_enable) + goto done; + /* Host must always specify the capacity. */ vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity), &capacity, sizeof(capacity)); @@ -340,6 +351,8 @@ static void virtblk_config_changed_work(struct work_struct *work) cap_str_10, cap_str_2); set_capacity(vblk->disk, capacity); +done: + mutex_unlock(&vblk->config_lock); } static void virtblk_config_changed(struct virtio_device *vdev) @@ -388,7 +401,9 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) vblk->vdev = vdev; vblk->sg_elems = sg_elems; sg_init_table(vblk->sg, vblk->sg_elems); + mutex_init(&vblk->config_lock); INIT_WORK(&vblk->config_work, virtblk_config_changed_work); + vblk->config_enable = true; /* We expect one virtqueue, for output. */ vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests"); @@ -542,7 +557,10 @@ static void __devexit virtblk_remove(struct virtio_device *vdev) struct virtio_blk *vblk = vdev->priv; int index = vblk->index; - flush_work(&vblk->config_work); + /* Prevent config work handler from accessing the device. */ + mutex_lock(&vblk->config_lock); + vblk->config_enable = false; + mutex_unlock(&vblk->config_lock); /* Nothing should be pending. */ BUG_ON(!list_empty(&vblk->reqs)); @@ -550,6 +568,8 @@ static void __devexit virtblk_remove(struct virtio_device *vdev) /* Stop all the virtqueues. */ vdev->config->reset(vdev); + flush_work(&vblk->config_work); + del_gendisk(vblk->disk); blk_cleanup_queue(vblk->disk->queue); put_disk(vblk->disk); -- cgit v1.2.3-18-g5258 From d077536386595309060dda57e7b7474c501a589b Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:25 +0530 Subject: virtio: pci: switch to new PM API The older PM API doesn't have a way to get notifications on hibernate events. Switch to the newer one that gives us those notifications. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/virtio/virtio_pci.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c index 688b42d28da..7f9ac1af7cf 100644 --- a/drivers/virtio/virtio_pci.c +++ b/drivers/virtio/virtio_pci.c @@ -716,19 +716,28 @@ static void __devexit virtio_pci_remove(struct pci_dev *pci_dev) } #ifdef CONFIG_PM -static int virtio_pci_suspend(struct pci_dev *pci_dev, pm_message_t state) +static int virtio_pci_suspend(struct device *dev) { + struct pci_dev *pci_dev = to_pci_dev(dev); + pci_save_state(pci_dev); pci_set_power_state(pci_dev, PCI_D3hot); return 0; } -static int virtio_pci_resume(struct pci_dev *pci_dev) +static int virtio_pci_resume(struct device *dev) { + struct pci_dev *pci_dev = to_pci_dev(dev); + pci_restore_state(pci_dev); pci_set_power_state(pci_dev, PCI_D0); return 0; } + +static const struct dev_pm_ops virtio_pci_pm_ops = { + .suspend = virtio_pci_suspend, + .resume = virtio_pci_resume, +}; #endif static struct pci_driver virtio_pci_driver = { @@ -737,8 +746,7 @@ static struct pci_driver virtio_pci_driver = { .probe = virtio_pci_probe, .remove = __devexit_p(virtio_pci_remove), #ifdef CONFIG_PM - .suspend = virtio_pci_suspend, - .resume = virtio_pci_resume, + .driver.pm = &virtio_pci_pm_ops, #endif }; -- cgit v1.2.3-18-g5258 From f0fe6f11503fa9880867554350ac5d3092c47251 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:26 +0530 Subject: virtio: pci: add PM notification handlers for restore, freeze, thaw, poweroff Handle thaw, restore and freeze notifications from the PM core. Expose these to individual virtio drivers that can quiesce and resume vq operations. For drivers not implementing the thaw() method, use the restore method instead. These functions also save device-specific data so that the device can be put in pre-suspend state after resume, and disable and enable the PCI device in the freeze and resume functions, respectively. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/virtio/virtio_pci.c | 94 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/virtio.h | 5 +++ 2 files changed, 97 insertions(+), 2 deletions(-) diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c index 7f9ac1af7cf..635e1efb379 100644 --- a/drivers/virtio/virtio_pci.c +++ b/drivers/virtio/virtio_pci.c @@ -55,6 +55,10 @@ struct virtio_pci_device unsigned msix_vectors; /* Vectors allocated, excluding per-vq vectors if any */ unsigned msix_used_vectors; + + /* Status saved during hibernate/restore */ + u8 saved_status; + /* Whether we have vector per vq */ bool per_vq_vectors; }; @@ -734,9 +738,95 @@ static int virtio_pci_resume(struct device *dev) return 0; } +static int virtio_pci_freeze(struct device *dev) +{ + struct pci_dev *pci_dev = to_pci_dev(dev); + struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + struct virtio_driver *drv; + int ret; + + drv = container_of(vp_dev->vdev.dev.driver, + struct virtio_driver, driver); + + ret = 0; + vp_dev->saved_status = vp_get_status(&vp_dev->vdev); + if (drv && drv->freeze) + ret = drv->freeze(&vp_dev->vdev); + + if (!ret) + pci_disable_device(pci_dev); + return ret; +} + +static int restore_common(struct device *dev) +{ + struct pci_dev *pci_dev = to_pci_dev(dev); + struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + int ret; + + ret = pci_enable_device(pci_dev); + if (ret) + return ret; + pci_set_master(pci_dev); + vp_finalize_features(&vp_dev->vdev); + + return ret; +} + +static int virtio_pci_thaw(struct device *dev) +{ + struct pci_dev *pci_dev = to_pci_dev(dev); + struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + struct virtio_driver *drv; + int ret; + + ret = restore_common(dev); + if (ret) + return ret; + + drv = container_of(vp_dev->vdev.dev.driver, + struct virtio_driver, driver); + + if (drv && drv->thaw) + ret = drv->thaw(&vp_dev->vdev); + else if (drv && drv->restore) + ret = drv->restore(&vp_dev->vdev); + + /* Finally, tell the device we're all set */ + if (!ret) + vp_set_status(&vp_dev->vdev, vp_dev->saved_status); + + return ret; +} + +static int virtio_pci_restore(struct device *dev) +{ + struct pci_dev *pci_dev = to_pci_dev(dev); + struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + struct virtio_driver *drv; + int ret; + + drv = container_of(vp_dev->vdev.dev.driver, + struct virtio_driver, driver); + + ret = restore_common(dev); + if (!ret && drv && drv->restore) + ret = drv->restore(&vp_dev->vdev); + + /* Finally, tell the device we're all set */ + if (!ret) + vp_set_status(&vp_dev->vdev, vp_dev->saved_status); + + return ret; +} + static const struct dev_pm_ops virtio_pci_pm_ops = { - .suspend = virtio_pci_suspend, - .resume = virtio_pci_resume, + .suspend = virtio_pci_suspend, + .resume = virtio_pci_resume, + .freeze = virtio_pci_freeze, + .thaw = virtio_pci_thaw, + .restore = virtio_pci_restore, + .poweroff = virtio_pci_suspend, }; #endif diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 31fe3a62874..d0018d27c28 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -94,6 +94,11 @@ struct virtio_driver { int (*probe)(struct virtio_device *dev); void (*remove)(struct virtio_device *dev); void (*config_changed)(struct virtio_device *dev); +#ifdef CONFIG_PM + int (*freeze)(struct virtio_device *dev); + int (*thaw)(struct virtio_device *dev); + int (*restore)(struct virtio_device *dev); +#endif }; int register_virtio_driver(struct virtio_driver *drv); -- cgit v1.2.3-18-g5258 From a0e2dbfc223028b72a1c193f94fcd3f67253ba4a Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:27 +0530 Subject: virtio: console: Move vq and vq buf removal into separate functions This common code will be shared with the PM freeze function. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/char/virtio_console.c | 68 +++++++++++++++++++++++++------------------ 1 file changed, 40 insertions(+), 28 deletions(-) diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index d1ae1492ee7..9681ffd7990 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1271,6 +1271,20 @@ static void remove_port(struct kref *kref) kfree(port); } +static void remove_port_data(struct port *port) +{ + struct port_buffer *buf; + + /* Remove unused data this port might have received. */ + discard_port_data(port); + + reclaim_consumed_buffers(port); + + /* Remove buffers we queued up for the Host to send us data in. */ + while ((buf = virtqueue_detach_unused_buf(port->in_vq))) + free_buf(buf); +} + /* * Port got unplugged. Remove port from portdev's list and drop the * kref reference. If no userspace has this port opened, it will @@ -1278,8 +1292,6 @@ static void remove_port(struct kref *kref) */ static void unplug_port(struct port *port) { - struct port_buffer *buf; - spin_lock_irq(&port->portdev->ports_lock); list_del(&port->list); spin_unlock_irq(&port->portdev->ports_lock); @@ -1300,14 +1312,7 @@ static void unplug_port(struct port *port) hvc_remove(port->cons.hvc); } - /* Remove unused data this port might have received. */ - discard_port_data(port); - - reclaim_consumed_buffers(port); - - /* Remove buffers we queued up for the Host to send us data in. */ - while ((buf = virtqueue_detach_unused_buf(port->in_vq))) - free_buf(buf); + remove_port_data(port); /* * We should just assume the device itself has gone off -- @@ -1659,6 +1664,28 @@ static const struct file_operations portdev_fops = { .owner = THIS_MODULE, }; +static void remove_vqs(struct ports_device *portdev) +{ + portdev->vdev->config->del_vqs(portdev->vdev); + kfree(portdev->in_vqs); + kfree(portdev->out_vqs); +} + +static void remove_controlq_data(struct ports_device *portdev) +{ + struct port_buffer *buf; + unsigned int len; + + if (!use_multiport(portdev)) + return; + + while ((buf = virtqueue_get_buf(portdev->c_ivq, &len))) + free_buf(buf); + + while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq))) + free_buf(buf); +} + /* * Once we're further in boot, we get probed like any other virtio * device. @@ -1764,9 +1791,7 @@ free_vqs: /* The host might want to notify mgmt sw about device add failure */ __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID, VIRTIO_CONSOLE_DEVICE_READY, 0); - vdev->config->del_vqs(vdev); - kfree(portdev->in_vqs); - kfree(portdev->out_vqs); + remove_vqs(portdev); free_chrdev: unregister_chrdev(portdev->chr_major, "virtio-portsdev"); free: @@ -1804,21 +1829,8 @@ static void virtcons_remove(struct virtio_device *vdev) * have to just stop using the port, as the vqs are going * away. */ - if (use_multiport(portdev)) { - struct port_buffer *buf; - unsigned int len; - - while ((buf = virtqueue_get_buf(portdev->c_ivq, &len))) - free_buf(buf); - - while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq))) - free_buf(buf); - } - - vdev->config->del_vqs(vdev); - kfree(portdev->in_vqs); - kfree(portdev->out_vqs); - + remove_controlq_data(portdev); + remove_vqs(portdev); kfree(portdev); } -- cgit v1.2.3-18-g5258 From 2b8f41d846990c3c1c8addbaed2cf53c3ef91d25 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:28 +0530 Subject: virtio: console: Add freeze and restore handlers to support S4 Remove all vqs and associated buffers in the freeze callback which prepares us to go into hibernation state. On restore, re-create all the vqs and populate the input vqs with buffers to get to the pre-hibernate state. Note: Any outstanding unconsumed buffers are discarded; which means there's a possibility of data loss in case the host or the guest didn't consume any data already present in the vqs. This can be addressed in a later patch series, perhaps in virtio common code. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/char/virtio_console.c | 58 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 9681ffd7990..614b84d38d7 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1844,6 +1844,60 @@ static unsigned int features[] = { VIRTIO_CONSOLE_F_MULTIPORT, }; +#ifdef CONFIG_PM +static int virtcons_freeze(struct virtio_device *vdev) +{ + struct ports_device *portdev; + struct port *port; + + portdev = vdev->priv; + + vdev->config->reset(vdev); + + cancel_work_sync(&portdev->control_work); + remove_controlq_data(portdev); + + list_for_each_entry(port, &portdev->ports, list) { + /* + * We'll ask the host later if the new invocation has + * the port opened or closed. + */ + port->host_connected = false; + remove_port_data(port); + } + remove_vqs(portdev); + + return 0; +} + +static int virtcons_restore(struct virtio_device *vdev) +{ + struct ports_device *portdev; + struct port *port; + int ret; + + portdev = vdev->priv; + + ret = init_vqs(portdev); + if (ret) + return ret; + + if (use_multiport(portdev)) + fill_queue(portdev->c_ivq, &portdev->cvq_lock); + + list_for_each_entry(port, &portdev->ports, list) { + port->in_vq = portdev->in_vqs[port->id]; + port->out_vq = portdev->out_vqs[port->id]; + + fill_queue(port->in_vq, &port->inbuf_lock); + + /* Get port open/close status on the host */ + send_control_msg(port, VIRTIO_CONSOLE_PORT_READY, 1); + } + return 0; +} +#endif + static struct virtio_driver virtio_console = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), @@ -1853,6 +1907,10 @@ static struct virtio_driver virtio_console = { .probe = virtcons_probe, .remove = virtcons_remove, .config_changed = config_intr, +#ifdef CONFIG_PM + .freeze = virtcons_freeze, + .restore = virtcons_restore, +#endif }; static int __init init(void) -- cgit v1.2.3-18-g5258 From c743d09dbd018dd6345519fb3264b16bdaa41746 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Fri, 6 Jan 2012 16:19:08 +0530 Subject: virtio: console: Disable callbacks for virtqueues at start of S4 freeze To ensure we don't receive any more interrupts from the host after we enter the freeze function, disable all vq interrupts. There wasn't any problem seen due to this in tests, but applying this patch makes the freeze case more robust. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/char/virtio_console.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 614b84d38d7..b58b5618706 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1854,10 +1854,18 @@ static int virtcons_freeze(struct virtio_device *vdev) vdev->config->reset(vdev); + virtqueue_disable_cb(portdev->c_ivq); cancel_work_sync(&portdev->control_work); + /* + * Once more: if control_work_handler() was running, it would + * enable the cb as the last step. + */ + virtqueue_disable_cb(portdev->c_ivq); remove_controlq_data(portdev); list_for_each_entry(port, &portdev->ports, list) { + virtqueue_disable_cb(port->in_vq); + virtqueue_disable_cb(port->out_vq); /* * We'll ask the host later if the new invocation has * the port opened or closed. -- cgit v1.2.3-18-g5258 From 6abd6e5a4404056e28be04958a57d0286883161a Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:29 +0530 Subject: virtio: blk: Move vq initialization to separate function The probe and PM restore functions will share this code. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/block/virtio_blk.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index ba73661fb9f..e8af52355bf 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -362,6 +362,18 @@ static void virtblk_config_changed(struct virtio_device *vdev) queue_work(virtblk_wq, &vblk->config_work); } +static int init_vq(struct virtio_blk *vblk) +{ + int err = 0; + + /* We expect one virtqueue, for output. */ + vblk->vq = virtio_find_single_vq(vblk->vdev, blk_done, "requests"); + if (IS_ERR(vblk->vq)) + err = PTR_ERR(vblk->vq); + + return err; +} + static int __devinit virtblk_probe(struct virtio_device *vdev) { struct virtio_blk *vblk; @@ -405,12 +417,9 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) INIT_WORK(&vblk->config_work, virtblk_config_changed_work); vblk->config_enable = true; - /* We expect one virtqueue, for output. */ - vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests"); - if (IS_ERR(vblk->vq)) { - err = PTR_ERR(vblk->vq); + err = init_vq(vblk); + if (err) goto out_free_vblk; - } vblk->pool = mempool_create_kmalloc_pool(1,sizeof(struct virtblk_req)); if (!vblk->pool) { -- cgit v1.2.3-18-g5258 From f8fb5bc23a50a5398aa31a4e8c6dbbef53d2dec6 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:30 +0530 Subject: virtio: blk: Add freeze, restore handlers to support S4 Delete the vq and flush any pending requests from the block queue on the freeze callback to prepare for hibernation. Re-create the vq in the restore callback to resume normal function. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/block/virtio_blk.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index e8af52355bf..ffd5ca91929 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -588,6 +588,46 @@ static void __devexit virtblk_remove(struct virtio_device *vdev) ida_simple_remove(&vd_index_ida, index); } +#ifdef CONFIG_PM +static int virtblk_freeze(struct virtio_device *vdev) +{ + struct virtio_blk *vblk = vdev->priv; + + /* Ensure we don't receive any more interrupts */ + vdev->config->reset(vdev); + + /* Prevent config work handler from accessing the device. */ + mutex_lock(&vblk->config_lock); + vblk->config_enable = false; + mutex_unlock(&vblk->config_lock); + + flush_work(&vblk->config_work); + + spin_lock_irq(vblk->disk->queue->queue_lock); + blk_stop_queue(vblk->disk->queue); + spin_unlock_irq(vblk->disk->queue->queue_lock); + blk_sync_queue(vblk->disk->queue); + + vdev->config->del_vqs(vdev); + return 0; +} + +static int virtblk_restore(struct virtio_device *vdev) +{ + struct virtio_blk *vblk = vdev->priv; + int ret; + + vblk->config_enable = true; + ret = init_vq(vdev->priv); + if (!ret) { + spin_lock_irq(vblk->disk->queue->queue_lock); + blk_start_queue(vblk->disk->queue); + spin_unlock_irq(vblk->disk->queue->queue_lock); + } + return ret; +} +#endif + static const struct virtio_device_id id_table[] = { { VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID }, { 0 }, @@ -613,6 +653,10 @@ static struct virtio_driver __refdata virtio_blk = { .probe = virtblk_probe, .remove = __devexit_p(virtblk_remove), .config_changed = virtblk_config_changed, +#ifdef CONFIG_PM + .freeze = virtblk_freeze, + .restore = virtblk_restore, +#endif }; static int __init init(void) -- cgit v1.2.3-18-g5258 From 3f9c10b0d478a3b7c3dde555edae79fecef496e5 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:31 +0530 Subject: virtio: net: Move vq initialization into separate function The probe and PM restore functions will share this code. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/net/virtio_net.c | 47 ++++++++++++++++++++++++++++------------------- 1 file changed, 28 insertions(+), 19 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 6345a52194f..70a9c4b1252 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -985,15 +985,38 @@ static void virtnet_config_changed(struct virtio_device *vdev) virtnet_update_status(vi); } +static int init_vqs(struct virtnet_info *vi) +{ + struct virtqueue *vqs[3]; + vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL}; + const char *names[] = { "input", "output", "control" }; + int nvqs, err; + + /* We expect two virtqueues, receive then send, + * and optionally control. */ + nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2; + + err = vi->vdev->config->find_vqs(vi->vdev, nvqs, vqs, callbacks, names); + if (err) + return err; + + vi->rvq = vqs[0]; + vi->svq = vqs[1]; + + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) { + vi->cvq = vqs[2]; + + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN)) + vi->dev->features |= NETIF_F_HW_VLAN_FILTER; + } + return 0; +} + static int virtnet_probe(struct virtio_device *vdev) { int err; struct net_device *dev; struct virtnet_info *vi; - struct virtqueue *vqs[3]; - vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL}; - const char *names[] = { "input", "output", "control" }; - int nvqs; /* Allocate ourselves a network device with room for our info */ dev = alloc_etherdev(sizeof(struct virtnet_info)); @@ -1065,24 +1088,10 @@ static int virtnet_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) vi->mergeable_rx_bufs = true; - /* We expect two virtqueues, receive then send, - * and optionally control. */ - nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2; - - err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names); + err = init_vqs(vi); if (err) goto free_stats; - vi->rvq = vqs[0]; - vi->svq = vqs[1]; - - if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) { - vi->cvq = vqs[2]; - - if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN)) - dev->features |= NETIF_F_HW_VLAN_FILTER; - } - err = register_netdev(dev); if (err) { pr_debug("virtio_net: registering device failed\n"); -- cgit v1.2.3-18-g5258 From 04486ed019d249249c00546704af12498a432c15 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:32 +0530 Subject: virtio: net: Move vq and vq buf removal into separate function The remove and PM freeze functions will share this code. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/net/virtio_net.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 70a9c4b1252..59109c1b6b8 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1153,22 +1153,26 @@ static void free_unused_bufs(struct virtnet_info *vi) BUG_ON(vi->num != 0); } -static void __devexit virtnet_remove(struct virtio_device *vdev) +static void remove_vq_common(struct virtnet_info *vi) { - struct virtnet_info *vi = vdev->priv; - - /* Stop all the virtqueues. */ - vdev->config->reset(vdev); - - unregister_netdev(vi->dev); + vi->vdev->config->reset(vi->vdev); /* Free unused buffers in both send and recv, if any. */ free_unused_bufs(vi); - vdev->config->del_vqs(vi->vdev); + vi->vdev->config->del_vqs(vi->vdev); while (vi->pages) __free_pages(get_a_page(vi, GFP_KERNEL), 0); +} + +static void __devexit virtnet_remove(struct virtio_device *vdev) +{ + struct virtnet_info *vi = vdev->priv; + + unregister_netdev(vi->dev); + + remove_vq_common(vi); free_percpu(vi->stats); free_netdev(vi->dev); -- cgit v1.2.3-18-g5258 From 0741bcb5584f9e2390ae6261573c4de8314999f2 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:33 +0530 Subject: virtio: net: Add freeze, restore handlers to support S4 Remove all the vqs, disable napi and detach from the netdev on hibernation. Re-create vqs after restoring from a hibernated image, re-enable napi and re-attach the netdev. This keeps networking working across hibernation. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/net/virtio_net.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 59109c1b6b8..4880aa8b4c2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1178,6 +1178,48 @@ static void __devexit virtnet_remove(struct virtio_device *vdev) free_netdev(vi->dev); } +#ifdef CONFIG_PM +static int virtnet_freeze(struct virtio_device *vdev) +{ + struct virtnet_info *vi = vdev->priv; + + virtqueue_disable_cb(vi->rvq); + virtqueue_disable_cb(vi->svq); + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) + virtqueue_disable_cb(vi->cvq); + + netif_device_detach(vi->dev); + cancel_delayed_work_sync(&vi->refill); + + if (netif_running(vi->dev)) + napi_disable(&vi->napi); + + remove_vq_common(vi); + + return 0; +} + +static int virtnet_restore(struct virtio_device *vdev) +{ + struct virtnet_info *vi = vdev->priv; + int err; + + err = init_vqs(vi); + if (err) + return err; + + if (netif_running(vi->dev)) + virtnet_napi_enable(vi); + + netif_device_attach(vi->dev); + + if (!try_fill_recv(vi, GFP_KERNEL)) + queue_delayed_work(system_nrt_wq, &vi->refill, 0); + + return 0; +} +#endif + static struct virtio_device_id id_table[] = { { VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID }, { 0 }, @@ -1202,6 +1244,10 @@ static struct virtio_driver virtio_net_driver = { .probe = virtnet_probe, .remove = __devexit_p(virtnet_remove), .config_changed = virtnet_config_changed, +#ifdef CONFIG_PM + .freeze = virtnet_freeze, + .restore = virtnet_restore, +#endif }; static int __init init(void) -- cgit v1.2.3-18-g5258 From be91c33dd15eff6b0dffc60cee4c8042e75493d2 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:34 +0530 Subject: virtio: balloon: Move vq initialization into separate function The probe and PM restore functions will share this code. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/virtio/virtio_balloon.c | 48 +++++++++++++++++++++++++---------------- 1 file changed, 30 insertions(+), 18 deletions(-) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 0a6425aadf9..3368cb6ef19 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -275,32 +275,21 @@ static int balloon(void *_vballoon) return 0; } -static int virtballoon_probe(struct virtio_device *vdev) +static int init_vqs(struct virtio_balloon *vb) { - struct virtio_balloon *vb; struct virtqueue *vqs[3]; vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request }; const char *names[] = { "inflate", "deflate", "stats" }; int err, nvqs; - vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL); - if (!vb) { - err = -ENOMEM; - goto out; - } - - INIT_LIST_HEAD(&vb->pages); - vb->num_pages = 0; - init_waitqueue_head(&vb->config_change); - vb->vdev = vdev; - vb->need_stats_update = 0; - - /* We expect two virtqueues: inflate and deflate, - * and optionally stat. */ + /* + * We expect two virtqueues: inflate and deflate, and + * optionally stat. + */ nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2; - err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names); + err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names); if (err) - goto out_free_vb; + return err; vb->inflate_vq = vqs[0]; vb->deflate_vq = vqs[1]; @@ -318,6 +307,29 @@ static int virtballoon_probe(struct virtio_device *vdev) BUG(); virtqueue_kick(vb->stats_vq); } + return 0; +} + +static int virtballoon_probe(struct virtio_device *vdev) +{ + struct virtio_balloon *vb; + int err; + + vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL); + if (!vb) { + err = -ENOMEM; + goto out; + } + + INIT_LIST_HEAD(&vb->pages); + vb->num_pages = 0; + init_waitqueue_head(&vb->config_change); + vb->vdev = vdev; + vb->need_stats_update = 0; + + err = init_vqs(vb); + if (err) + goto out_free_vb; vb->thread = kthread_run(balloon, vb, "vballoon"); if (IS_ERR(vb->thread)) { -- cgit v1.2.3-18-g5258 From e562966dbaf49e7804097cd991e5d3a8934fc148 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Thu, 22 Dec 2011 16:58:35 +0530 Subject: virtio: balloon: Add freeze, restore handlers to support S4 Handling balloon hibernate / restore is tricky. If the balloon was inflated before going into the hibernation state, upon resume, the host will not have any memory of that. Any pages that were passed on to the host earlier would most likely be invalid, and the host will have to re-balloon to the previous value to get in the pre-hibernate state. So the only sane thing for the guest to do here is to discard all the pages that were put in the balloon. When to discard the pages is the next question. One solution is to deflate the balloon just before writing the image to the disk (in the freeze() PM callback). However, asking for pages from the host just to discard them immediately after seems wasteful of resources. Hence, it makes sense to do this by just fudging our counters soon after wakeup. This means we don't deflate the balloon before sleep, and also don't put unnecessary pressure on the host. This also helps in the thaw case: if the freeze fails for whatever reason, the balloon should continue to remain in the inflated state. This was tested by issuing 'swapoff -a' and trying to go into the S4 state. That fails, and the balloon stays inflated, as expected. Both the host and the guest are happy. Finally, in the restore() callback, we empty the list of pages that were previously given off to the host, add the appropriate number of pages to the totalram_pages counter, reset the num_pages counter to 0, and all is fine. As a last step, delete the vqs on the freeze callback to prepare for hibernation, and re-create them in the restore and thaw callbacks to resume normal operation. The kthread doesn't race with any operations here, since it's frozen before the freeze() call and is thawed after the thaw() and restore() callbacks, so we're safe with that. Signed-off-by: Amit Shah Signed-off-by: Rusty Russell --- drivers/virtio/virtio_balloon.c | 47 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 3368cb6ef19..95aeedf198f 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -364,6 +364,48 @@ static void __devexit virtballoon_remove(struct virtio_device *vdev) kfree(vb); } +#ifdef CONFIG_PM +static int virtballoon_freeze(struct virtio_device *vdev) +{ + /* + * The kthread is already frozen by the PM core before this + * function is called. + */ + + /* Ensure we don't get any more requests from the host */ + vdev->config->reset(vdev); + vdev->config->del_vqs(vdev); + return 0; +} + +static int virtballoon_thaw(struct virtio_device *vdev) +{ + return init_vqs(vdev->priv); +} + +static int virtballoon_restore(struct virtio_device *vdev) +{ + struct virtio_balloon *vb = vdev->priv; + struct page *page, *page2; + + /* We're starting from a clean slate */ + vb->num_pages = 0; + + /* + * If a request wasn't complete at the time of freezing, this + * could have been set. + */ + vb->need_stats_update = 0; + + /* We don't have these pages in the balloon anymore! */ + list_for_each_entry_safe(page, page2, &vb->pages, lru) { + list_del(&page->lru); + totalram_pages++; + } + return init_vqs(vdev->priv); +} +#endif + static unsigned int features[] = { VIRTIO_BALLOON_F_MUST_TELL_HOST, VIRTIO_BALLOON_F_STATS_VQ, @@ -378,6 +420,11 @@ static struct virtio_driver virtio_balloon_driver = { .probe = virtballoon_probe, .remove = __devexit_p(virtballoon_remove), .config_changed = virtballoon_changed, +#ifdef CONFIG_PM + .freeze = virtballoon_freeze, + .restore = virtballoon_restore, + .thaw = virtballoon_thaw, +#endif }; static int __init init(void) -- cgit v1.2.3-18-g5258 From 39082f7e5912cdc70f9ab0767e7342711f34b9f8 Mon Sep 17 00:00:00 2001 From: Jacek Galowicz Date: Thu, 12 Jan 2012 15:44:47 +1030 Subject: lguest: switch segment-voodoo-numbers to readable symbols When studying lguest's x86 segment descriptor code, it is not longer necessary to have the Intel x86 architecture manual open on the page with the segment descriptor illustration to understand the crazy numbers assigned to both descriptor structure halves a/b. Now the struct desc_struct's fields, like suggested by Glauber de Oliveira Costa in 2008, are used. Signed-off-by: Jacek Galowicz Signed-off-by: Rusty Russell --- drivers/lguest/segments.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/drivers/lguest/segments.c b/drivers/lguest/segments.c index ede46581351..c4fb424dfdd 100644 --- a/drivers/lguest/segments.c +++ b/drivers/lguest/segments.c @@ -81,8 +81,8 @@ static void fixup_gdt_table(struct lg_cpu *cpu, unsigned start, unsigned end) * sometimes careless and leaves this as 0, even though it's * running at privilege level 1. If so, we fix it here. */ - if ((cpu->arch.gdt[i].b & 0x00006000) == 0) - cpu->arch.gdt[i].b |= (GUEST_PL << 13); + if (cpu->arch.gdt[i].dpl == 0) + cpu->arch.gdt[i].dpl |= GUEST_PL; /* * Each descriptor has an "accessed" bit. If we don't set it @@ -90,7 +90,7 @@ static void fixup_gdt_table(struct lg_cpu *cpu, unsigned start, unsigned end) * that entry into a segment register. But the GDT isn't * writable by the Guest, so bad things can happen. */ - cpu->arch.gdt[i].b |= 0x00000100; + cpu->arch.gdt[i].type |= 0x1; } } @@ -114,13 +114,19 @@ void setup_default_gdt_entries(struct lguest_ro_state *state) /* * The TSS segment refers to the TSS entry for this particular CPU. - * Forgive the magic flags: the 0x8900 means the entry is Present, it's - * privilege level 0 Available 386 TSS system segment, and the 0x67 - * means Saturn is eclipsed by Mercury in the twelfth house. */ - gdt[GDT_ENTRY_TSS].a = 0x00000067 | (tss << 16); - gdt[GDT_ENTRY_TSS].b = 0x00008900 | (tss & 0xFF000000) - | ((tss >> 16) & 0x000000FF); + gdt[GDT_ENTRY_TSS].a = 0; + gdt[GDT_ENTRY_TSS].b = 0; + + gdt[GDT_ENTRY_TSS].limit0 = 0x67; + gdt[GDT_ENTRY_TSS].base0 = tss & 0xFFFF; + gdt[GDT_ENTRY_TSS].base1 = (tss >> 16) & 0xFF; + gdt[GDT_ENTRY_TSS].base2 = tss >> 24; + gdt[GDT_ENTRY_TSS].type = 0x9; /* 32-bit TSS (available) */ + gdt[GDT_ENTRY_TSS].p = 0x1; /* Entry is present */ + gdt[GDT_ENTRY_TSS].dpl = 0x0; /* Privilege level 0 */ + gdt[GDT_ENTRY_TSS].s = 0x0; /* system segment */ + } /* @@ -135,8 +141,8 @@ void setup_guest_gdt(struct lg_cpu *cpu) */ cpu->arch.gdt[GDT_ENTRY_KERNEL_CS] = FULL_EXEC_SEGMENT; cpu->arch.gdt[GDT_ENTRY_KERNEL_DS] = FULL_SEGMENT; - cpu->arch.gdt[GDT_ENTRY_KERNEL_CS].b |= (GUEST_PL << 13); - cpu->arch.gdt[GDT_ENTRY_KERNEL_DS].b |= (GUEST_PL << 13); + cpu->arch.gdt[GDT_ENTRY_KERNEL_CS].dpl |= GUEST_PL; + cpu->arch.gdt[GDT_ENTRY_KERNEL_DS].dpl |= GUEST_PL; } /*H:650 -- cgit v1.2.3-18-g5258 From 07fe9977b6234ede1bd29e10e0323e478860c871 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 12 Jan 2012 15:44:47 +1030 Subject: lguest: move the lguest tool to the tools directory This is a better location instead of having it in Documentation. Signed-off-by: Davidlohr Bueso Signed-off-by: Rusty Russell (fixed compile) --- Documentation/virtual/lguest/.gitignore | 1 - Documentation/virtual/lguest/Makefile | 8 - Documentation/virtual/lguest/extract | 58 - Documentation/virtual/lguest/lguest.c | 2065 ------------------------------- Documentation/virtual/lguest/lguest.txt | 129 -- drivers/lguest/Makefile | 2 +- tools/lguest/.gitignore | 1 + tools/lguest/Makefile | 8 + tools/lguest/extract | 58 + tools/lguest/lguest.c | 2065 +++++++++++++++++++++++++++++++ tools/lguest/lguest.txt | 129 ++ 11 files changed, 2262 insertions(+), 2262 deletions(-) delete mode 100644 Documentation/virtual/lguest/.gitignore delete mode 100644 Documentation/virtual/lguest/Makefile delete mode 100644 Documentation/virtual/lguest/extract delete mode 100644 Documentation/virtual/lguest/lguest.c delete mode 100644 Documentation/virtual/lguest/lguest.txt create mode 100644 tools/lguest/.gitignore create mode 100644 tools/lguest/Makefile create mode 100644 tools/lguest/extract create mode 100644 tools/lguest/lguest.c create mode 100644 tools/lguest/lguest.txt diff --git a/Documentation/virtual/lguest/.gitignore b/Documentation/virtual/lguest/.gitignore deleted file mode 100644 index 115587fd5f6..00000000000 --- a/Documentation/virtual/lguest/.gitignore +++ /dev/null @@ -1 +0,0 @@ -lguest diff --git a/Documentation/virtual/lguest/Makefile b/Documentation/virtual/lguest/Makefile deleted file mode 100644 index 0ac34206f7a..00000000000 --- a/Documentation/virtual/lguest/Makefile +++ /dev/null @@ -1,8 +0,0 @@ -# This creates the demonstration utility "lguest" which runs a Linux guest. -# Missing headers? Add "-I../../../include -I../../../arch/x86/include" -CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE - -all: lguest - -clean: - rm -f lguest diff --git a/Documentation/virtual/lguest/extract b/Documentation/virtual/lguest/extract deleted file mode 100644 index 7730bb6e4b9..00000000000 --- a/Documentation/virtual/lguest/extract +++ /dev/null @@ -1,58 +0,0 @@ -#! /bin/sh - -set -e - -PREFIX=$1 -shift - -trap 'rm -r $TMPDIR' 0 -TMPDIR=`mktemp -d` - -exec 3>/dev/null -for f; do - while IFS=" -" read -r LINE; do - case "$LINE" in - *$PREFIX:[0-9]*:\**) - NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` - if [ -f $TMPDIR/$NUM ]; then - echo "$TMPDIR/$NUM already exits prior to $f" - exit 1 - fi - exec 3>>$TMPDIR/$NUM - echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM - /bin/echo "$LINE" | sed -e "s/$PREFIX:[0-9]*//" -e "s/:\*/*/" >&3 - ;; - *$PREFIX:[0-9]*) - NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` - if [ -f $TMPDIR/$NUM ]; then - echo "$TMPDIR/$NUM already exits prior to $f" - exit 1 - fi - exec 3>>$TMPDIR/$NUM - echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM - /bin/echo "$LINE" | sed "s/$PREFIX:[0-9]*//" >&3 - ;; - *:\**) - /bin/echo "$LINE" | sed -e "s/:\*/*/" -e "s,/\*\*/,," >&3 - echo >&3 - exec 3>/dev/null - ;; - *) - /bin/echo "$LINE" >&3 - ;; - esac - done < $f - echo >&3 - exec 3>/dev/null -done - -LASTFILE="" -for f in $TMPDIR/*; do - if [ "$LASTFILE" != $(cat $TMPDIR/.$(basename $f) ) ]; then - LASTFILE=$(cat $TMPDIR/.$(basename $f) ) - echo "[ $LASTFILE ]" - fi - cat $f -done - diff --git a/Documentation/virtual/lguest/lguest.c b/Documentation/virtual/lguest/lguest.c deleted file mode 100644 index c095d79cae7..00000000000 --- a/Documentation/virtual/lguest/lguest.c +++ /dev/null @@ -1,2065 +0,0 @@ -/*P:100 - * This is the Launcher code, a simple program which lays out the "physical" - * memory for the new Guest by mapping the kernel image and the virtual - * devices, then opens /dev/lguest to tell the kernel about the Guest and - * control it. -:*/ -#define _LARGEFILE64_SOURCE -#define _GNU_SOURCE -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include "../../../include/linux/lguest_launcher.h" -/*L:110 - * We can ignore the 43 include files we need for this program, but I do want - * to draw attention to the use of kernel-style types. - * - * As Linus said, "C is a Spartan language, and so should your naming be." I - * like these abbreviations, so we define them here. Note that u64 is always - * unsigned long long, which works on all Linux systems: this means that we can - * use %llu in printf for any u64. - */ -typedef unsigned long long u64; -typedef uint32_t u32; -typedef uint16_t u16; -typedef uint8_t u8; -/*:*/ - -#define BRIDGE_PFX "bridge:" -#ifndef SIOCBRADDIF -#define SIOCBRADDIF 0x89a2 /* add interface to bridge */ -#endif -/* We can have up to 256 pages for devices. */ -#define DEVICE_PAGES 256 -/* This will occupy 3 pages: it must be a power of 2. */ -#define VIRTQUEUE_NUM 256 - -/*L:120 - * verbose is both a global flag and a macro. The C preprocessor allows - * this, and although I wouldn't recommend it, it works quite nicely here. - */ -static bool verbose; -#define verbose(args...) \ - do { if (verbose) printf(args); } while(0) -/*:*/ - -/* The pointer to the start of guest memory. */ -static void *guest_base; -/* The maximum guest physical address allowed, and maximum possible. */ -static unsigned long guest_limit, guest_max; -/* The /dev/lguest file descriptor. */ -static int lguest_fd; - -/* a per-cpu variable indicating whose vcpu is currently running */ -static unsigned int __thread cpu_id; - -/* This is our list of devices. */ -struct device_list { - /* Counter to assign interrupt numbers. */ - unsigned int next_irq; - - /* Counter to print out convenient device numbers. */ - unsigned int device_num; - - /* The descriptor page for the devices. */ - u8 *descpage; - - /* A single linked list of devices. */ - struct device *dev; - /* And a pointer to the last device for easy append. */ - struct device *lastdev; -}; - -/* The list of Guest devices, based on command line arguments. */ -static struct device_list devices; - -/* The device structure describes a single device. */ -struct device { - /* The linked-list pointer. */ - struct device *next; - - /* The device's descriptor, as mapped into the Guest. */ - struct lguest_device_desc *desc; - - /* We can't trust desc values once Guest has booted: we use these. */ - unsigned int feature_len; - unsigned int num_vq; - - /* The name of this device, for --verbose. */ - const char *name; - - /* Any queues attached to this device */ - struct virtqueue *vq; - - /* Is it operational */ - bool running; - - /* Device-specific data. */ - void *priv; -}; - -/* The virtqueue structure describes a queue attached to a device. */ -struct virtqueue { - struct virtqueue *next; - - /* Which device owns me. */ - struct device *dev; - - /* The configuration for this queue. */ - struct lguest_vqconfig config; - - /* The actual ring of buffers. */ - struct vring vring; - - /* Last available index we saw. */ - u16 last_avail_idx; - - /* How many are used since we sent last irq? */ - unsigned int pending_used; - - /* Eventfd where Guest notifications arrive. */ - int eventfd; - - /* Function for the thread which is servicing this virtqueue. */ - void (*service)(struct virtqueue *vq); - pid_t thread; -}; - -/* Remember the arguments to the program so we can "reboot" */ -static char **main_args; - -/* The original tty settings to restore on exit. */ -static struct termios orig_term; - -/* - * We have to be careful with barriers: our devices are all run in separate - * threads and so we need to make sure that changes visible to the Guest happen - * in precise order. - */ -#define wmb() __asm__ __volatile__("" : : : "memory") -#define mb() __asm__ __volatile__("" : : : "memory") - -/* - * Convert an iovec element to the given type. - * - * This is a fairly ugly trick: we need to know the size of the type and - * alignment requirement to check the pointer is kosher. It's also nice to - * have the name of the type in case we report failure. - * - * Typing those three things all the time is cumbersome and error prone, so we - * have a macro which sets them all up and passes to the real function. - */ -#define convert(iov, type) \ - ((type *)_convert((iov), sizeof(type), __alignof__(type), #type)) - -static void *_convert(struct iovec *iov, size_t size, size_t align, - const char *name) -{ - if (iov->iov_len != size) - errx(1, "Bad iovec size %zu for %s", iov->iov_len, name); - if ((unsigned long)iov->iov_base % align != 0) - errx(1, "Bad alignment %p for %s", iov->iov_base, name); - return iov->iov_base; -} - -/* Wrapper for the last available index. Makes it easier to change. */ -#define lg_last_avail(vq) ((vq)->last_avail_idx) - -/* - * The virtio configuration space is defined to be little-endian. x86 is - * little-endian too, but it's nice to be explicit so we have these helpers. - */ -#define cpu_to_le16(v16) (v16) -#define cpu_to_le32(v32) (v32) -#define cpu_to_le64(v64) (v64) -#define le16_to_cpu(v16) (v16) -#define le32_to_cpu(v32) (v32) -#define le64_to_cpu(v64) (v64) - -/* Is this iovec empty? */ -static bool iov_empty(const struct iovec iov[], unsigned int num_iov) -{ - unsigned int i; - - for (i = 0; i < num_iov; i++) - if (iov[i].iov_len) - return false; - return true; -} - -/* Take len bytes from the front of this iovec. */ -static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len) -{ - unsigned int i; - - for (i = 0; i < num_iov; i++) { - unsigned int used; - - used = iov[i].iov_len < len ? iov[i].iov_len : len; - iov[i].iov_base += used; - iov[i].iov_len -= used; - len -= used; - } - assert(len == 0); -} - -/* The device virtqueue descriptors are followed by feature bitmasks. */ -static u8 *get_feature_bits(struct device *dev) -{ - return (u8 *)(dev->desc + 1) - + dev->num_vq * sizeof(struct lguest_vqconfig); -} - -/*L:100 - * The Launcher code itself takes us out into userspace, that scary place where - * pointers run wild and free! Unfortunately, like most userspace programs, - * it's quite boring (which is why everyone likes to hack on the kernel!). - * Perhaps if you make up an Lguest Drinking Game at this point, it will get - * you through this section. Or, maybe not. - * - * The Launcher sets up a big chunk of memory to be the Guest's "physical" - * memory and stores it in "guest_base". In other words, Guest physical == - * Launcher virtual with an offset. - * - * This can be tough to get your head around, but usually it just means that we - * use these trivial conversion functions when the Guest gives us its - * "physical" addresses: - */ -static void *from_guest_phys(unsigned long addr) -{ - return guest_base + addr; -} - -static unsigned long to_guest_phys(const void *addr) -{ - return (addr - guest_base); -} - -/*L:130 - * Loading the Kernel. - * - * We start with couple of simple helper routines. open_or_die() avoids - * error-checking code cluttering the callers: - */ -static int open_or_die(const char *name, int flags) -{ - int fd = open(name, flags); - if (fd < 0) - err(1, "Failed to open %s", name); - return fd; -} - -/* map_zeroed_pages() takes a number of pages. */ -static void *map_zeroed_pages(unsigned int num) -{ - int fd = open_or_die("/dev/zero", O_RDONLY); - void *addr; - - /* - * We use a private mapping (ie. if we write to the page, it will be - * copied). We allocate an extra two pages PROT_NONE to act as guard - * pages against read/write attempts that exceed allocated space. - */ - addr = mmap(NULL, getpagesize() * (num+2), - PROT_NONE, MAP_PRIVATE, fd, 0); - - if (addr == MAP_FAILED) - err(1, "Mmapping %u pages of /dev/zero", num); - - if (mprotect(addr + getpagesize(), getpagesize() * num, - PROT_READ|PROT_WRITE) == -1) - err(1, "mprotect rw %u pages failed", num); - - /* - * One neat mmap feature is that you can close the fd, and it - * stays mapped. - */ - close(fd); - - /* Return address after PROT_NONE page */ - return addr + getpagesize(); -} - -/* Get some more pages for a device. */ -static void *get_pages(unsigned int num) -{ - void *addr = from_guest_phys(guest_limit); - - guest_limit += num * getpagesize(); - if (guest_limit > guest_max) - errx(1, "Not enough memory for devices"); - return addr; -} - -/* - * This routine is used to load the kernel or initrd. It tries mmap, but if - * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries), - * it falls back to reading the memory in. - */ -static void map_at(int fd, void *addr, unsigned long offset, unsigned long len) -{ - ssize_t r; - - /* - * We map writable even though for some segments are marked read-only. - * The kernel really wants to be writable: it patches its own - * instructions. - * - * MAP_PRIVATE means that the page won't be copied until a write is - * done to it. This allows us to share untouched memory between - * Guests. - */ - if (mmap(addr, len, PROT_READ|PROT_WRITE, - MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED) - return; - - /* pread does a seek and a read in one shot: saves a few lines. */ - r = pread(fd, addr, len, offset); - if (r != len) - err(1, "Reading offset %lu len %lu gave %zi", offset, len, r); -} - -/* - * This routine takes an open vmlinux image, which is in ELF, and maps it into - * the Guest memory. ELF = Embedded Linking Format, which is the format used - * by all modern binaries on Linux including the kernel. - * - * The ELF headers give *two* addresses: a physical address, and a virtual - * address. We use the physical address; the Guest will map itself to the - * virtual address. - * - * We return the starting address. - */ -static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) -{ - Elf32_Phdr phdr[ehdr->e_phnum]; - unsigned int i; - - /* - * Sanity checks on the main ELF header: an x86 executable with a - * reasonable number of correctly-sized program headers. - */ - if (ehdr->e_type != ET_EXEC - || ehdr->e_machine != EM_386 - || ehdr->e_phentsize != sizeof(Elf32_Phdr) - || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr)) - errx(1, "Malformed elf header"); - - /* - * An ELF executable contains an ELF header and a number of "program" - * headers which indicate which parts ("segments") of the program to - * load where. - */ - - /* We read in all the program headers at once: */ - if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0) - err(1, "Seeking to program headers"); - if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr)) - err(1, "Reading program headers"); - - /* - * Try all the headers: there are usually only three. A read-only one, - * a read-write one, and a "note" section which we don't load. - */ - for (i = 0; i < ehdr->e_phnum; i++) { - /* If this isn't a loadable segment, we ignore it */ - if (phdr[i].p_type != PT_LOAD) - continue; - - verbose("Section %i: size %i addr %p\n", - i, phdr[i].p_memsz, (void *)phdr[i].p_paddr); - - /* We map this section of the file at its physical address. */ - map_at(elf_fd, from_guest_phys(phdr[i].p_paddr), - phdr[i].p_offset, phdr[i].p_filesz); - } - - /* The entry point is given in the ELF header. */ - return ehdr->e_entry; -} - -/*L:150 - * A bzImage, unlike an ELF file, is not meant to be loaded. You're supposed - * to jump into it and it will unpack itself. We used to have to perform some - * hairy magic because the unpacking code scared me. - * - * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote - * a small patch to jump over the tricky bits in the Guest, so now we just read - * the funky header so we know where in the file to load, and away we go! - */ -static unsigned long load_bzimage(int fd) -{ - struct boot_params boot; - int r; - /* Modern bzImages get loaded at 1M. */ - void *p = from_guest_phys(0x100000); - - /* - * Go back to the start of the file and read the header. It should be - * a Linux boot header (see Documentation/x86/boot.txt) - */ - lseek(fd, 0, SEEK_SET); - read(fd, &boot, sizeof(boot)); - - /* Inside the setup_hdr, we expect the magic "HdrS" */ - if (memcmp(&boot.hdr.header, "HdrS", 4) != 0) - errx(1, "This doesn't look like a bzImage to me"); - - /* Skip over the extra sectors of the header. */ - lseek(fd, (boot.hdr.setup_sects+1) * 512, SEEK_SET); - - /* Now read everything into memory. in nice big chunks. */ - while ((r = read(fd, p, 65536)) > 0) - p += r; - - /* Finally, code32_start tells us where to enter the kernel. */ - return boot.hdr.code32_start; -} - -/*L:140 - * Loading the kernel is easy when it's a "vmlinux", but most kernels - * come wrapped up in the self-decompressing "bzImage" format. With a little - * work, we can load those, too. - */ -static unsigned long load_kernel(int fd) -{ - Elf32_Ehdr hdr; - - /* Read in the first few bytes. */ - if (read(fd, &hdr, sizeof(hdr)) != sizeof(hdr)) - err(1, "Reading kernel"); - - /* If it's an ELF file, it starts with "\177ELF" */ - if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0) - return map_elf(fd, &hdr); - - /* Otherwise we assume it's a bzImage, and try to load it. */ - return load_bzimage(fd); -} - -/* - * This is a trivial little helper to align pages. Andi Kleen hated it because - * it calls getpagesize() twice: "it's dumb code." - * - * Kernel guys get really het up about optimization, even when it's not - * necessary. I leave this code as a reaction against that. - */ -static inline unsigned long page_align(unsigned long addr) -{ - /* Add upwards and truncate downwards. */ - return ((addr + getpagesize()-1) & ~(getpagesize()-1)); -} - -/*L:180 - * An "initial ram disk" is a disk image loaded into memory along with the - * kernel which the kernel can use to boot from without needing any drivers. - * Most distributions now use this as standard: the initrd contains the code to - * load the appropriate driver modules for the current machine. - * - * Importantly, James Morris works for RedHat, and Fedora uses initrds for its - * kernels. He sent me this (and tells me when I break it). - */ -static unsigned long load_initrd(const char *name, unsigned long mem) -{ - int ifd; - struct stat st; - unsigned long len; - - ifd = open_or_die(name, O_RDONLY); - /* fstat() is needed to get the file size. */ - if (fstat(ifd, &st) < 0) - err(1, "fstat() on initrd '%s'", name); - - /* - * We map the initrd at the top of memory, but mmap wants it to be - * page-aligned, so we round the size up for that. - */ - len = page_align(st.st_size); - map_at(ifd, from_guest_phys(mem - len), 0, st.st_size); - /* - * Once a file is mapped, you can close the file descriptor. It's a - * little odd, but quite useful. - */ - close(ifd); - verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len); - - /* We return the initrd size. */ - return len; -} -/*:*/ - -/* - * Simple routine to roll all the commandline arguments together with spaces - * between them. - */ -static void concat(char *dst, char *args[]) -{ - unsigned int i, len = 0; - - for (i = 0; args[i]; i++) { - if (i) { - strcat(dst+len, " "); - len++; - } - strcpy(dst+len, args[i]); - len += strlen(args[i]); - } - /* In case it's empty. */ - dst[len] = '\0'; -} - -/*L:185 - * This is where we actually tell the kernel to initialize the Guest. We - * saw the arguments it expects when we looked at initialize() in lguest_user.c: - * the base of Guest "physical" memory, the top physical page to allow and the - * entry point for the Guest. - */ -static void tell_kernel(unsigned long start) -{ - unsigned long args[] = { LHREQ_INITIALIZE, - (unsigned long)guest_base, - guest_limit / getpagesize(), start }; - verbose("Guest: %p - %p (%#lx)\n", - guest_base, guest_base + guest_limit, guest_limit); - lguest_fd = open_or_die("/dev/lguest", O_RDWR); - if (write(lguest_fd, args, sizeof(args)) < 0) - err(1, "Writing to /dev/lguest"); -} -/*:*/ - -/*L:200 - * Device Handling. - * - * When the Guest gives us a buffer, it sends an array of addresses and sizes. - * We need to make sure it's not trying to reach into the Launcher itself, so - * we have a convenient routine which checks it and exits with an error message - * if something funny is going on: - */ -static void *_check_pointer(unsigned long addr, unsigned int size, - unsigned int line) -{ - /* - * Check if the requested address and size exceeds the allocated memory, - * or addr + size wraps around. - */ - if ((addr + size) > guest_limit || (addr + size) < addr) - errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr); - /* - * We return a pointer for the caller's convenience, now we know it's - * safe to use. - */ - return from_guest_phys(addr); -} -/* A macro which transparently hands the line number to the real function. */ -#define check_pointer(addr,size) _check_pointer(addr, size, __LINE__) - -/* - * Each buffer in the virtqueues is actually a chain of descriptors. This - * function returns the next descriptor in the chain, or vq->vring.num if we're - * at the end. - */ -static unsigned next_desc(struct vring_desc *desc, - unsigned int i, unsigned int max) -{ - unsigned int next; - - /* If this descriptor says it doesn't chain, we're done. */ - if (!(desc[i].flags & VRING_DESC_F_NEXT)) - return max; - - /* Check they're not leading us off end of descriptors. */ - next = desc[i].next; - /* Make sure compiler knows to grab that: we don't want it changing! */ - wmb(); - - if (next >= max) - errx(1, "Desc next is %u", next); - - return next; -} - -/* - * This actually sends the interrupt for this virtqueue, if we've used a - * buffer. - */ -static void trigger_irq(struct virtqueue *vq) -{ - unsigned long buf[] = { LHREQ_IRQ, vq->config.irq }; - - /* Don't inform them if nothing used. */ - if (!vq->pending_used) - return; - vq->pending_used = 0; - - /* If they don't want an interrupt, don't send one... */ - if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) { - return; - } - - /* Send the Guest an interrupt tell them we used something up. */ - if (write(lguest_fd, buf, sizeof(buf)) != 0) - err(1, "Triggering irq %i", vq->config.irq); -} - -/* - * This looks in the virtqueue for the first available buffer, and converts - * it to an iovec for convenient access. Since descriptors consist of some - * number of output then some number of input descriptors, it's actually two - * iovecs, but we pack them into one and note how many of each there were. - * - * This function waits if necessary, and returns the descriptor number found. - */ -static unsigned wait_for_vq_desc(struct virtqueue *vq, - struct iovec iov[], - unsigned int *out_num, unsigned int *in_num) -{ - unsigned int i, head, max; - struct vring_desc *desc; - u16 last_avail = lg_last_avail(vq); - - /* There's nothing available? */ - while (last_avail == vq->vring.avail->idx) { - u64 event; - - /* - * Since we're about to sleep, now is a good time to tell the - * Guest about what we've used up to now. - */ - trigger_irq(vq); - - /* OK, now we need to know about added descriptors. */ - vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; - - /* - * They could have slipped one in as we were doing that: make - * sure it's written, then check again. - */ - mb(); - if (last_avail != vq->vring.avail->idx) { - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - break; - } - - /* Nothing new? Wait for eventfd to tell us they refilled. */ - if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event)) - errx(1, "Event read failed?"); - - /* We don't need to be notified again. */ - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - } - - /* Check it isn't doing very strange things with descriptor numbers. */ - if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num) - errx(1, "Guest moved used index from %u to %u", - last_avail, vq->vring.avail->idx); - - /* - * Grab the next descriptor number they're advertising, and increment - * the index we've seen. - */ - head = vq->vring.avail->ring[last_avail % vq->vring.num]; - lg_last_avail(vq)++; - - /* If their number is silly, that's a fatal mistake. */ - if (head >= vq->vring.num) - errx(1, "Guest says index %u is available", head); - - /* When we start there are none of either input nor output. */ - *out_num = *in_num = 0; - - max = vq->vring.num; - desc = vq->vring.desc; - i = head; - - /* - * If this is an indirect entry, then this buffer contains a descriptor - * table which we handle as if it's any normal descriptor chain. - */ - if (desc[i].flags & VRING_DESC_F_INDIRECT) { - if (desc[i].len % sizeof(struct vring_desc)) - errx(1, "Invalid size for indirect buffer table"); - - max = desc[i].len / sizeof(struct vring_desc); - desc = check_pointer(desc[i].addr, desc[i].len); - i = 0; - } - - do { - /* Grab the first descriptor, and check it's OK. */ - iov[*out_num + *in_num].iov_len = desc[i].len; - iov[*out_num + *in_num].iov_base - = check_pointer(desc[i].addr, desc[i].len); - /* If this is an input descriptor, increment that count. */ - if (desc[i].flags & VRING_DESC_F_WRITE) - (*in_num)++; - else { - /* - * If it's an output descriptor, they're all supposed - * to come before any input descriptors. - */ - if (*in_num) - errx(1, "Descriptor has out after in"); - (*out_num)++; - } - - /* If we've got too many, that implies a descriptor loop. */ - if (*out_num + *in_num > max) - errx(1, "Looped descriptor"); - } while ((i = next_desc(desc, i, max)) != max); - - return head; -} - -/* - * After we've used one of their buffers, we tell the Guest about it. Sometime - * later we'll want to send them an interrupt using trigger_irq(); note that - * wait_for_vq_desc() does that for us if it has to wait. - */ -static void add_used(struct virtqueue *vq, unsigned int head, int len) -{ - struct vring_used_elem *used; - - /* - * The virtqueue contains a ring of used buffers. Get a pointer to the - * next entry in that used ring. - */ - used = &vq->vring.used->ring[vq->vring.used->idx % vq->vring.num]; - used->id = head; - used->len = len; - /* Make sure buffer is written before we update index. */ - wmb(); - vq->vring.used->idx++; - vq->pending_used++; -} - -/* And here's the combo meal deal. Supersize me! */ -static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len) -{ - add_used(vq, head, len); - trigger_irq(vq); -} - -/* - * The Console - * - * We associate some data with the console for our exit hack. - */ -struct console_abort { - /* How many times have they hit ^C? */ - int count; - /* When did they start? */ - struct timeval start; -}; - -/* This is the routine which handles console input (ie. stdin). */ -static void console_input(struct virtqueue *vq) -{ - int len; - unsigned int head, in_num, out_num; - struct console_abort *abort = vq->dev->priv; - struct iovec iov[vq->vring.num]; - - /* Make sure there's a descriptor available. */ - head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - if (out_num) - errx(1, "Output buffers in console in queue?"); - - /* Read into it. This is where we usually wait. */ - len = readv(STDIN_FILENO, iov, in_num); - if (len <= 0) { - /* Ran out of input? */ - warnx("Failed to get console input, ignoring console."); - /* - * For simplicity, dying threads kill the whole Launcher. So - * just nap here. - */ - for (;;) - pause(); - } - - /* Tell the Guest we used a buffer. */ - add_used_and_trigger(vq, head, len); - - /* - * Three ^C within one second? Exit. - * - * This is such a hack, but works surprisingly well. Each ^C has to - * be in a buffer by itself, so they can't be too fast. But we check - * that we get three within about a second, so they can't be too - * slow. - */ - if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) { - abort->count = 0; - return; - } - - abort->count++; - if (abort->count == 1) - gettimeofday(&abort->start, NULL); - else if (abort->count == 3) { - struct timeval now; - gettimeofday(&now, NULL); - /* Kill all Launcher processes with SIGINT, like normal ^C */ - if (now.tv_sec <= abort->start.tv_sec+1) - kill(0, SIGINT); - abort->count = 0; - } -} - -/* This is the routine which handles console output (ie. stdout). */ -static void console_output(struct virtqueue *vq) -{ - unsigned int head, out, in; - struct iovec iov[vq->vring.num]; - - /* We usually wait in here, for the Guest to give us something. */ - head = wait_for_vq_desc(vq, iov, &out, &in); - if (in) - errx(1, "Input buffers in console output queue?"); - - /* writev can return a partial write, so we loop here. */ - while (!iov_empty(iov, out)) { - int len = writev(STDOUT_FILENO, iov, out); - if (len <= 0) { - warn("Write to stdout gave %i (%d)", len, errno); - break; - } - iov_consume(iov, out, len); - } - - /* - * We're finished with that buffer: if we're going to sleep, - * wait_for_vq_desc() will prod the Guest with an interrupt. - */ - add_used(vq, head, 0); -} - -/* - * The Network - * - * Handling output for network is also simple: we get all the output buffers - * and write them to /dev/net/tun. - */ -struct net_info { - int tunfd; -}; - -static void net_output(struct virtqueue *vq) -{ - struct net_info *net_info = vq->dev->priv; - unsigned int head, out, in; - struct iovec iov[vq->vring.num]; - - /* We usually wait in here for the Guest to give us a packet. */ - head = wait_for_vq_desc(vq, iov, &out, &in); - if (in) - errx(1, "Input buffers in net output queue?"); - /* - * Send the whole thing through to /dev/net/tun. It expects the exact - * same format: what a coincidence! - */ - if (writev(net_info->tunfd, iov, out) < 0) - warnx("Write to tun failed (%d)?", errno); - - /* - * Done with that one; wait_for_vq_desc() will send the interrupt if - * all packets are processed. - */ - add_used(vq, head, 0); -} - -/* - * Handling network input is a bit trickier, because I've tried to optimize it. - * - * First we have a helper routine which tells is if from this file descriptor - * (ie. the /dev/net/tun device) will block: - */ -static bool will_block(int fd) -{ - fd_set fdset; - struct timeval zero = { 0, 0 }; - FD_ZERO(&fdset); - FD_SET(fd, &fdset); - return select(fd+1, &fdset, NULL, NULL, &zero) != 1; -} - -/* - * This handles packets coming in from the tun device to our Guest. Like all - * service routines, it gets called again as soon as it returns, so you don't - * see a while(1) loop here. - */ -static void net_input(struct virtqueue *vq) -{ - int len; - unsigned int head, out, in; - struct iovec iov[vq->vring.num]; - struct net_info *net_info = vq->dev->priv; - - /* - * Get a descriptor to write an incoming packet into. This will also - * send an interrupt if they're out of descriptors. - */ - head = wait_for_vq_desc(vq, iov, &out, &in); - if (out) - errx(1, "Output buffers in net input queue?"); - - /* - * If it looks like we'll block reading from the tun device, send them - * an interrupt. - */ - if (vq->pending_used && will_block(net_info->tunfd)) - trigger_irq(vq); - - /* - * Read in the packet. This is where we normally wait (when there's no - * incoming network traffic). - */ - len = readv(net_info->tunfd, iov, in); - if (len <= 0) - warn("Failed to read from tun (%d).", errno); - - /* - * Mark that packet buffer as used, but don't interrupt here. We want - * to wait until we've done as much work as we can. - */ - add_used(vq, head, len); -} -/*:*/ - -/* This is the helper to create threads: run the service routine in a loop. */ -static int do_thread(void *_vq) -{ - struct virtqueue *vq = _vq; - - for (;;) - vq->service(vq); - return 0; -} - -/* - * When a child dies, we kill our entire process group with SIGTERM. This - * also has the side effect that the shell restores the console for us! - */ -static void kill_launcher(int signal) -{ - kill(0, SIGTERM); -} - -static void reset_device(struct device *dev) -{ - struct virtqueue *vq; - - verbose("Resetting device %s\n", dev->name); - - /* Clear any features they've acked. */ - memset(get_feature_bits(dev) + dev->feature_len, 0, dev->feature_len); - - /* We're going to be explicitly killing threads, so ignore them. */ - signal(SIGCHLD, SIG_IGN); - - /* Zero out the virtqueues, get rid of their threads */ - for (vq = dev->vq; vq; vq = vq->next) { - if (vq->thread != (pid_t)-1) { - kill(vq->thread, SIGTERM); - waitpid(vq->thread, NULL, 0); - vq->thread = (pid_t)-1; - } - memset(vq->vring.desc, 0, - vring_size(vq->config.num, LGUEST_VRING_ALIGN)); - lg_last_avail(vq) = 0; - } - dev->running = false; - - /* Now we care if threads die. */ - signal(SIGCHLD, (void *)kill_launcher); -} - -/*L:216 - * This actually creates the thread which services the virtqueue for a device. - */ -static void create_thread(struct virtqueue *vq) -{ - /* - * Create stack for thread. Since the stack grows upwards, we point - * the stack pointer to the end of this region. - */ - char *stack = malloc(32768); - unsigned long args[] = { LHREQ_EVENTFD, - vq->config.pfn*getpagesize(), 0 }; - - /* Create a zero-initialized eventfd. */ - vq->eventfd = eventfd(0, 0); - if (vq->eventfd < 0) - err(1, "Creating eventfd"); - args[2] = vq->eventfd; - - /* - * Attach an eventfd to this virtqueue: it will go off when the Guest - * does an LHCALL_NOTIFY for this vq. - */ - if (write(lguest_fd, &args, sizeof(args)) != 0) - err(1, "Attaching eventfd"); - - /* - * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so - * we get a signal if it dies. - */ - vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq); - if (vq->thread == (pid_t)-1) - err(1, "Creating clone"); - - /* We close our local copy now the child has it. */ - close(vq->eventfd); -} - -static void start_device(struct device *dev) -{ - unsigned int i; - struct virtqueue *vq; - - verbose("Device %s OK: offered", dev->name); - for (i = 0; i < dev->feature_len; i++) - verbose(" %02x", get_feature_bits(dev)[i]); - verbose(", accepted"); - for (i = 0; i < dev->feature_len; i++) - verbose(" %02x", get_feature_bits(dev) - [dev->feature_len+i]); - - for (vq = dev->vq; vq; vq = vq->next) { - if (vq->service) - create_thread(vq); - } - dev->running = true; -} - -static void cleanup_devices(void) -{ - struct device *dev; - - for (dev = devices.dev; dev; dev = dev->next) - reset_device(dev); - - /* If we saved off the original terminal settings, restore them now. */ - if (orig_term.c_lflag & (ISIG|ICANON|ECHO)) - tcsetattr(STDIN_FILENO, TCSANOW, &orig_term); -} - -/* When the Guest tells us they updated the status field, we handle it. */ -static void update_device_status(struct device *dev) -{ - /* A zero status is a reset, otherwise it's a set of flags. */ - if (dev->desc->status == 0) - reset_device(dev); - else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) { - warnx("Device %s configuration FAILED", dev->name); - if (dev->running) - reset_device(dev); - } else { - if (dev->running) - err(1, "Device %s features finalized twice", dev->name); - start_device(dev); - } -} - -/*L:215 - * This is the generic routine we call when the Guest uses LHCALL_NOTIFY. In - * particular, it's used to notify us of device status changes during boot. - */ -static void handle_output(unsigned long addr) -{ - struct device *i; - - /* Check each device. */ - for (i = devices.dev; i; i = i->next) { - struct virtqueue *vq; - - /* - * Notifications to device descriptors mean they updated the - * device status. - */ - if (from_guest_phys(addr) == i->desc) { - update_device_status(i); - return; - } - - /* Devices should not be used before features are finalized. */ - for (vq = i->vq; vq; vq = vq->next) { - if (addr != vq->config.pfn*getpagesize()) - continue; - errx(1, "Notification on %s before setup!", i->name); - } - } - - /* - * Early console write is done using notify on a nul-terminated string - * in Guest memory. It's also great for hacking debugging messages - * into a Guest. - */ - if (addr >= guest_limit) - errx(1, "Bad NOTIFY %#lx", addr); - - write(STDOUT_FILENO, from_guest_phys(addr), - strnlen(from_guest_phys(addr), guest_limit - addr)); -} - -/*L:190 - * Device Setup - * - * All devices need a descriptor so the Guest knows it exists, and a "struct - * device" so the Launcher can keep track of it. We have common helper - * routines to allocate and manage them. - */ - -/* - * The layout of the device page is a "struct lguest_device_desc" followed by a - * number of virtqueue descriptors, then two sets of feature bits, then an - * array of configuration bytes. This routine returns the configuration - * pointer. - */ -static u8 *device_config(const struct device *dev) -{ - return (void *)(dev->desc + 1) - + dev->num_vq * sizeof(struct lguest_vqconfig) - + dev->feature_len * 2; -} - -/* - * This routine allocates a new "struct lguest_device_desc" from descriptor - * table page just above the Guest's normal memory. It returns a pointer to - * that descriptor. - */ -static struct lguest_device_desc *new_dev_desc(u16 type) -{ - struct lguest_device_desc d = { .type = type }; - void *p; - - /* Figure out where the next device config is, based on the last one. */ - if (devices.lastdev) - p = device_config(devices.lastdev) - + devices.lastdev->desc->config_len; - else - p = devices.descpage; - - /* We only have one page for all the descriptors. */ - if (p + sizeof(d) > (void *)devices.descpage + getpagesize()) - errx(1, "Too many devices"); - - /* p might not be aligned, so we memcpy in. */ - return memcpy(p, &d, sizeof(d)); -} - -/* - * Each device descriptor is followed by the description of its virtqueues. We - * specify how many descriptors the virtqueue is to have. - */ -static void add_virtqueue(struct device *dev, unsigned int num_descs, - void (*service)(struct virtqueue *)) -{ - unsigned int pages; - struct virtqueue **i, *vq = malloc(sizeof(*vq)); - void *p; - - /* First we need some memory for this virtqueue. */ - pages = (vring_size(num_descs, LGUEST_VRING_ALIGN) + getpagesize() - 1) - / getpagesize(); - p = get_pages(pages); - - /* Initialize the virtqueue */ - vq->next = NULL; - vq->last_avail_idx = 0; - vq->dev = dev; - - /* - * This is the routine the service thread will run, and its Process ID - * once it's running. - */ - vq->service = service; - vq->thread = (pid_t)-1; - - /* Initialize the configuration. */ - vq->config.num = num_descs; - vq->config.irq = devices.next_irq++; - vq->config.pfn = to_guest_phys(p) / getpagesize(); - - /* Initialize the vring. */ - vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN); - - /* - * Append virtqueue to this device's descriptor. We use - * device_config() to get the end of the device's current virtqueues; - * we check that we haven't added any config or feature information - * yet, otherwise we'd be overwriting them. - */ - assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0); - memcpy(device_config(dev), &vq->config, sizeof(vq->config)); - dev->num_vq++; - dev->desc->num_vq++; - - verbose("Virtqueue page %#lx\n", to_guest_phys(p)); - - /* - * Add to tail of list, so dev->vq is first vq, dev->vq->next is - * second. - */ - for (i = &dev->vq; *i; i = &(*i)->next); - *i = vq; -} - -/* - * The first half of the feature bitmask is for us to advertise features. The - * second half is for the Guest to accept features. - */ -static void add_feature(struct device *dev, unsigned bit) -{ - u8 *features = get_feature_bits(dev); - - /* We can't extend the feature bits once we've added config bytes */ - if (dev->desc->feature_len <= bit / CHAR_BIT) { - assert(dev->desc->config_len == 0); - dev->feature_len = dev->desc->feature_len = (bit/CHAR_BIT) + 1; - } - - features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT)); -} - -/* - * This routine sets the configuration fields for an existing device's - * descriptor. It only works for the last device, but that's OK because that's - * how we use it. - */ -static void set_config(struct device *dev, unsigned len, const void *conf) -{ - /* Check we haven't overflowed our single page. */ - if (device_config(dev) + len > devices.descpage + getpagesize()) - errx(1, "Too many devices"); - - /* Copy in the config information, and store the length. */ - memcpy(device_config(dev), conf, len); - dev->desc->config_len = len; - - /* Size must fit in config_len field (8 bits)! */ - assert(dev->desc->config_len == len); -} - -/* - * This routine does all the creation and setup of a new device, including - * calling new_dev_desc() to allocate the descriptor and device memory. We - * don't actually start the service threads until later. - * - * See what I mean about userspace being boring? - */ -static struct device *new_device(const char *name, u16 type) -{ - struct device *dev = malloc(sizeof(*dev)); - - /* Now we populate the fields one at a time. */ - dev->desc = new_dev_desc(type); - dev->name = name; - dev->vq = NULL; - dev->feature_len = 0; - dev->num_vq = 0; - dev->running = false; - - /* - * Append to device list. Prepending to a single-linked list is - * easier, but the user expects the devices to be arranged on the bus - * in command-line order. The first network device on the command line - * is eth0, the first block device /dev/vda, etc. - */ - if (devices.lastdev) - devices.lastdev->next = dev; - else - devices.dev = dev; - devices.lastdev = dev; - - return dev; -} - -/* - * Our first setup routine is the console. It's a fairly simple device, but - * UNIX tty handling makes it uglier than it could be. - */ -static void setup_console(void) -{ - struct device *dev; - - /* If we can save the initial standard input settings... */ - if (tcgetattr(STDIN_FILENO, &orig_term) == 0) { - struct termios term = orig_term; - /* - * Then we turn off echo, line buffering and ^C etc: We want a - * raw input stream to the Guest. - */ - term.c_lflag &= ~(ISIG|ICANON|ECHO); - tcsetattr(STDIN_FILENO, TCSANOW, &term); - } - - dev = new_device("console", VIRTIO_ID_CONSOLE); - - /* We store the console state in dev->priv, and initialize it. */ - dev->priv = malloc(sizeof(struct console_abort)); - ((struct console_abort *)dev->priv)->count = 0; - - /* - * The console needs two virtqueues: the input then the output. When - * they put something the input queue, we make sure we're listening to - * stdin. When they put something in the output queue, we write it to - * stdout. - */ - add_virtqueue(dev, VIRTQUEUE_NUM, console_input); - add_virtqueue(dev, VIRTQUEUE_NUM, console_output); - - verbose("device %u: console\n", ++devices.device_num); -} -/*:*/ - -/*M:010 - * Inter-guest networking is an interesting area. Simplest is to have a - * --sharenet= option which opens or creates a named pipe. This can be - * used to send packets to another guest in a 1:1 manner. - * - * More sophisticated is to use one of the tools developed for project like UML - * to do networking. - * - * Faster is to do virtio bonding in kernel. Doing this 1:1 would be - * completely generic ("here's my vring, attach to your vring") and would work - * for any traffic. Of course, namespace and permissions issues need to be - * dealt with. A more sophisticated "multi-channel" virtio_net.c could hide - * multiple inter-guest channels behind one interface, although it would - * require some manner of hotplugging new virtio channels. - * - * Finally, we could use a virtio network switch in the kernel, ie. vhost. -:*/ - -static u32 str2ip(const char *ipaddr) -{ - unsigned int b[4]; - - if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4) - errx(1, "Failed to parse IP address '%s'", ipaddr); - return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3]; -} - -static void str2mac(const char *macaddr, unsigned char mac[6]) -{ - unsigned int m[6]; - if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x", - &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6) - errx(1, "Failed to parse mac address '%s'", macaddr); - mac[0] = m[0]; - mac[1] = m[1]; - mac[2] = m[2]; - mac[3] = m[3]; - mac[4] = m[4]; - mac[5] = m[5]; -} - -/* - * This code is "adapted" from libbridge: it attaches the Host end of the - * network device to the bridge device specified by the command line. - * - * This is yet another James Morris contribution (I'm an IP-level guy, so I - * dislike bridging), and I just try not to break it. - */ -static void add_to_bridge(int fd, const char *if_name, const char *br_name) -{ - int ifidx; - struct ifreq ifr; - - if (!*br_name) - errx(1, "must specify bridge name"); - - ifidx = if_nametoindex(if_name); - if (!ifidx) - errx(1, "interface %s does not exist!", if_name); - - strncpy(ifr.ifr_name, br_name, IFNAMSIZ); - ifr.ifr_name[IFNAMSIZ-1] = '\0'; - ifr.ifr_ifindex = ifidx; - if (ioctl(fd, SIOCBRADDIF, &ifr) < 0) - err(1, "can't add %s to bridge %s", if_name, br_name); -} - -/* - * This sets up the Host end of the network device with an IP address, brings - * it up so packets will flow, the copies the MAC address into the hwaddr - * pointer. - */ -static void configure_device(int fd, const char *tapif, u32 ipaddr) -{ - struct ifreq ifr; - struct sockaddr_in sin; - - memset(&ifr, 0, sizeof(ifr)); - strcpy(ifr.ifr_name, tapif); - - /* Don't read these incantations. Just cut & paste them like I did! */ - sin.sin_family = AF_INET; - sin.sin_addr.s_addr = htonl(ipaddr); - memcpy(&ifr.ifr_addr, &sin, sizeof(sin)); - if (ioctl(fd, SIOCSIFADDR, &ifr) != 0) - err(1, "Setting %s interface address", tapif); - ifr.ifr_flags = IFF_UP; - if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0) - err(1, "Bringing interface %s up", tapif); -} - -static int get_tun_device(char tapif[IFNAMSIZ]) -{ - struct ifreq ifr; - int netfd; - - /* Start with this zeroed. Messy but sure. */ - memset(&ifr, 0, sizeof(ifr)); - - /* - * We open the /dev/net/tun device and tell it we want a tap device. A - * tap device is like a tun device, only somehow different. To tell - * the truth, I completely blundered my way through this code, but it - * works now! - */ - netfd = open_or_die("/dev/net/tun", O_RDWR); - ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; - strcpy(ifr.ifr_name, "tap%d"); - if (ioctl(netfd, TUNSETIFF, &ifr) != 0) - err(1, "configuring /dev/net/tun"); - - if (ioctl(netfd, TUNSETOFFLOAD, - TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0) - err(1, "Could not set features for tun device"); - - /* - * We don't need checksums calculated for packets coming in this - * device: trust us! - */ - ioctl(netfd, TUNSETNOCSUM, 1); - - memcpy(tapif, ifr.ifr_name, IFNAMSIZ); - return netfd; -} - -/*L:195 - * Our network is a Host<->Guest network. This can either use bridging or - * routing, but the principle is the same: it uses the "tun" device to inject - * packets into the Host as if they came in from a normal network card. We - * just shunt packets between the Guest and the tun device. - */ -static void setup_tun_net(char *arg) -{ - struct device *dev; - struct net_info *net_info = malloc(sizeof(*net_info)); - int ipfd; - u32 ip = INADDR_ANY; - bool bridging = false; - char tapif[IFNAMSIZ], *p; - struct virtio_net_config conf; - - net_info->tunfd = get_tun_device(tapif); - - /* First we create a new network device. */ - dev = new_device("net", VIRTIO_ID_NET); - dev->priv = net_info; - - /* Network devices need a recv and a send queue, just like console. */ - add_virtqueue(dev, VIRTQUEUE_NUM, net_input); - add_virtqueue(dev, VIRTQUEUE_NUM, net_output); - - /* - * We need a socket to perform the magic network ioctls to bring up the - * tap interface, connect to the bridge etc. Any socket will do! - */ - ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP); - if (ipfd < 0) - err(1, "opening IP socket"); - - /* If the command line was --tunnet=bridge: do bridging. */ - if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) { - arg += strlen(BRIDGE_PFX); - bridging = true; - } - - /* A mac address may follow the bridge name or IP address */ - p = strchr(arg, ':'); - if (p) { - str2mac(p+1, conf.mac); - add_feature(dev, VIRTIO_NET_F_MAC); - *p = '\0'; - } - - /* arg is now either an IP address or a bridge name */ - if (bridging) - add_to_bridge(ipfd, tapif, arg); - else - ip = str2ip(arg); - - /* Set up the tun device. */ - configure_device(ipfd, tapif, ip); - - /* Expect Guest to handle everything except UFO */ - add_feature(dev, VIRTIO_NET_F_CSUM); - add_feature(dev, VIRTIO_NET_F_GUEST_CSUM); - add_feature(dev, VIRTIO_NET_F_GUEST_TSO4); - add_feature(dev, VIRTIO_NET_F_GUEST_TSO6); - add_feature(dev, VIRTIO_NET_F_GUEST_ECN); - add_feature(dev, VIRTIO_NET_F_HOST_TSO4); - add_feature(dev, VIRTIO_NET_F_HOST_TSO6); - add_feature(dev, VIRTIO_NET_F_HOST_ECN); - /* We handle indirect ring entries */ - add_feature(dev, VIRTIO_RING_F_INDIRECT_DESC); - set_config(dev, sizeof(conf), &conf); - - /* We don't need the socket any more; setup is done. */ - close(ipfd); - - devices.device_num++; - - if (bridging) - verbose("device %u: tun %s attached to bridge: %s\n", - devices.device_num, tapif, arg); - else - verbose("device %u: tun %s: %s\n", - devices.device_num, tapif, arg); -} -/*:*/ - -/* This hangs off device->priv. */ -struct vblk_info { - /* The size of the file. */ - off64_t len; - - /* The file descriptor for the file. */ - int fd; - -}; - -/*L:210 - * The Disk - * - * The disk only has one virtqueue, so it only has one thread. It is really - * simple: the Guest asks for a block number and we read or write that position - * in the file. - * - * Before we serviced each virtqueue in a separate thread, that was unacceptably - * slow: the Guest waits until the read is finished before running anything - * else, even if it could have been doing useful work. - * - * We could have used async I/O, except it's reputed to suck so hard that - * characters actually go missing from your code when you try to use it. - */ -static void blk_request(struct virtqueue *vq) -{ - struct vblk_info *vblk = vq->dev->priv; - unsigned int head, out_num, in_num, wlen; - int ret; - u8 *in; - struct virtio_blk_outhdr *out; - struct iovec iov[vq->vring.num]; - off64_t off; - - /* - * Get the next request, where we normally wait. It triggers the - * interrupt to acknowledge previously serviced requests (if any). - */ - head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - - /* - * Every block request should contain at least one output buffer - * (detailing the location on disk and the type of request) and one - * input buffer (to hold the result). - */ - if (out_num == 0 || in_num == 0) - errx(1, "Bad virtblk cmd %u out=%u in=%u", - head, out_num, in_num); - - out = convert(&iov[0], struct virtio_blk_outhdr); - in = convert(&iov[out_num+in_num-1], u8); - /* - * For historical reasons, block operations are expressed in 512 byte - * "sectors". - */ - off = out->sector * 512; - - /* - * In general the virtio block driver is allowed to try SCSI commands. - * It'd be nice if we supported eject, for example, but we don't. - */ - if (out->type & VIRTIO_BLK_T_SCSI_CMD) { - fprintf(stderr, "Scsi commands unsupported\n"); - *in = VIRTIO_BLK_S_UNSUPP; - wlen = sizeof(*in); - } else if (out->type & VIRTIO_BLK_T_OUT) { - /* - * Write - * - * Move to the right location in the block file. This can fail - * if they try to write past end. - */ - if (lseek64(vblk->fd, off, SEEK_SET) != off) - err(1, "Bad seek to sector %llu", out->sector); - - ret = writev(vblk->fd, iov+1, out_num-1); - verbose("WRITE to sector %llu: %i\n", out->sector, ret); - - /* - * Grr... Now we know how long the descriptor they sent was, we - * make sure they didn't try to write over the end of the block - * file (possibly extending it). - */ - if (ret > 0 && off + ret > vblk->len) { - /* Trim it back to the correct length */ - ftruncate64(vblk->fd, vblk->len); - /* Die, bad Guest, die. */ - errx(1, "Write past end %llu+%u", off, ret); - } - - wlen = sizeof(*in); - *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR); - } else if (out->type & VIRTIO_BLK_T_FLUSH) { - /* Flush */ - ret = fdatasync(vblk->fd); - verbose("FLUSH fdatasync: %i\n", ret); - wlen = sizeof(*in); - *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR); - } else { - /* - * Read - * - * Move to the right location in the block file. This can fail - * if they try to read past end. - */ - if (lseek64(vblk->fd, off, SEEK_SET) != off) - err(1, "Bad seek to sector %llu", out->sector); - - ret = readv(vblk->fd, iov+1, in_num-1); - verbose("READ from sector %llu: %i\n", out->sector, ret); - if (ret >= 0) { - wlen = sizeof(*in) + ret; - *in = VIRTIO_BLK_S_OK; - } else { - wlen = sizeof(*in); - *in = VIRTIO_BLK_S_IOERR; - } - } - - /* Finished that request. */ - add_used(vq, head, wlen); -} - -/*L:198 This actually sets up a virtual block device. */ -static void setup_block_file(const char *filename) -{ - struct device *dev; - struct vblk_info *vblk; - struct virtio_blk_config conf; - - /* Creat the device. */ - dev = new_device("block", VIRTIO_ID_BLOCK); - - /* The device has one virtqueue, where the Guest places requests. */ - add_virtqueue(dev, VIRTQUEUE_NUM, blk_request); - - /* Allocate the room for our own bookkeeping */ - vblk = dev->priv = malloc(sizeof(*vblk)); - - /* First we open the file and store the length. */ - vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE); - vblk->len = lseek64(vblk->fd, 0, SEEK_END); - - /* We support FLUSH. */ - add_feature(dev, VIRTIO_BLK_F_FLUSH); - - /* Tell Guest how many sectors this device has. */ - conf.capacity = cpu_to_le64(vblk->len / 512); - - /* - * Tell Guest not to put in too many descriptors at once: two are used - * for the in and out elements. - */ - add_feature(dev, VIRTIO_BLK_F_SEG_MAX); - conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2); - - /* Don't try to put whole struct: we have 8 bit limit. */ - set_config(dev, offsetof(struct virtio_blk_config, geometry), &conf); - - verbose("device %u: virtblock %llu sectors\n", - ++devices.device_num, le64_to_cpu(conf.capacity)); -} - -/*L:211 - * Our random number generator device reads from /dev/random into the Guest's - * input buffers. The usual case is that the Guest doesn't want random numbers - * and so has no buffers although /dev/random is still readable, whereas - * console is the reverse. - * - * The same logic applies, however. - */ -struct rng_info { - int rfd; -}; - -static void rng_input(struct virtqueue *vq) -{ - int len; - unsigned int head, in_num, out_num, totlen = 0; - struct rng_info *rng_info = vq->dev->priv; - struct iovec iov[vq->vring.num]; - - /* First we need a buffer from the Guests's virtqueue. */ - head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - if (out_num) - errx(1, "Output buffers in rng?"); - - /* - * Just like the console write, we loop to cover the whole iovec. - * In this case, short reads actually happen quite a bit. - */ - while (!iov_empty(iov, in_num)) { - len = readv(rng_info->rfd, iov, in_num); - if (len <= 0) - err(1, "Read from /dev/random gave %i", len); - iov_consume(iov, in_num, len); - totlen += len; - } - - /* Tell the Guest about the new input. */ - add_used(vq, head, totlen); -} - -/*L:199 - * This creates a "hardware" random number device for the Guest. - */ -static void setup_rng(void) -{ - struct device *dev; - struct rng_info *rng_info = malloc(sizeof(*rng_info)); - - /* Our device's privat info simply contains the /dev/random fd. */ - rng_info->rfd = open_or_die("/dev/random", O_RDONLY); - - /* Create the new device. */ - dev = new_device("rng", VIRTIO_ID_RNG); - dev->priv = rng_info; - - /* The device has one virtqueue, where the Guest places inbufs. */ - add_virtqueue(dev, VIRTQUEUE_NUM, rng_input); - - verbose("device %u: rng\n", devices.device_num++); -} -/* That's the end of device setup. */ - -/*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */ -static void __attribute__((noreturn)) restart_guest(void) -{ - unsigned int i; - - /* - * Since we don't track all open fds, we simply close everything beyond - * stderr. - */ - for (i = 3; i < FD_SETSIZE; i++) - close(i); - - /* Reset all the devices (kills all threads). */ - cleanup_devices(); - - execv(main_args[0], main_args); - err(1, "Could not exec %s", main_args[0]); -} - -/*L:220 - * Finally we reach the core of the Launcher which runs the Guest, serves - * its input and output, and finally, lays it to rest. - */ -static void __attribute__((noreturn)) run_guest(void) -{ - for (;;) { - unsigned long notify_addr; - int readval; - - /* We read from the /dev/lguest device to run the Guest. */ - readval = pread(lguest_fd, ¬ify_addr, - sizeof(notify_addr), cpu_id); - - /* One unsigned long means the Guest did HCALL_NOTIFY */ - if (readval == sizeof(notify_addr)) { - verbose("Notify on address %#lx\n", notify_addr); - handle_output(notify_addr); - /* ENOENT means the Guest died. Reading tells us why. */ - } else if (errno == ENOENT) { - char reason[1024] = { 0 }; - pread(lguest_fd, reason, sizeof(reason)-1, cpu_id); - errx(1, "%s", reason); - /* ERESTART means that we need to reboot the guest */ - } else if (errno == ERESTART) { - restart_guest(); - /* Anything else means a bug or incompatible change. */ - } else - err(1, "Running guest failed"); - } -} -/*L:240 - * This is the end of the Launcher. The good news: we are over halfway - * through! The bad news: the most fiendish part of the code still lies ahead - * of us. - * - * Are you ready? Take a deep breath and join me in the core of the Host, in - * "make Host". -:*/ - -static struct option opts[] = { - { "verbose", 0, NULL, 'v' }, - { "tunnet", 1, NULL, 't' }, - { "block", 1, NULL, 'b' }, - { "rng", 0, NULL, 'r' }, - { "initrd", 1, NULL, 'i' }, - { "username", 1, NULL, 'u' }, - { "chroot", 1, NULL, 'c' }, - { NULL }, -}; -static void usage(void) -{ - errx(1, "Usage: lguest [--verbose] " - "[--tunnet=(:|bridge::)\n" - "|--block=|--initrd=]...\n" - " vmlinux [args...]"); -} - -/*L:105 The main routine is where the real work begins: */ -int main(int argc, char *argv[]) -{ - /* Memory, code startpoint and size of the (optional) initrd. */ - unsigned long mem = 0, start, initrd_size = 0; - /* Two temporaries. */ - int i, c; - /* The boot information for the Guest. */ - struct boot_params *boot; - /* If they specify an initrd file to load. */ - const char *initrd_name = NULL; - - /* Password structure for initgroups/setres[gu]id */ - struct passwd *user_details = NULL; - - /* Directory to chroot to */ - char *chroot_path = NULL; - - /* Save the args: we "reboot" by execing ourselves again. */ - main_args = argv; - - /* - * First we initialize the device list. We keep a pointer to the last - * device, and the next interrupt number to use for devices (1: - * remember that 0 is used by the timer). - */ - devices.lastdev = NULL; - devices.next_irq = 1; - - /* We're CPU 0. In fact, that's the only CPU possible right now. */ - cpu_id = 0; - - /* - * We need to know how much memory so we can set up the device - * descriptor and memory pages for the devices as we parse the command - * line. So we quickly look through the arguments to find the amount - * of memory now. - */ - for (i = 1; i < argc; i++) { - if (argv[i][0] != '-') { - mem = atoi(argv[i]) * 1024 * 1024; - /* - * We start by mapping anonymous pages over all of - * guest-physical memory range. This fills it with 0, - * and ensures that the Guest won't be killed when it - * tries to access it. - */ - guest_base = map_zeroed_pages(mem / getpagesize() - + DEVICE_PAGES); - guest_limit = mem; - guest_max = mem + DEVICE_PAGES*getpagesize(); - devices.descpage = get_pages(1); - break; - } - } - - /* The options are fairly straight-forward */ - while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) { - switch (c) { - case 'v': - verbose = true; - break; - case 't': - setup_tun_net(optarg); - break; - case 'b': - setup_block_file(optarg); - break; - case 'r': - setup_rng(); - break; - case 'i': - initrd_name = optarg; - break; - case 'u': - user_details = getpwnam(optarg); - if (!user_details) - err(1, "getpwnam failed, incorrect username?"); - break; - case 'c': - chroot_path = optarg; - break; - default: - warnx("Unknown argument %s", argv[optind]); - usage(); - } - } - /* - * After the other arguments we expect memory and kernel image name, - * followed by command line arguments for the kernel. - */ - if (optind + 2 > argc) - usage(); - - verbose("Guest base is at %p\n", guest_base); - - /* We always have a console device */ - setup_console(); - - /* Now we load the kernel */ - start = load_kernel(open_or_die(argv[optind+1], O_RDONLY)); - - /* Boot information is stashed at physical address 0 */ - boot = from_guest_phys(0); - - /* Map the initrd image if requested (at top of physical memory) */ - if (initrd_name) { - initrd_size = load_initrd(initrd_name, mem); - /* - * These are the location in the Linux boot header where the - * start and size of the initrd are expected to be found. - */ - boot->hdr.ramdisk_image = mem - initrd_size; - boot->hdr.ramdisk_size = initrd_size; - /* The bootloader type 0xFF means "unknown"; that's OK. */ - boot->hdr.type_of_loader = 0xFF; - } - - /* - * The Linux boot header contains an "E820" memory map: ours is a - * simple, single region. - */ - boot->e820_entries = 1; - boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM }); - /* - * The boot header contains a command line pointer: we put the command - * line after the boot header. - */ - boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1); - /* We use a simple helper to copy the arguments separated by spaces. */ - concat((char *)(boot + 1), argv+optind+2); - - /* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */ - boot->hdr.kernel_alignment = 0x1000000; - - /* Boot protocol version: 2.07 supports the fields for lguest. */ - boot->hdr.version = 0x207; - - /* The hardware_subarch value of "1" tells the Guest it's an lguest. */ - boot->hdr.hardware_subarch = 1; - - /* Tell the entry path not to try to reload segment registers. */ - boot->hdr.loadflags |= KEEP_SEGMENTS; - - /* We tell the kernel to initialize the Guest. */ - tell_kernel(start); - - /* Ensure that we terminate if a device-servicing child dies. */ - signal(SIGCHLD, kill_launcher); - - /* If we exit via err(), this kills all the threads, restores tty. */ - atexit(cleanup_devices); - - /* If requested, chroot to a directory */ - if (chroot_path) { - if (chroot(chroot_path) != 0) - err(1, "chroot(\"%s\") failed", chroot_path); - - if (chdir("/") != 0) - err(1, "chdir(\"/\") failed"); - - verbose("chroot done\n"); - } - - /* If requested, drop privileges */ - if (user_details) { - uid_t u; - gid_t g; - - u = user_details->pw_uid; - g = user_details->pw_gid; - - if (initgroups(user_details->pw_name, g) != 0) - err(1, "initgroups failed"); - - if (setresgid(g, g, g) != 0) - err(1, "setresgid failed"); - - if (setresuid(u, u, u) != 0) - err(1, "setresuid failed"); - - verbose("Dropping privileges completed\n"); - } - - /* Finally, run the Guest. This doesn't return. */ - run_guest(); -} -/*:*/ - -/*M:999 - * Mastery is done: you now know everything I do. - * - * But surely you have seen code, features and bugs in your wanderings which - * you now yearn to attack? That is the real game, and I look forward to you - * patching and forking lguest into the Your-Name-Here-visor. - * - * Farewell, and good coding! - * Rusty Russell. - */ diff --git a/Documentation/virtual/lguest/lguest.txt b/Documentation/virtual/lguest/lguest.txt deleted file mode 100644 index bff0c554485..00000000000 --- a/Documentation/virtual/lguest/lguest.txt +++ /dev/null @@ -1,129 +0,0 @@ - __ - (___()'`; Rusty's Remarkably Unreliable Guide to Lguest - /, /` - or, A Young Coder's Illustrated Hypervisor - \\"--\\ http://lguest.ozlabs.org - -Lguest is designed to be a minimal 32-bit x86 hypervisor for the Linux kernel, -for Linux developers and users to experiment with virtualization with the -minimum of complexity. Nonetheless, it should have sufficient features to -make it useful for specific tasks, and, of course, you are encouraged to fork -and enhance it (see drivers/lguest/README). - -Features: - -- Kernel module which runs in a normal kernel. -- Simple I/O model for communication. -- Simple program to create new guests. -- Logo contains cute puppies: http://lguest.ozlabs.org - -Developer features: - -- Fun to hack on. -- No ABI: being tied to a specific kernel anyway, you can change anything. -- Many opportunities for improvement or feature implementation. - -Running Lguest: - -- The easiest way to run lguest is to use same kernel as guest and host. - You can configure them differently, but usually it's easiest not to. - - You will need to configure your kernel with the following options: - - "General setup": - "Prompt for development and/or incomplete code/drivers" = Y - (CONFIG_EXPERIMENTAL=y) - - "Processor type and features": - "Paravirtualized guest support" = Y - "Lguest guest support" = Y - "High Memory Support" = off/4GB - "Alignment value to which kernel should be aligned" = 0x100000 - (CONFIG_PARAVIRT=y, CONFIG_LGUEST_GUEST=y, CONFIG_HIGHMEM64G=n and - CONFIG_PHYSICAL_ALIGN=0x100000) - - "Device Drivers": - "Block devices" - "Virtio block driver (EXPERIMENTAL)" = M/Y - "Network device support" - "Universal TUN/TAP device driver support" = M/Y - "Virtio network driver (EXPERIMENTAL)" = M/Y - (CONFIG_VIRTIO_BLK=m, CONFIG_VIRTIO_NET=m and CONFIG_TUN=m) - - "Virtualization" - "Linux hypervisor example code" = M/Y - (CONFIG_LGUEST=m) - -- A tool called "lguest" is available in this directory: type "make" - to build it. If you didn't build your kernel in-tree, use "make - O=". - -- Create or find a root disk image. There are several useful ones - around, such as the xm-test tiny root image at - http://xm-test.xensource.com/ramdisks/initrd-1.1-i386.img - - For more serious work, I usually use a distribution ISO image and - install it under qemu, then make multiple copies: - - dd if=/dev/zero of=rootfile bs=1M count=2048 - qemu -cdrom image.iso -hda rootfile -net user -net nic -boot d - - Make sure that you install a getty on /dev/hvc0 if you want to log in on the - console! - -- "modprobe lg" if you built it as a module. - -- Run an lguest as root: - - Documentation/virtual/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \ - --block=rootfile root=/dev/vda - - Explanation: - 64: the amount of memory to use, in MB. - - vmlinux: the kernel image found in the top of your build directory. You - can also use a standard bzImage. - - --tunnet=192.168.19.1: configures a "tap" device for networking with this - IP address. - - --block=rootfile: a file or block device which becomes /dev/vda - inside the guest. - - root=/dev/vda: this (and anything else on the command line) are - kernel boot parameters. - -- Configuring networking. I usually have the host masquerade, using - "iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE" and "echo 1 > - /proc/sys/net/ipv4/ip_forward". In this example, I would configure - eth0 inside the guest at 192.168.19.2. - - Another method is to bridge the tap device to an external interface - using --tunnet=bridge:, and perhaps run dhcp on the guest - to obtain an IP address. The bridge needs to be configured first: - this option simply adds the tap interface to it. - - A simple example on my system: - - ifconfig eth0 0.0.0.0 - brctl addbr lg0 - ifconfig lg0 up - brctl addif lg0 eth0 - dhclient lg0 - - Then use --tunnet=bridge:lg0 when launching the guest. - - See: - - http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge - - for general information on how to get bridging to work. - -- Random number generation. Using the --rng option will provide a - /dev/hwrng in the guest that will read from the host's /dev/random. - Use this option in conjunction with rng-tools (see ../hw_random.txt) - to provide entropy to the guest kernel's /dev/random. - -There is a helpful mailing list at http://ozlabs.org/mailman/listinfo/lguest - -Good luck! -Rusty Russell rusty@rustcorp.com.au. diff --git a/drivers/lguest/Makefile b/drivers/lguest/Makefile index 8ac947c7e7c..c4197503900 100644 --- a/drivers/lguest/Makefile +++ b/drivers/lguest/Makefile @@ -18,7 +18,7 @@ Mastery: PREFIX=M Beer: @for f in Preparation Guest Drivers Launcher Host Switcher Mastery; do echo "{==- $$f -==}"; make -s $$f; done; echo "{==-==}" Preparation Preparation! Guest Drivers Launcher Host Switcher Mastery: - @sh ../../Documentation/virtual/lguest/extract $(PREFIX) `find ../../* -name '*.[chS]' -wholename '*lguest*'` + @sh ../../tools/lguest/extract $(PREFIX) `find ../../* -name '*.[chS]' -wholename '*lguest*'` Puppy: @clear @printf " __ \n (___()'\`;\n /, /\`\n \\\\\\\"--\\\\\\ \n" diff --git a/tools/lguest/.gitignore b/tools/lguest/.gitignore new file mode 100644 index 00000000000..115587fd5f6 --- /dev/null +++ b/tools/lguest/.gitignore @@ -0,0 +1 @@ +lguest diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile new file mode 100644 index 00000000000..0ac34206f7a --- /dev/null +++ b/tools/lguest/Makefile @@ -0,0 +1,8 @@ +# This creates the demonstration utility "lguest" which runs a Linux guest. +# Missing headers? Add "-I../../../include -I../../../arch/x86/include" +CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE + +all: lguest + +clean: + rm -f lguest diff --git a/tools/lguest/extract b/tools/lguest/extract new file mode 100644 index 00000000000..7730bb6e4b9 --- /dev/null +++ b/tools/lguest/extract @@ -0,0 +1,58 @@ +#! /bin/sh + +set -e + +PREFIX=$1 +shift + +trap 'rm -r $TMPDIR' 0 +TMPDIR=`mktemp -d` + +exec 3>/dev/null +for f; do + while IFS=" +" read -r LINE; do + case "$LINE" in + *$PREFIX:[0-9]*:\**) + NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` + if [ -f $TMPDIR/$NUM ]; then + echo "$TMPDIR/$NUM already exits prior to $f" + exit 1 + fi + exec 3>>$TMPDIR/$NUM + echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM + /bin/echo "$LINE" | sed -e "s/$PREFIX:[0-9]*//" -e "s/:\*/*/" >&3 + ;; + *$PREFIX:[0-9]*) + NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` + if [ -f $TMPDIR/$NUM ]; then + echo "$TMPDIR/$NUM already exits prior to $f" + exit 1 + fi + exec 3>>$TMPDIR/$NUM + echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM + /bin/echo "$LINE" | sed "s/$PREFIX:[0-9]*//" >&3 + ;; + *:\**) + /bin/echo "$LINE" | sed -e "s/:\*/*/" -e "s,/\*\*/,," >&3 + echo >&3 + exec 3>/dev/null + ;; + *) + /bin/echo "$LINE" >&3 + ;; + esac + done < $f + echo >&3 + exec 3>/dev/null +done + +LASTFILE="" +for f in $TMPDIR/*; do + if [ "$LASTFILE" != $(cat $TMPDIR/.$(basename $f) ) ]; then + LASTFILE=$(cat $TMPDIR/.$(basename $f) ) + echo "[ $LASTFILE ]" + fi + cat $f +done + diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c new file mode 100644 index 00000000000..f759f4f097c --- /dev/null +++ b/tools/lguest/lguest.c @@ -0,0 +1,2065 @@ +/*P:100 + * This is the Launcher code, a simple program which lays out the "physical" + * memory for the new Guest by mapping the kernel image and the virtual + * devices, then opens /dev/lguest to tell the kernel about the Guest and + * control it. +:*/ +#define _LARGEFILE64_SOURCE +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include "../../include/linux/lguest_launcher.h" +/*L:110 + * We can ignore the 43 include files we need for this program, but I do want + * to draw attention to the use of kernel-style types. + * + * As Linus said, "C is a Spartan language, and so should your naming be." I + * like these abbreviations, so we define them here. Note that u64 is always + * unsigned long long, which works on all Linux systems: this means that we can + * use %llu in printf for any u64. + */ +typedef unsigned long long u64; +typedef uint32_t u32; +typedef uint16_t u16; +typedef uint8_t u8; +/*:*/ + +#define BRIDGE_PFX "bridge:" +#ifndef SIOCBRADDIF +#define SIOCBRADDIF 0x89a2 /* add interface to bridge */ +#endif +/* We can have up to 256 pages for devices. */ +#define DEVICE_PAGES 256 +/* This will occupy 3 pages: it must be a power of 2. */ +#define VIRTQUEUE_NUM 256 + +/*L:120 + * verbose is both a global flag and a macro. The C preprocessor allows + * this, and although I wouldn't recommend it, it works quite nicely here. + */ +static bool verbose; +#define verbose(args...) \ + do { if (verbose) printf(args); } while(0) +/*:*/ + +/* The pointer to the start of guest memory. */ +static void *guest_base; +/* The maximum guest physical address allowed, and maximum possible. */ +static unsigned long guest_limit, guest_max; +/* The /dev/lguest file descriptor. */ +static int lguest_fd; + +/* a per-cpu variable indicating whose vcpu is currently running */ +static unsigned int __thread cpu_id; + +/* This is our list of devices. */ +struct device_list { + /* Counter to assign interrupt numbers. */ + unsigned int next_irq; + + /* Counter to print out convenient device numbers. */ + unsigned int device_num; + + /* The descriptor page for the devices. */ + u8 *descpage; + + /* A single linked list of devices. */ + struct device *dev; + /* And a pointer to the last device for easy append. */ + struct device *lastdev; +}; + +/* The list of Guest devices, based on command line arguments. */ +static struct device_list devices; + +/* The device structure describes a single device. */ +struct device { + /* The linked-list pointer. */ + struct device *next; + + /* The device's descriptor, as mapped into the Guest. */ + struct lguest_device_desc *desc; + + /* We can't trust desc values once Guest has booted: we use these. */ + unsigned int feature_len; + unsigned int num_vq; + + /* The name of this device, for --verbose. */ + const char *name; + + /* Any queues attached to this device */ + struct virtqueue *vq; + + /* Is it operational */ + bool running; + + /* Device-specific data. */ + void *priv; +}; + +/* The virtqueue structure describes a queue attached to a device. */ +struct virtqueue { + struct virtqueue *next; + + /* Which device owns me. */ + struct device *dev; + + /* The configuration for this queue. */ + struct lguest_vqconfig config; + + /* The actual ring of buffers. */ + struct vring vring; + + /* Last available index we saw. */ + u16 last_avail_idx; + + /* How many are used since we sent last irq? */ + unsigned int pending_used; + + /* Eventfd where Guest notifications arrive. */ + int eventfd; + + /* Function for the thread which is servicing this virtqueue. */ + void (*service)(struct virtqueue *vq); + pid_t thread; +}; + +/* Remember the arguments to the program so we can "reboot" */ +static char **main_args; + +/* The original tty settings to restore on exit. */ +static struct termios orig_term; + +/* + * We have to be careful with barriers: our devices are all run in separate + * threads and so we need to make sure that changes visible to the Guest happen + * in precise order. + */ +#define wmb() __asm__ __volatile__("" : : : "memory") +#define mb() __asm__ __volatile__("" : : : "memory") + +/* + * Convert an iovec element to the given type. + * + * This is a fairly ugly trick: we need to know the size of the type and + * alignment requirement to check the pointer is kosher. It's also nice to + * have the name of the type in case we report failure. + * + * Typing those three things all the time is cumbersome and error prone, so we + * have a macro which sets them all up and passes to the real function. + */ +#define convert(iov, type) \ + ((type *)_convert((iov), sizeof(type), __alignof__(type), #type)) + +static void *_convert(struct iovec *iov, size_t size, size_t align, + const char *name) +{ + if (iov->iov_len != size) + errx(1, "Bad iovec size %zu for %s", iov->iov_len, name); + if ((unsigned long)iov->iov_base % align != 0) + errx(1, "Bad alignment %p for %s", iov->iov_base, name); + return iov->iov_base; +} + +/* Wrapper for the last available index. Makes it easier to change. */ +#define lg_last_avail(vq) ((vq)->last_avail_idx) + +/* + * The virtio configuration space is defined to be little-endian. x86 is + * little-endian too, but it's nice to be explicit so we have these helpers. + */ +#define cpu_to_le16(v16) (v16) +#define cpu_to_le32(v32) (v32) +#define cpu_to_le64(v64) (v64) +#define le16_to_cpu(v16) (v16) +#define le32_to_cpu(v32) (v32) +#define le64_to_cpu(v64) (v64) + +/* Is this iovec empty? */ +static bool iov_empty(const struct iovec iov[], unsigned int num_iov) +{ + unsigned int i; + + for (i = 0; i < num_iov; i++) + if (iov[i].iov_len) + return false; + return true; +} + +/* Take len bytes from the front of this iovec. */ +static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len) +{ + unsigned int i; + + for (i = 0; i < num_iov; i++) { + unsigned int used; + + used = iov[i].iov_len < len ? iov[i].iov_len : len; + iov[i].iov_base += used; + iov[i].iov_len -= used; + len -= used; + } + assert(len == 0); +} + +/* The device virtqueue descriptors are followed by feature bitmasks. */ +static u8 *get_feature_bits(struct device *dev) +{ + return (u8 *)(dev->desc + 1) + + dev->num_vq * sizeof(struct lguest_vqconfig); +} + +/*L:100 + * The Launcher code itself takes us out into userspace, that scary place where + * pointers run wild and free! Unfortunately, like most userspace programs, + * it's quite boring (which is why everyone likes to hack on the kernel!). + * Perhaps if you make up an Lguest Drinking Game at this point, it will get + * you through this section. Or, maybe not. + * + * The Launcher sets up a big chunk of memory to be the Guest's "physical" + * memory and stores it in "guest_base". In other words, Guest physical == + * Launcher virtual with an offset. + * + * This can be tough to get your head around, but usually it just means that we + * use these trivial conversion functions when the Guest gives us its + * "physical" addresses: + */ +static void *from_guest_phys(unsigned long addr) +{ + return guest_base + addr; +} + +static unsigned long to_guest_phys(const void *addr) +{ + return (addr - guest_base); +} + +/*L:130 + * Loading the Kernel. + * + * We start with couple of simple helper routines. open_or_die() avoids + * error-checking code cluttering the callers: + */ +static int open_or_die(const char *name, int flags) +{ + int fd = open(name, flags); + if (fd < 0) + err(1, "Failed to open %s", name); + return fd; +} + +/* map_zeroed_pages() takes a number of pages. */ +static void *map_zeroed_pages(unsigned int num) +{ + int fd = open_or_die("/dev/zero", O_RDONLY); + void *addr; + + /* + * We use a private mapping (ie. if we write to the page, it will be + * copied). We allocate an extra two pages PROT_NONE to act as guard + * pages against read/write attempts that exceed allocated space. + */ + addr = mmap(NULL, getpagesize() * (num+2), + PROT_NONE, MAP_PRIVATE, fd, 0); + + if (addr == MAP_FAILED) + err(1, "Mmapping %u pages of /dev/zero", num); + + if (mprotect(addr + getpagesize(), getpagesize() * num, + PROT_READ|PROT_WRITE) == -1) + err(1, "mprotect rw %u pages failed", num); + + /* + * One neat mmap feature is that you can close the fd, and it + * stays mapped. + */ + close(fd); + + /* Return address after PROT_NONE page */ + return addr + getpagesize(); +} + +/* Get some more pages for a device. */ +static void *get_pages(unsigned int num) +{ + void *addr = from_guest_phys(guest_limit); + + guest_limit += num * getpagesize(); + if (guest_limit > guest_max) + errx(1, "Not enough memory for devices"); + return addr; +} + +/* + * This routine is used to load the kernel or initrd. It tries mmap, but if + * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries), + * it falls back to reading the memory in. + */ +static void map_at(int fd, void *addr, unsigned long offset, unsigned long len) +{ + ssize_t r; + + /* + * We map writable even though for some segments are marked read-only. + * The kernel really wants to be writable: it patches its own + * instructions. + * + * MAP_PRIVATE means that the page won't be copied until a write is + * done to it. This allows us to share untouched memory between + * Guests. + */ + if (mmap(addr, len, PROT_READ|PROT_WRITE, + MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED) + return; + + /* pread does a seek and a read in one shot: saves a few lines. */ + r = pread(fd, addr, len, offset); + if (r != len) + err(1, "Reading offset %lu len %lu gave %zi", offset, len, r); +} + +/* + * This routine takes an open vmlinux image, which is in ELF, and maps it into + * the Guest memory. ELF = Embedded Linking Format, which is the format used + * by all modern binaries on Linux including the kernel. + * + * The ELF headers give *two* addresses: a physical address, and a virtual + * address. We use the physical address; the Guest will map itself to the + * virtual address. + * + * We return the starting address. + */ +static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) +{ + Elf32_Phdr phdr[ehdr->e_phnum]; + unsigned int i; + + /* + * Sanity checks on the main ELF header: an x86 executable with a + * reasonable number of correctly-sized program headers. + */ + if (ehdr->e_type != ET_EXEC + || ehdr->e_machine != EM_386 + || ehdr->e_phentsize != sizeof(Elf32_Phdr) + || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr)) + errx(1, "Malformed elf header"); + + /* + * An ELF executable contains an ELF header and a number of "program" + * headers which indicate which parts ("segments") of the program to + * load where. + */ + + /* We read in all the program headers at once: */ + if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0) + err(1, "Seeking to program headers"); + if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr)) + err(1, "Reading program headers"); + + /* + * Try all the headers: there are usually only three. A read-only one, + * a read-write one, and a "note" section which we don't load. + */ + for (i = 0; i < ehdr->e_phnum; i++) { + /* If this isn't a loadable segment, we ignore it */ + if (phdr[i].p_type != PT_LOAD) + continue; + + verbose("Section %i: size %i addr %p\n", + i, phdr[i].p_memsz, (void *)phdr[i].p_paddr); + + /* We map this section of the file at its physical address. */ + map_at(elf_fd, from_guest_phys(phdr[i].p_paddr), + phdr[i].p_offset, phdr[i].p_filesz); + } + + /* The entry point is given in the ELF header. */ + return ehdr->e_entry; +} + +/*L:150 + * A bzImage, unlike an ELF file, is not meant to be loaded. You're supposed + * to jump into it and it will unpack itself. We used to have to perform some + * hairy magic because the unpacking code scared me. + * + * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote + * a small patch to jump over the tricky bits in the Guest, so now we just read + * the funky header so we know where in the file to load, and away we go! + */ +static unsigned long load_bzimage(int fd) +{ + struct boot_params boot; + int r; + /* Modern bzImages get loaded at 1M. */ + void *p = from_guest_phys(0x100000); + + /* + * Go back to the start of the file and read the header. It should be + * a Linux boot header (see Documentation/x86/boot.txt) + */ + lseek(fd, 0, SEEK_SET); + read(fd, &boot, sizeof(boot)); + + /* Inside the setup_hdr, we expect the magic "HdrS" */ + if (memcmp(&boot.hdr.header, "HdrS", 4) != 0) + errx(1, "This doesn't look like a bzImage to me"); + + /* Skip over the extra sectors of the header. */ + lseek(fd, (boot.hdr.setup_sects+1) * 512, SEEK_SET); + + /* Now read everything into memory. in nice big chunks. */ + while ((r = read(fd, p, 65536)) > 0) + p += r; + + /* Finally, code32_start tells us where to enter the kernel. */ + return boot.hdr.code32_start; +} + +/*L:140 + * Loading the kernel is easy when it's a "vmlinux", but most kernels + * come wrapped up in the self-decompressing "bzImage" format. With a little + * work, we can load those, too. + */ +static unsigned long load_kernel(int fd) +{ + Elf32_Ehdr hdr; + + /* Read in the first few bytes. */ + if (read(fd, &hdr, sizeof(hdr)) != sizeof(hdr)) + err(1, "Reading kernel"); + + /* If it's an ELF file, it starts with "\177ELF" */ + if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0) + return map_elf(fd, &hdr); + + /* Otherwise we assume it's a bzImage, and try to load it. */ + return load_bzimage(fd); +} + +/* + * This is a trivial little helper to align pages. Andi Kleen hated it because + * it calls getpagesize() twice: "it's dumb code." + * + * Kernel guys get really het up about optimization, even when it's not + * necessary. I leave this code as a reaction against that. + */ +static inline unsigned long page_align(unsigned long addr) +{ + /* Add upwards and truncate downwards. */ + return ((addr + getpagesize()-1) & ~(getpagesize()-1)); +} + +/*L:180 + * An "initial ram disk" is a disk image loaded into memory along with the + * kernel which the kernel can use to boot from without needing any drivers. + * Most distributions now use this as standard: the initrd contains the code to + * load the appropriate driver modules for the current machine. + * + * Importantly, James Morris works for RedHat, and Fedora uses initrds for its + * kernels. He sent me this (and tells me when I break it). + */ +static unsigned long load_initrd(const char *name, unsigned long mem) +{ + int ifd; + struct stat st; + unsigned long len; + + ifd = open_or_die(name, O_RDONLY); + /* fstat() is needed to get the file size. */ + if (fstat(ifd, &st) < 0) + err(1, "fstat() on initrd '%s'", name); + + /* + * We map the initrd at the top of memory, but mmap wants it to be + * page-aligned, so we round the size up for that. + */ + len = page_align(st.st_size); + map_at(ifd, from_guest_phys(mem - len), 0, st.st_size); + /* + * Once a file is mapped, you can close the file descriptor. It's a + * little odd, but quite useful. + */ + close(ifd); + verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len); + + /* We return the initrd size. */ + return len; +} +/*:*/ + +/* + * Simple routine to roll all the commandline arguments together with spaces + * between them. + */ +static void concat(char *dst, char *args[]) +{ + unsigned int i, len = 0; + + for (i = 0; args[i]; i++) { + if (i) { + strcat(dst+len, " "); + len++; + } + strcpy(dst+len, args[i]); + len += strlen(args[i]); + } + /* In case it's empty. */ + dst[len] = '\0'; +} + +/*L:185 + * This is where we actually tell the kernel to initialize the Guest. We + * saw the arguments it expects when we looked at initialize() in lguest_user.c: + * the base of Guest "physical" memory, the top physical page to allow and the + * entry point for the Guest. + */ +static void tell_kernel(unsigned long start) +{ + unsigned long args[] = { LHREQ_INITIALIZE, + (unsigned long)guest_base, + guest_limit / getpagesize(), start }; + verbose("Guest: %p - %p (%#lx)\n", + guest_base, guest_base + guest_limit, guest_limit); + lguest_fd = open_or_die("/dev/lguest", O_RDWR); + if (write(lguest_fd, args, sizeof(args)) < 0) + err(1, "Writing to /dev/lguest"); +} +/*:*/ + +/*L:200 + * Device Handling. + * + * When the Guest gives us a buffer, it sends an array of addresses and sizes. + * We need to make sure it's not trying to reach into the Launcher itself, so + * we have a convenient routine which checks it and exits with an error message + * if something funny is going on: + */ +static void *_check_pointer(unsigned long addr, unsigned int size, + unsigned int line) +{ + /* + * Check if the requested address and size exceeds the allocated memory, + * or addr + size wraps around. + */ + if ((addr + size) > guest_limit || (addr + size) < addr) + errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr); + /* + * We return a pointer for the caller's convenience, now we know it's + * safe to use. + */ + return from_guest_phys(addr); +} +/* A macro which transparently hands the line number to the real function. */ +#define check_pointer(addr,size) _check_pointer(addr, size, __LINE__) + +/* + * Each buffer in the virtqueues is actually a chain of descriptors. This + * function returns the next descriptor in the chain, or vq->vring.num if we're + * at the end. + */ +static unsigned next_desc(struct vring_desc *desc, + unsigned int i, unsigned int max) +{ + unsigned int next; + + /* If this descriptor says it doesn't chain, we're done. */ + if (!(desc[i].flags & VRING_DESC_F_NEXT)) + return max; + + /* Check they're not leading us off end of descriptors. */ + next = desc[i].next; + /* Make sure compiler knows to grab that: we don't want it changing! */ + wmb(); + + if (next >= max) + errx(1, "Desc next is %u", next); + + return next; +} + +/* + * This actually sends the interrupt for this virtqueue, if we've used a + * buffer. + */ +static void trigger_irq(struct virtqueue *vq) +{ + unsigned long buf[] = { LHREQ_IRQ, vq->config.irq }; + + /* Don't inform them if nothing used. */ + if (!vq->pending_used) + return; + vq->pending_used = 0; + + /* If they don't want an interrupt, don't send one... */ + if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) { + return; + } + + /* Send the Guest an interrupt tell them we used something up. */ + if (write(lguest_fd, buf, sizeof(buf)) != 0) + err(1, "Triggering irq %i", vq->config.irq); +} + +/* + * This looks in the virtqueue for the first available buffer, and converts + * it to an iovec for convenient access. Since descriptors consist of some + * number of output then some number of input descriptors, it's actually two + * iovecs, but we pack them into one and note how many of each there were. + * + * This function waits if necessary, and returns the descriptor number found. + */ +static unsigned wait_for_vq_desc(struct virtqueue *vq, + struct iovec iov[], + unsigned int *out_num, unsigned int *in_num) +{ + unsigned int i, head, max; + struct vring_desc *desc; + u16 last_avail = lg_last_avail(vq); + + /* There's nothing available? */ + while (last_avail == vq->vring.avail->idx) { + u64 event; + + /* + * Since we're about to sleep, now is a good time to tell the + * Guest about what we've used up to now. + */ + trigger_irq(vq); + + /* OK, now we need to know about added descriptors. */ + vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; + + /* + * They could have slipped one in as we were doing that: make + * sure it's written, then check again. + */ + mb(); + if (last_avail != vq->vring.avail->idx) { + vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; + break; + } + + /* Nothing new? Wait for eventfd to tell us they refilled. */ + if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event)) + errx(1, "Event read failed?"); + + /* We don't need to be notified again. */ + vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; + } + + /* Check it isn't doing very strange things with descriptor numbers. */ + if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num) + errx(1, "Guest moved used index from %u to %u", + last_avail, vq->vring.avail->idx); + + /* + * Grab the next descriptor number they're advertising, and increment + * the index we've seen. + */ + head = vq->vring.avail->ring[last_avail % vq->vring.num]; + lg_last_avail(vq)++; + + /* If their number is silly, that's a fatal mistake. */ + if (head >= vq->vring.num) + errx(1, "Guest says index %u is available", head); + + /* When we start there are none of either input nor output. */ + *out_num = *in_num = 0; + + max = vq->vring.num; + desc = vq->vring.desc; + i = head; + + /* + * If this is an indirect entry, then this buffer contains a descriptor + * table which we handle as if it's any normal descriptor chain. + */ + if (desc[i].flags & VRING_DESC_F_INDIRECT) { + if (desc[i].len % sizeof(struct vring_desc)) + errx(1, "Invalid size for indirect buffer table"); + + max = desc[i].len / sizeof(struct vring_desc); + desc = check_pointer(desc[i].addr, desc[i].len); + i = 0; + } + + do { + /* Grab the first descriptor, and check it's OK. */ + iov[*out_num + *in_num].iov_len = desc[i].len; + iov[*out_num + *in_num].iov_base + = check_pointer(desc[i].addr, desc[i].len); + /* If this is an input descriptor, increment that count. */ + if (desc[i].flags & VRING_DESC_F_WRITE) + (*in_num)++; + else { + /* + * If it's an output descriptor, they're all supposed + * to come before any input descriptors. + */ + if (*in_num) + errx(1, "Descriptor has out after in"); + (*out_num)++; + } + + /* If we've got too many, that implies a descriptor loop. */ + if (*out_num + *in_num > max) + errx(1, "Looped descriptor"); + } while ((i = next_desc(desc, i, max)) != max); + + return head; +} + +/* + * After we've used one of their buffers, we tell the Guest about it. Sometime + * later we'll want to send them an interrupt using trigger_irq(); note that + * wait_for_vq_desc() does that for us if it has to wait. + */ +static void add_used(struct virtqueue *vq, unsigned int head, int len) +{ + struct vring_used_elem *used; + + /* + * The virtqueue contains a ring of used buffers. Get a pointer to the + * next entry in that used ring. + */ + used = &vq->vring.used->ring[vq->vring.used->idx % vq->vring.num]; + used->id = head; + used->len = len; + /* Make sure buffer is written before we update index. */ + wmb(); + vq->vring.used->idx++; + vq->pending_used++; +} + +/* And here's the combo meal deal. Supersize me! */ +static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len) +{ + add_used(vq, head, len); + trigger_irq(vq); +} + +/* + * The Console + * + * We associate some data with the console for our exit hack. + */ +struct console_abort { + /* How many times have they hit ^C? */ + int count; + /* When did they start? */ + struct timeval start; +}; + +/* This is the routine which handles console input (ie. stdin). */ +static void console_input(struct virtqueue *vq) +{ + int len; + unsigned int head, in_num, out_num; + struct console_abort *abort = vq->dev->priv; + struct iovec iov[vq->vring.num]; + + /* Make sure there's a descriptor available. */ + head = wait_for_vq_desc(vq, iov, &out_num, &in_num); + if (out_num) + errx(1, "Output buffers in console in queue?"); + + /* Read into it. This is where we usually wait. */ + len = readv(STDIN_FILENO, iov, in_num); + if (len <= 0) { + /* Ran out of input? */ + warnx("Failed to get console input, ignoring console."); + /* + * For simplicity, dying threads kill the whole Launcher. So + * just nap here. + */ + for (;;) + pause(); + } + + /* Tell the Guest we used a buffer. */ + add_used_and_trigger(vq, head, len); + + /* + * Three ^C within one second? Exit. + * + * This is such a hack, but works surprisingly well. Each ^C has to + * be in a buffer by itself, so they can't be too fast. But we check + * that we get three within about a second, so they can't be too + * slow. + */ + if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) { + abort->count = 0; + return; + } + + abort->count++; + if (abort->count == 1) + gettimeofday(&abort->start, NULL); + else if (abort->count == 3) { + struct timeval now; + gettimeofday(&now, NULL); + /* Kill all Launcher processes with SIGINT, like normal ^C */ + if (now.tv_sec <= abort->start.tv_sec+1) + kill(0, SIGINT); + abort->count = 0; + } +} + +/* This is the routine which handles console output (ie. stdout). */ +static void console_output(struct virtqueue *vq) +{ + unsigned int head, out, in; + struct iovec iov[vq->vring.num]; + + /* We usually wait in here, for the Guest to give us something. */ + head = wait_for_vq_desc(vq, iov, &out, &in); + if (in) + errx(1, "Input buffers in console output queue?"); + + /* writev can return a partial write, so we loop here. */ + while (!iov_empty(iov, out)) { + int len = writev(STDOUT_FILENO, iov, out); + if (len <= 0) { + warn("Write to stdout gave %i (%d)", len, errno); + break; + } + iov_consume(iov, out, len); + } + + /* + * We're finished with that buffer: if we're going to sleep, + * wait_for_vq_desc() will prod the Guest with an interrupt. + */ + add_used(vq, head, 0); +} + +/* + * The Network + * + * Handling output for network is also simple: we get all the output buffers + * and write them to /dev/net/tun. + */ +struct net_info { + int tunfd; +}; + +static void net_output(struct virtqueue *vq) +{ + struct net_info *net_info = vq->dev->priv; + unsigned int head, out, in; + struct iovec iov[vq->vring.num]; + + /* We usually wait in here for the Guest to give us a packet. */ + head = wait_for_vq_desc(vq, iov, &out, &in); + if (in) + errx(1, "Input buffers in net output queue?"); + /* + * Send the whole thing through to /dev/net/tun. It expects the exact + * same format: what a coincidence! + */ + if (writev(net_info->tunfd, iov, out) < 0) + warnx("Write to tun failed (%d)?", errno); + + /* + * Done with that one; wait_for_vq_desc() will send the interrupt if + * all packets are processed. + */ + add_used(vq, head, 0); +} + +/* + * Handling network input is a bit trickier, because I've tried to optimize it. + * + * First we have a helper routine which tells is if from this file descriptor + * (ie. the /dev/net/tun device) will block: + */ +static bool will_block(int fd) +{ + fd_set fdset; + struct timeval zero = { 0, 0 }; + FD_ZERO(&fdset); + FD_SET(fd, &fdset); + return select(fd+1, &fdset, NULL, NULL, &zero) != 1; +} + +/* + * This handles packets coming in from the tun device to our Guest. Like all + * service routines, it gets called again as soon as it returns, so you don't + * see a while(1) loop here. + */ +static void net_input(struct virtqueue *vq) +{ + int len; + unsigned int head, out, in; + struct iovec iov[vq->vring.num]; + struct net_info *net_info = vq->dev->priv; + + /* + * Get a descriptor to write an incoming packet into. This will also + * send an interrupt if they're out of descriptors. + */ + head = wait_for_vq_desc(vq, iov, &out, &in); + if (out) + errx(1, "Output buffers in net input queue?"); + + /* + * If it looks like we'll block reading from the tun device, send them + * an interrupt. + */ + if (vq->pending_used && will_block(net_info->tunfd)) + trigger_irq(vq); + + /* + * Read in the packet. This is where we normally wait (when there's no + * incoming network traffic). + */ + len = readv(net_info->tunfd, iov, in); + if (len <= 0) + warn("Failed to read from tun (%d).", errno); + + /* + * Mark that packet buffer as used, but don't interrupt here. We want + * to wait until we've done as much work as we can. + */ + add_used(vq, head, len); +} +/*:*/ + +/* This is the helper to create threads: run the service routine in a loop. */ +static int do_thread(void *_vq) +{ + struct virtqueue *vq = _vq; + + for (;;) + vq->service(vq); + return 0; +} + +/* + * When a child dies, we kill our entire process group with SIGTERM. This + * also has the side effect that the shell restores the console for us! + */ +static void kill_launcher(int signal) +{ + kill(0, SIGTERM); +} + +static void reset_device(struct device *dev) +{ + struct virtqueue *vq; + + verbose("Resetting device %s\n", dev->name); + + /* Clear any features they've acked. */ + memset(get_feature_bits(dev) + dev->feature_len, 0, dev->feature_len); + + /* We're going to be explicitly killing threads, so ignore them. */ + signal(SIGCHLD, SIG_IGN); + + /* Zero out the virtqueues, get rid of their threads */ + for (vq = dev->vq; vq; vq = vq->next) { + if (vq->thread != (pid_t)-1) { + kill(vq->thread, SIGTERM); + waitpid(vq->thread, NULL, 0); + vq->thread = (pid_t)-1; + } + memset(vq->vring.desc, 0, + vring_size(vq->config.num, LGUEST_VRING_ALIGN)); + lg_last_avail(vq) = 0; + } + dev->running = false; + + /* Now we care if threads die. */ + signal(SIGCHLD, (void *)kill_launcher); +} + +/*L:216 + * This actually creates the thread which services the virtqueue for a device. + */ +static void create_thread(struct virtqueue *vq) +{ + /* + * Create stack for thread. Since the stack grows upwards, we point + * the stack pointer to the end of this region. + */ + char *stack = malloc(32768); + unsigned long args[] = { LHREQ_EVENTFD, + vq->config.pfn*getpagesize(), 0 }; + + /* Create a zero-initialized eventfd. */ + vq->eventfd = eventfd(0, 0); + if (vq->eventfd < 0) + err(1, "Creating eventfd"); + args[2] = vq->eventfd; + + /* + * Attach an eventfd to this virtqueue: it will go off when the Guest + * does an LHCALL_NOTIFY for this vq. + */ + if (write(lguest_fd, &args, sizeof(args)) != 0) + err(1, "Attaching eventfd"); + + /* + * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so + * we get a signal if it dies. + */ + vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq); + if (vq->thread == (pid_t)-1) + err(1, "Creating clone"); + + /* We close our local copy now the child has it. */ + close(vq->eventfd); +} + +static void start_device(struct device *dev) +{ + unsigned int i; + struct virtqueue *vq; + + verbose("Device %s OK: offered", dev->name); + for (i = 0; i < dev->feature_len; i++) + verbose(" %02x", get_feature_bits(dev)[i]); + verbose(", accepted"); + for (i = 0; i < dev->feature_len; i++) + verbose(" %02x", get_feature_bits(dev) + [dev->feature_len+i]); + + for (vq = dev->vq; vq; vq = vq->next) { + if (vq->service) + create_thread(vq); + } + dev->running = true; +} + +static void cleanup_devices(void) +{ + struct device *dev; + + for (dev = devices.dev; dev; dev = dev->next) + reset_device(dev); + + /* If we saved off the original terminal settings, restore them now. */ + if (orig_term.c_lflag & (ISIG|ICANON|ECHO)) + tcsetattr(STDIN_FILENO, TCSANOW, &orig_term); +} + +/* When the Guest tells us they updated the status field, we handle it. */ +static void update_device_status(struct device *dev) +{ + /* A zero status is a reset, otherwise it's a set of flags. */ + if (dev->desc->status == 0) + reset_device(dev); + else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) { + warnx("Device %s configuration FAILED", dev->name); + if (dev->running) + reset_device(dev); + } else { + if (dev->running) + err(1, "Device %s features finalized twice", dev->name); + start_device(dev); + } +} + +/*L:215 + * This is the generic routine we call when the Guest uses LHCALL_NOTIFY. In + * particular, it's used to notify us of device status changes during boot. + */ +static void handle_output(unsigned long addr) +{ + struct device *i; + + /* Check each device. */ + for (i = devices.dev; i; i = i->next) { + struct virtqueue *vq; + + /* + * Notifications to device descriptors mean they updated the + * device status. + */ + if (from_guest_phys(addr) == i->desc) { + update_device_status(i); + return; + } + + /* Devices should not be used before features are finalized. */ + for (vq = i->vq; vq; vq = vq->next) { + if (addr != vq->config.pfn*getpagesize()) + continue; + errx(1, "Notification on %s before setup!", i->name); + } + } + + /* + * Early console write is done using notify on a nul-terminated string + * in Guest memory. It's also great for hacking debugging messages + * into a Guest. + */ + if (addr >= guest_limit) + errx(1, "Bad NOTIFY %#lx", addr); + + write(STDOUT_FILENO, from_guest_phys(addr), + strnlen(from_guest_phys(addr), guest_limit - addr)); +} + +/*L:190 + * Device Setup + * + * All devices need a descriptor so the Guest knows it exists, and a "struct + * device" so the Launcher can keep track of it. We have common helper + * routines to allocate and manage them. + */ + +/* + * The layout of the device page is a "struct lguest_device_desc" followed by a + * number of virtqueue descriptors, then two sets of feature bits, then an + * array of configuration bytes. This routine returns the configuration + * pointer. + */ +static u8 *device_config(const struct device *dev) +{ + return (void *)(dev->desc + 1) + + dev->num_vq * sizeof(struct lguest_vqconfig) + + dev->feature_len * 2; +} + +/* + * This routine allocates a new "struct lguest_device_desc" from descriptor + * table page just above the Guest's normal memory. It returns a pointer to + * that descriptor. + */ +static struct lguest_device_desc *new_dev_desc(u16 type) +{ + struct lguest_device_desc d = { .type = type }; + void *p; + + /* Figure out where the next device config is, based on the last one. */ + if (devices.lastdev) + p = device_config(devices.lastdev) + + devices.lastdev->desc->config_len; + else + p = devices.descpage; + + /* We only have one page for all the descriptors. */ + if (p + sizeof(d) > (void *)devices.descpage + getpagesize()) + errx(1, "Too many devices"); + + /* p might not be aligned, so we memcpy in. */ + return memcpy(p, &d, sizeof(d)); +} + +/* + * Each device descriptor is followed by the description of its virtqueues. We + * specify how many descriptors the virtqueue is to have. + */ +static void add_virtqueue(struct device *dev, unsigned int num_descs, + void (*service)(struct virtqueue *)) +{ + unsigned int pages; + struct virtqueue **i, *vq = malloc(sizeof(*vq)); + void *p; + + /* First we need some memory for this virtqueue. */ + pages = (vring_size(num_descs, LGUEST_VRING_ALIGN) + getpagesize() - 1) + / getpagesize(); + p = get_pages(pages); + + /* Initialize the virtqueue */ + vq->next = NULL; + vq->last_avail_idx = 0; + vq->dev = dev; + + /* + * This is the routine the service thread will run, and its Process ID + * once it's running. + */ + vq->service = service; + vq->thread = (pid_t)-1; + + /* Initialize the configuration. */ + vq->config.num = num_descs; + vq->config.irq = devices.next_irq++; + vq->config.pfn = to_guest_phys(p) / getpagesize(); + + /* Initialize the vring. */ + vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN); + + /* + * Append virtqueue to this device's descriptor. We use + * device_config() to get the end of the device's current virtqueues; + * we check that we haven't added any config or feature information + * yet, otherwise we'd be overwriting them. + */ + assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0); + memcpy(device_config(dev), &vq->config, sizeof(vq->config)); + dev->num_vq++; + dev->desc->num_vq++; + + verbose("Virtqueue page %#lx\n", to_guest_phys(p)); + + /* + * Add to tail of list, so dev->vq is first vq, dev->vq->next is + * second. + */ + for (i = &dev->vq; *i; i = &(*i)->next); + *i = vq; +} + +/* + * The first half of the feature bitmask is for us to advertise features. The + * second half is for the Guest to accept features. + */ +static void add_feature(struct device *dev, unsigned bit) +{ + u8 *features = get_feature_bits(dev); + + /* We can't extend the feature bits once we've added config bytes */ + if (dev->desc->feature_len <= bit / CHAR_BIT) { + assert(dev->desc->config_len == 0); + dev->feature_len = dev->desc->feature_len = (bit/CHAR_BIT) + 1; + } + + features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT)); +} + +/* + * This routine sets the configuration fields for an existing device's + * descriptor. It only works for the last device, but that's OK because that's + * how we use it. + */ +static void set_config(struct device *dev, unsigned len, const void *conf) +{ + /* Check we haven't overflowed our single page. */ + if (device_config(dev) + len > devices.descpage + getpagesize()) + errx(1, "Too many devices"); + + /* Copy in the config information, and store the length. */ + memcpy(device_config(dev), conf, len); + dev->desc->config_len = len; + + /* Size must fit in config_len field (8 bits)! */ + assert(dev->desc->config_len == len); +} + +/* + * This routine does all the creation and setup of a new device, including + * calling new_dev_desc() to allocate the descriptor and device memory. We + * don't actually start the service threads until later. + * + * See what I mean about userspace being boring? + */ +static struct device *new_device(const char *name, u16 type) +{ + struct device *dev = malloc(sizeof(*dev)); + + /* Now we populate the fields one at a time. */ + dev->desc = new_dev_desc(type); + dev->name = name; + dev->vq = NULL; + dev->feature_len = 0; + dev->num_vq = 0; + dev->running = false; + + /* + * Append to device list. Prepending to a single-linked list is + * easier, but the user expects the devices to be arranged on the bus + * in command-line order. The first network device on the command line + * is eth0, the first block device /dev/vda, etc. + */ + if (devices.lastdev) + devices.lastdev->next = dev; + else + devices.dev = dev; + devices.lastdev = dev; + + return dev; +} + +/* + * Our first setup routine is the console. It's a fairly simple device, but + * UNIX tty handling makes it uglier than it could be. + */ +static void setup_console(void) +{ + struct device *dev; + + /* If we can save the initial standard input settings... */ + if (tcgetattr(STDIN_FILENO, &orig_term) == 0) { + struct termios term = orig_term; + /* + * Then we turn off echo, line buffering and ^C etc: We want a + * raw input stream to the Guest. + */ + term.c_lflag &= ~(ISIG|ICANON|ECHO); + tcsetattr(STDIN_FILENO, TCSANOW, &term); + } + + dev = new_device("console", VIRTIO_ID_CONSOLE); + + /* We store the console state in dev->priv, and initialize it. */ + dev->priv = malloc(sizeof(struct console_abort)); + ((struct console_abort *)dev->priv)->count = 0; + + /* + * The console needs two virtqueues: the input then the output. When + * they put something the input queue, we make sure we're listening to + * stdin. When they put something in the output queue, we write it to + * stdout. + */ + add_virtqueue(dev, VIRTQUEUE_NUM, console_input); + add_virtqueue(dev, VIRTQUEUE_NUM, console_output); + + verbose("device %u: console\n", ++devices.device_num); +} +/*:*/ + +/*M:010 + * Inter-guest networking is an interesting area. Simplest is to have a + * --sharenet= option which opens or creates a named pipe. This can be + * used to send packets to another guest in a 1:1 manner. + * + * More sophisticated is to use one of the tools developed for project like UML + * to do networking. + * + * Faster is to do virtio bonding in kernel. Doing this 1:1 would be + * completely generic ("here's my vring, attach to your vring") and would work + * for any traffic. Of course, namespace and permissions issues need to be + * dealt with. A more sophisticated "multi-channel" virtio_net.c could hide + * multiple inter-guest channels behind one interface, although it would + * require some manner of hotplugging new virtio channels. + * + * Finally, we could use a virtio network switch in the kernel, ie. vhost. +:*/ + +static u32 str2ip(const char *ipaddr) +{ + unsigned int b[4]; + + if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4) + errx(1, "Failed to parse IP address '%s'", ipaddr); + return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3]; +} + +static void str2mac(const char *macaddr, unsigned char mac[6]) +{ + unsigned int m[6]; + if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x", + &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6) + errx(1, "Failed to parse mac address '%s'", macaddr); + mac[0] = m[0]; + mac[1] = m[1]; + mac[2] = m[2]; + mac[3] = m[3]; + mac[4] = m[4]; + mac[5] = m[5]; +} + +/* + * This code is "adapted" from libbridge: it attaches the Host end of the + * network device to the bridge device specified by the command line. + * + * This is yet another James Morris contribution (I'm an IP-level guy, so I + * dislike bridging), and I just try not to break it. + */ +static void add_to_bridge(int fd, const char *if_name, const char *br_name) +{ + int ifidx; + struct ifreq ifr; + + if (!*br_name) + errx(1, "must specify bridge name"); + + ifidx = if_nametoindex(if_name); + if (!ifidx) + errx(1, "interface %s does not exist!", if_name); + + strncpy(ifr.ifr_name, br_name, IFNAMSIZ); + ifr.ifr_name[IFNAMSIZ-1] = '\0'; + ifr.ifr_ifindex = ifidx; + if (ioctl(fd, SIOCBRADDIF, &ifr) < 0) + err(1, "can't add %s to bridge %s", if_name, br_name); +} + +/* + * This sets up the Host end of the network device with an IP address, brings + * it up so packets will flow, the copies the MAC address into the hwaddr + * pointer. + */ +static void configure_device(int fd, const char *tapif, u32 ipaddr) +{ + struct ifreq ifr; + struct sockaddr_in sin; + + memset(&ifr, 0, sizeof(ifr)); + strcpy(ifr.ifr_name, tapif); + + /* Don't read these incantations. Just cut & paste them like I did! */ + sin.sin_family = AF_INET; + sin.sin_addr.s_addr = htonl(ipaddr); + memcpy(&ifr.ifr_addr, &sin, sizeof(sin)); + if (ioctl(fd, SIOCSIFADDR, &ifr) != 0) + err(1, "Setting %s interface address", tapif); + ifr.ifr_flags = IFF_UP; + if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0) + err(1, "Bringing interface %s up", tapif); +} + +static int get_tun_device(char tapif[IFNAMSIZ]) +{ + struct ifreq ifr; + int netfd; + + /* Start with this zeroed. Messy but sure. */ + memset(&ifr, 0, sizeof(ifr)); + + /* + * We open the /dev/net/tun device and tell it we want a tap device. A + * tap device is like a tun device, only somehow different. To tell + * the truth, I completely blundered my way through this code, but it + * works now! + */ + netfd = open_or_die("/dev/net/tun", O_RDWR); + ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; + strcpy(ifr.ifr_name, "tap%d"); + if (ioctl(netfd, TUNSETIFF, &ifr) != 0) + err(1, "configuring /dev/net/tun"); + + if (ioctl(netfd, TUNSETOFFLOAD, + TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0) + err(1, "Could not set features for tun device"); + + /* + * We don't need checksums calculated for packets coming in this + * device: trust us! + */ + ioctl(netfd, TUNSETNOCSUM, 1); + + memcpy(tapif, ifr.ifr_name, IFNAMSIZ); + return netfd; +} + +/*L:195 + * Our network is a Host<->Guest network. This can either use bridging or + * routing, but the principle is the same: it uses the "tun" device to inject + * packets into the Host as if they came in from a normal network card. We + * just shunt packets between the Guest and the tun device. + */ +static void setup_tun_net(char *arg) +{ + struct device *dev; + struct net_info *net_info = malloc(sizeof(*net_info)); + int ipfd; + u32 ip = INADDR_ANY; + bool bridging = false; + char tapif[IFNAMSIZ], *p; + struct virtio_net_config conf; + + net_info->tunfd = get_tun_device(tapif); + + /* First we create a new network device. */ + dev = new_device("net", VIRTIO_ID_NET); + dev->priv = net_info; + + /* Network devices need a recv and a send queue, just like console. */ + add_virtqueue(dev, VIRTQUEUE_NUM, net_input); + add_virtqueue(dev, VIRTQUEUE_NUM, net_output); + + /* + * We need a socket to perform the magic network ioctls to bring up the + * tap interface, connect to the bridge etc. Any socket will do! + */ + ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP); + if (ipfd < 0) + err(1, "opening IP socket"); + + /* If the command line was --tunnet=bridge: do bridging. */ + if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) { + arg += strlen(BRIDGE_PFX); + bridging = true; + } + + /* A mac address may follow the bridge name or IP address */ + p = strchr(arg, ':'); + if (p) { + str2mac(p+1, conf.mac); + add_feature(dev, VIRTIO_NET_F_MAC); + *p = '\0'; + } + + /* arg is now either an IP address or a bridge name */ + if (bridging) + add_to_bridge(ipfd, tapif, arg); + else + ip = str2ip(arg); + + /* Set up the tun device. */ + configure_device(ipfd, tapif, ip); + + /* Expect Guest to handle everything except UFO */ + add_feature(dev, VIRTIO_NET_F_CSUM); + add_feature(dev, VIRTIO_NET_F_GUEST_CSUM); + add_feature(dev, VIRTIO_NET_F_GUEST_TSO4); + add_feature(dev, VIRTIO_NET_F_GUEST_TSO6); + add_feature(dev, VIRTIO_NET_F_GUEST_ECN); + add_feature(dev, VIRTIO_NET_F_HOST_TSO4); + add_feature(dev, VIRTIO_NET_F_HOST_TSO6); + add_feature(dev, VIRTIO_NET_F_HOST_ECN); + /* We handle indirect ring entries */ + add_feature(dev, VIRTIO_RING_F_INDIRECT_DESC); + set_config(dev, sizeof(conf), &conf); + + /* We don't need the socket any more; setup is done. */ + close(ipfd); + + devices.device_num++; + + if (bridging) + verbose("device %u: tun %s attached to bridge: %s\n", + devices.device_num, tapif, arg); + else + verbose("device %u: tun %s: %s\n", + devices.device_num, tapif, arg); +} +/*:*/ + +/* This hangs off device->priv. */ +struct vblk_info { + /* The size of the file. */ + off64_t len; + + /* The file descriptor for the file. */ + int fd; + +}; + +/*L:210 + * The Disk + * + * The disk only has one virtqueue, so it only has one thread. It is really + * simple: the Guest asks for a block number and we read or write that position + * in the file. + * + * Before we serviced each virtqueue in a separate thread, that was unacceptably + * slow: the Guest waits until the read is finished before running anything + * else, even if it could have been doing useful work. + * + * We could have used async I/O, except it's reputed to suck so hard that + * characters actually go missing from your code when you try to use it. + */ +static void blk_request(struct virtqueue *vq) +{ + struct vblk_info *vblk = vq->dev->priv; + unsigned int head, out_num, in_num, wlen; + int ret; + u8 *in; + struct virtio_blk_outhdr *out; + struct iovec iov[vq->vring.num]; + off64_t off; + + /* + * Get the next request, where we normally wait. It triggers the + * interrupt to acknowledge previously serviced requests (if any). + */ + head = wait_for_vq_desc(vq, iov, &out_num, &in_num); + + /* + * Every block request should contain at least one output buffer + * (detailing the location on disk and the type of request) and one + * input buffer (to hold the result). + */ + if (out_num == 0 || in_num == 0) + errx(1, "Bad virtblk cmd %u out=%u in=%u", + head, out_num, in_num); + + out = convert(&iov[0], struct virtio_blk_outhdr); + in = convert(&iov[out_num+in_num-1], u8); + /* + * For historical reasons, block operations are expressed in 512 byte + * "sectors". + */ + off = out->sector * 512; + + /* + * In general the virtio block driver is allowed to try SCSI commands. + * It'd be nice if we supported eject, for example, but we don't. + */ + if (out->type & VIRTIO_BLK_T_SCSI_CMD) { + fprintf(stderr, "Scsi commands unsupported\n"); + *in = VIRTIO_BLK_S_UNSUPP; + wlen = sizeof(*in); + } else if (out->type & VIRTIO_BLK_T_OUT) { + /* + * Write + * + * Move to the right location in the block file. This can fail + * if they try to write past end. + */ + if (lseek64(vblk->fd, off, SEEK_SET) != off) + err(1, "Bad seek to sector %llu", out->sector); + + ret = writev(vblk->fd, iov+1, out_num-1); + verbose("WRITE to sector %llu: %i\n", out->sector, ret); + + /* + * Grr... Now we know how long the descriptor they sent was, we + * make sure they didn't try to write over the end of the block + * file (possibly extending it). + */ + if (ret > 0 && off + ret > vblk->len) { + /* Trim it back to the correct length */ + ftruncate64(vblk->fd, vblk->len); + /* Die, bad Guest, die. */ + errx(1, "Write past end %llu+%u", off, ret); + } + + wlen = sizeof(*in); + *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR); + } else if (out->type & VIRTIO_BLK_T_FLUSH) { + /* Flush */ + ret = fdatasync(vblk->fd); + verbose("FLUSH fdatasync: %i\n", ret); + wlen = sizeof(*in); + *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR); + } else { + /* + * Read + * + * Move to the right location in the block file. This can fail + * if they try to read past end. + */ + if (lseek64(vblk->fd, off, SEEK_SET) != off) + err(1, "Bad seek to sector %llu", out->sector); + + ret = readv(vblk->fd, iov+1, in_num-1); + verbose("READ from sector %llu: %i\n", out->sector, ret); + if (ret >= 0) { + wlen = sizeof(*in) + ret; + *in = VIRTIO_BLK_S_OK; + } else { + wlen = sizeof(*in); + *in = VIRTIO_BLK_S_IOERR; + } + } + + /* Finished that request. */ + add_used(vq, head, wlen); +} + +/*L:198 This actually sets up a virtual block device. */ +static void setup_block_file(const char *filename) +{ + struct device *dev; + struct vblk_info *vblk; + struct virtio_blk_config conf; + + /* Creat the device. */ + dev = new_device("block", VIRTIO_ID_BLOCK); + + /* The device has one virtqueue, where the Guest places requests. */ + add_virtqueue(dev, VIRTQUEUE_NUM, blk_request); + + /* Allocate the room for our own bookkeeping */ + vblk = dev->priv = malloc(sizeof(*vblk)); + + /* First we open the file and store the length. */ + vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE); + vblk->len = lseek64(vblk->fd, 0, SEEK_END); + + /* We support FLUSH. */ + add_feature(dev, VIRTIO_BLK_F_FLUSH); + + /* Tell Guest how many sectors this device has. */ + conf.capacity = cpu_to_le64(vblk->len / 512); + + /* + * Tell Guest not to put in too many descriptors at once: two are used + * for the in and out elements. + */ + add_feature(dev, VIRTIO_BLK_F_SEG_MAX); + conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2); + + /* Don't try to put whole struct: we have 8 bit limit. */ + set_config(dev, offsetof(struct virtio_blk_config, geometry), &conf); + + verbose("device %u: virtblock %llu sectors\n", + ++devices.device_num, le64_to_cpu(conf.capacity)); +} + +/*L:211 + * Our random number generator device reads from /dev/random into the Guest's + * input buffers. The usual case is that the Guest doesn't want random numbers + * and so has no buffers although /dev/random is still readable, whereas + * console is the reverse. + * + * The same logic applies, however. + */ +struct rng_info { + int rfd; +}; + +static void rng_input(struct virtqueue *vq) +{ + int len; + unsigned int head, in_num, out_num, totlen = 0; + struct rng_info *rng_info = vq->dev->priv; + struct iovec iov[vq->vring.num]; + + /* First we need a buffer from the Guests's virtqueue. */ + head = wait_for_vq_desc(vq, iov, &out_num, &in_num); + if (out_num) + errx(1, "Output buffers in rng?"); + + /* + * Just like the console write, we loop to cover the whole iovec. + * In this case, short reads actually happen quite a bit. + */ + while (!iov_empty(iov, in_num)) { + len = readv(rng_info->rfd, iov, in_num); + if (len <= 0) + err(1, "Read from /dev/random gave %i", len); + iov_consume(iov, in_num, len); + totlen += len; + } + + /* Tell the Guest about the new input. */ + add_used(vq, head, totlen); +} + +/*L:199 + * This creates a "hardware" random number device for the Guest. + */ +static void setup_rng(void) +{ + struct device *dev; + struct rng_info *rng_info = malloc(sizeof(*rng_info)); + + /* Our device's privat info simply contains the /dev/random fd. */ + rng_info->rfd = open_or_die("/dev/random", O_RDONLY); + + /* Create the new device. */ + dev = new_device("rng", VIRTIO_ID_RNG); + dev->priv = rng_info; + + /* The device has one virtqueue, where the Guest places inbufs. */ + add_virtqueue(dev, VIRTQUEUE_NUM, rng_input); + + verbose("device %u: rng\n", devices.device_num++); +} +/* That's the end of device setup. */ + +/*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */ +static void __attribute__((noreturn)) restart_guest(void) +{ + unsigned int i; + + /* + * Since we don't track all open fds, we simply close everything beyond + * stderr. + */ + for (i = 3; i < FD_SETSIZE; i++) + close(i); + + /* Reset all the devices (kills all threads). */ + cleanup_devices(); + + execv(main_args[0], main_args); + err(1, "Could not exec %s", main_args[0]); +} + +/*L:220 + * Finally we reach the core of the Launcher which runs the Guest, serves + * its input and output, and finally, lays it to rest. + */ +static void __attribute__((noreturn)) run_guest(void) +{ + for (;;) { + unsigned long notify_addr; + int readval; + + /* We read from the /dev/lguest device to run the Guest. */ + readval = pread(lguest_fd, ¬ify_addr, + sizeof(notify_addr), cpu_id); + + /* One unsigned long means the Guest did HCALL_NOTIFY */ + if (readval == sizeof(notify_addr)) { + verbose("Notify on address %#lx\n", notify_addr); + handle_output(notify_addr); + /* ENOENT means the Guest died. Reading tells us why. */ + } else if (errno == ENOENT) { + char reason[1024] = { 0 }; + pread(lguest_fd, reason, sizeof(reason)-1, cpu_id); + errx(1, "%s", reason); + /* ERESTART means that we need to reboot the guest */ + } else if (errno == ERESTART) { + restart_guest(); + /* Anything else means a bug or incompatible change. */ + } else + err(1, "Running guest failed"); + } +} +/*L:240 + * This is the end of the Launcher. The good news: we are over halfway + * through! The bad news: the most fiendish part of the code still lies ahead + * of us. + * + * Are you ready? Take a deep breath and join me in the core of the Host, in + * "make Host". +:*/ + +static struct option opts[] = { + { "verbose", 0, NULL, 'v' }, + { "tunnet", 1, NULL, 't' }, + { "block", 1, NULL, 'b' }, + { "rng", 0, NULL, 'r' }, + { "initrd", 1, NULL, 'i' }, + { "username", 1, NULL, 'u' }, + { "chroot", 1, NULL, 'c' }, + { NULL }, +}; +static void usage(void) +{ + errx(1, "Usage: lguest [--verbose] " + "[--tunnet=(:|bridge::)\n" + "|--block=|--initrd=]...\n" + " vmlinux [args...]"); +} + +/*L:105 The main routine is where the real work begins: */ +int main(int argc, char *argv[]) +{ + /* Memory, code startpoint and size of the (optional) initrd. */ + unsigned long mem = 0, start, initrd_size = 0; + /* Two temporaries. */ + int i, c; + /* The boot information for the Guest. */ + struct boot_params *boot; + /* If they specify an initrd file to load. */ + const char *initrd_name = NULL; + + /* Password structure for initgroups/setres[gu]id */ + struct passwd *user_details = NULL; + + /* Directory to chroot to */ + char *chroot_path = NULL; + + /* Save the args: we "reboot" by execing ourselves again. */ + main_args = argv; + + /* + * First we initialize the device list. We keep a pointer to the last + * device, and the next interrupt number to use for devices (1: + * remember that 0 is used by the timer). + */ + devices.lastdev = NULL; + devices.next_irq = 1; + + /* We're CPU 0. In fact, that's the only CPU possible right now. */ + cpu_id = 0; + + /* + * We need to know how much memory so we can set up the device + * descriptor and memory pages for the devices as we parse the command + * line. So we quickly look through the arguments to find the amount + * of memory now. + */ + for (i = 1; i < argc; i++) { + if (argv[i][0] != '-') { + mem = atoi(argv[i]) * 1024 * 1024; + /* + * We start by mapping anonymous pages over all of + * guest-physical memory range. This fills it with 0, + * and ensures that the Guest won't be killed when it + * tries to access it. + */ + guest_base = map_zeroed_pages(mem / getpagesize() + + DEVICE_PAGES); + guest_limit = mem; + guest_max = mem + DEVICE_PAGES*getpagesize(); + devices.descpage = get_pages(1); + break; + } + } + + /* The options are fairly straight-forward */ + while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) { + switch (c) { + case 'v': + verbose = true; + break; + case 't': + setup_tun_net(optarg); + break; + case 'b': + setup_block_file(optarg); + break; + case 'r': + setup_rng(); + break; + case 'i': + initrd_name = optarg; + break; + case 'u': + user_details = getpwnam(optarg); + if (!user_details) + err(1, "getpwnam failed, incorrect username?"); + break; + case 'c': + chroot_path = optarg; + break; + default: + warnx("Unknown argument %s", argv[optind]); + usage(); + } + } + /* + * After the other arguments we expect memory and kernel image name, + * followed by command line arguments for the kernel. + */ + if (optind + 2 > argc) + usage(); + + verbose("Guest base is at %p\n", guest_base); + + /* We always have a console device */ + setup_console(); + + /* Now we load the kernel */ + start = load_kernel(open_or_die(argv[optind+1], O_RDONLY)); + + /* Boot information is stashed at physical address 0 */ + boot = from_guest_phys(0); + + /* Map the initrd image if requested (at top of physical memory) */ + if (initrd_name) { + initrd_size = load_initrd(initrd_name, mem); + /* + * These are the location in the Linux boot header where the + * start and size of the initrd are expected to be found. + */ + boot->hdr.ramdisk_image = mem - initrd_size; + boot->hdr.ramdisk_size = initrd_size; + /* The bootloader type 0xFF means "unknown"; that's OK. */ + boot->hdr.type_of_loader = 0xFF; + } + + /* + * The Linux boot header contains an "E820" memory map: ours is a + * simple, single region. + */ + boot->e820_entries = 1; + boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM }); + /* + * The boot header contains a command line pointer: we put the command + * line after the boot header. + */ + boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1); + /* We use a simple helper to copy the arguments separated by spaces. */ + concat((char *)(boot + 1), argv+optind+2); + + /* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */ + boot->hdr.kernel_alignment = 0x1000000; + + /* Boot protocol version: 2.07 supports the fields for lguest. */ + boot->hdr.version = 0x207; + + /* The hardware_subarch value of "1" tells the Guest it's an lguest. */ + boot->hdr.hardware_subarch = 1; + + /* Tell the entry path not to try to reload segment registers. */ + boot->hdr.loadflags |= KEEP_SEGMENTS; + + /* We tell the kernel to initialize the Guest. */ + tell_kernel(start); + + /* Ensure that we terminate if a device-servicing child dies. */ + signal(SIGCHLD, kill_launcher); + + /* If we exit via err(), this kills all the threads, restores tty. */ + atexit(cleanup_devices); + + /* If requested, chroot to a directory */ + if (chroot_path) { + if (chroot(chroot_path) != 0) + err(1, "chroot(\"%s\") failed", chroot_path); + + if (chdir("/") != 0) + err(1, "chdir(\"/\") failed"); + + verbose("chroot done\n"); + } + + /* If requested, drop privileges */ + if (user_details) { + uid_t u; + gid_t g; + + u = user_details->pw_uid; + g = user_details->pw_gid; + + if (initgroups(user_details->pw_name, g) != 0) + err(1, "initgroups failed"); + + if (setresgid(g, g, g) != 0) + err(1, "setresgid failed"); + + if (setresuid(u, u, u) != 0) + err(1, "setresuid failed"); + + verbose("Dropping privileges completed\n"); + } + + /* Finally, run the Guest. This doesn't return. */ + run_guest(); +} +/*:*/ + +/*M:999 + * Mastery is done: you now know everything I do. + * + * But surely you have seen code, features and bugs in your wanderings which + * you now yearn to attack? That is the real game, and I look forward to you + * patching and forking lguest into the Your-Name-Here-visor. + * + * Farewell, and good coding! + * Rusty Russell. + */ diff --git a/tools/lguest/lguest.txt b/tools/lguest/lguest.txt new file mode 100644 index 00000000000..bff0c554485 --- /dev/null +++ b/tools/lguest/lguest.txt @@ -0,0 +1,129 @@ + __ + (___()'`; Rusty's Remarkably Unreliable Guide to Lguest + /, /` - or, A Young Coder's Illustrated Hypervisor + \\"--\\ http://lguest.ozlabs.org + +Lguest is designed to be a minimal 32-bit x86 hypervisor for the Linux kernel, +for Linux developers and users to experiment with virtualization with the +minimum of complexity. Nonetheless, it should have sufficient features to +make it useful for specific tasks, and, of course, you are encouraged to fork +and enhance it (see drivers/lguest/README). + +Features: + +- Kernel module which runs in a normal kernel. +- Simple I/O model for communication. +- Simple program to create new guests. +- Logo contains cute puppies: http://lguest.ozlabs.org + +Developer features: + +- Fun to hack on. +- No ABI: being tied to a specific kernel anyway, you can change anything. +- Many opportunities for improvement or feature implementation. + +Running Lguest: + +- The easiest way to run lguest is to use same kernel as guest and host. + You can configure them differently, but usually it's easiest not to. + + You will need to configure your kernel with the following options: + + "General setup": + "Prompt for development and/or incomplete code/drivers" = Y + (CONFIG_EXPERIMENTAL=y) + + "Processor type and features": + "Paravirtualized guest support" = Y + "Lguest guest support" = Y + "High Memory Support" = off/4GB + "Alignment value to which kernel should be aligned" = 0x100000 + (CONFIG_PARAVIRT=y, CONFIG_LGUEST_GUEST=y, CONFIG_HIGHMEM64G=n and + CONFIG_PHYSICAL_ALIGN=0x100000) + + "Device Drivers": + "Block devices" + "Virtio block driver (EXPERIMENTAL)" = M/Y + "Network device support" + "Universal TUN/TAP device driver support" = M/Y + "Virtio network driver (EXPERIMENTAL)" = M/Y + (CONFIG_VIRTIO_BLK=m, CONFIG_VIRTIO_NET=m and CONFIG_TUN=m) + + "Virtualization" + "Linux hypervisor example code" = M/Y + (CONFIG_LGUEST=m) + +- A tool called "lguest" is available in this directory: type "make" + to build it. If you didn't build your kernel in-tree, use "make + O=". + +- Create or find a root disk image. There are several useful ones + around, such as the xm-test tiny root image at + http://xm-test.xensource.com/ramdisks/initrd-1.1-i386.img + + For more serious work, I usually use a distribution ISO image and + install it under qemu, then make multiple copies: + + dd if=/dev/zero of=rootfile bs=1M count=2048 + qemu -cdrom image.iso -hda rootfile -net user -net nic -boot d + + Make sure that you install a getty on /dev/hvc0 if you want to log in on the + console! + +- "modprobe lg" if you built it as a module. + +- Run an lguest as root: + + Documentation/virtual/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \ + --block=rootfile root=/dev/vda + + Explanation: + 64: the amount of memory to use, in MB. + + vmlinux: the kernel image found in the top of your build directory. You + can also use a standard bzImage. + + --tunnet=192.168.19.1: configures a "tap" device for networking with this + IP address. + + --block=rootfile: a file or block device which becomes /dev/vda + inside the guest. + + root=/dev/vda: this (and anything else on the command line) are + kernel boot parameters. + +- Configuring networking. I usually have the host masquerade, using + "iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE" and "echo 1 > + /proc/sys/net/ipv4/ip_forward". In this example, I would configure + eth0 inside the guest at 192.168.19.2. + + Another method is to bridge the tap device to an external interface + using --tunnet=bridge:, and perhaps run dhcp on the guest + to obtain an IP address. The bridge needs to be configured first: + this option simply adds the tap interface to it. + + A simple example on my system: + + ifconfig eth0 0.0.0.0 + brctl addbr lg0 + ifconfig lg0 up + brctl addif lg0 eth0 + dhclient lg0 + + Then use --tunnet=bridge:lg0 when launching the guest. + + See: + + http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge + + for general information on how to get bridging to work. + +- Random number generation. Using the --rng option will provide a + /dev/hwrng in the guest that will read from the host's /dev/random. + Use this option in conjunction with rng-tools (see ../hw_random.txt) + to provide entropy to the guest kernel's /dev/random. + +There is a helpful mailing list at http://ozlabs.org/mailman/listinfo/lguest + +Good luck! +Rusty Russell rusty@rustcorp.com.au. -- cgit v1.2.3-18-g5258 From b6c96c0214138186f495e3ee73737c6fc5e4efa2 Mon Sep 17 00:00:00 2001 From: Stratos Psomadakis Date: Thu, 12 Jan 2012 15:44:47 +1030 Subject: lguest: Make sure interrupt is allocated ok by lguest_setup_irq Make sure the interrupt is allocated correctly by lguest_setup_irq (check the return value of irq_alloc_desc_at for -ENOMEM) Signed-off-by: Stratos Psomadakis Signed-off-by: Rusty Russell (cleanups and commentry) --- arch/x86/lguest/boot.c | 21 +++++++++++++-------- drivers/lguest/lguest_device.c | 10 +++++++--- 2 files changed, 20 insertions(+), 11 deletions(-) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index cf4603ba866..642d8805bc1 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -856,18 +856,23 @@ static void __init lguest_init_IRQ(void) } /* - * With CONFIG_SPARSE_IRQ, interrupt descriptors are allocated as-needed, so - * rather than set them in lguest_init_IRQ we are called here every time an - * lguest device needs an interrupt. - * - * FIXME: irq_alloc_desc_at() can fail due to lack of memory, we should - * pass that up! + * Interrupt descriptors are allocated as-needed, but low-numbered ones are + * reserved by the generic x86 code. So we ignore irq_alloc_desc_at if it + * tells us the irq is already used: other errors (ie. ENOMEM) we take + * seriously. */ -void lguest_setup_irq(unsigned int irq) +int lguest_setup_irq(unsigned int irq) { - irq_alloc_desc_at(irq, 0); + int err; + + /* Returns -ve error or vector number. */ + err = irq_alloc_desc_at(irq, 0); + if (err < 0 && err != -EEXIST) + return err; + irq_set_chip_and_handler_name(irq, &lguest_irq_controller, handle_level_irq, "level"); + return 0; } /* diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c index 6a1d6447b86..9e8388efd88 100644 --- a/drivers/lguest/lguest_device.c +++ b/drivers/lguest/lguest_device.c @@ -241,7 +241,7 @@ static void lg_notify(struct virtqueue *vq) } /* An extern declaration inside a C file is bad form. Don't do it. */ -extern void lguest_setup_irq(unsigned int irq); +extern int lguest_setup_irq(unsigned int irq); /* * This routine finds the Nth virtqueue described in the configuration of @@ -304,7 +304,9 @@ static struct virtqueue *lg_find_vq(struct virtio_device *vdev, } /* Make sure the interrupt is allocated. */ - lguest_setup_irq(lvq->config.irq); + err = lguest_setup_irq(lvq->config.irq); + if (err) + goto destroy_vring; /* * Tell the interrupt for this virtqueue to go to the virtio_ring @@ -317,7 +319,7 @@ static struct virtqueue *lg_find_vq(struct virtio_device *vdev, err = request_irq(lvq->config.irq, vring_interrupt, IRQF_SHARED, dev_name(&vdev->dev), vq); if (err) - goto destroy_vring; + goto free_desc; /* * Last of all we hook up our 'struct lguest_vq_info" to the @@ -326,6 +328,8 @@ static struct virtqueue *lg_find_vq(struct virtio_device *vdev, vq->priv = lvq; return vq; +free_desc: + irq_free_desc(lvq->config.irq); destroy_vring: vring_del_virtqueue(vq); unmap: -- cgit v1.2.3-18-g5258