Merge tag 'virtio-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux

Pull virtio updates from Rusty Russell:
 "OK, this has the big virtio 1.0 implementation, as specified by OASIS.

  On top of tht is the major rework of lguest, to use PCI and virtio
  1.0, to double-check the implementation.

  Then comes the inevitable fixes and cleanups from that work"

* tag 'virtio-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux: (80 commits)
  virtio: don't set VIRTIO_CONFIG_S_DRIVER_OK twice.
  virtio_net: unconditionally define struct virtio_net_hdr_v1.
  tools/lguest: don't use legacy definitions for net device in example launcher.
  virtio: Don't expose legacy net features when VIRTIO_NET_NO_LEGACY defined.
  tools/lguest: use common error macros in the example launcher.
  tools/lguest: give virtqueues names for better error messages
  tools/lguest: more documentation and checking of virtio 1.0 compliance.
  lguest: don't look in console features to find emerg_wr.
  tools/lguest: don't start devices until DRIVER_OK status set.
  tools/lguest: handle indirect partway through chain.
  tools/lguest: insert driver references from the 1.0 spec (4.1 Virtio Over PCI)
  tools/lguest: insert device references from the 1.0 spec (4.1 Virtio Over PCI)
  tools/lguest: rename virtio_pci_cfg_cap field to match spec.
  tools/lguest: fix features_accepted logic in example launcher.
  tools/lguest: handle device reset correctly in example launcher.
  virtual: Documentation: simplify and generalize paravirt_ops.txt
  lguest: remove NOTIFY call and eventfd facility.
  lguest: remove NOTIFY facility from demonstration launcher.
  lguest: use the PCI console device's emerg_wr for early boot messages.
  lguest: always put console in PCI slot #1.
  ...

2 files changed, 1684 insertions, 340 deletions

diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile
index 97bca4871ea3..a107b5e4da13 100644
--- a/tools/lguest/Makefile
+++ b/tools/lguest/Makefile
@@ -1,7 +1,13 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
+CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE -Iinclude
 
 all: lguest
 
+include/linux/virtio_types.h: ../../include/uapi/linux/virtio_types.h
+	mkdir -p include/linux 2>&1 || true
+	ln -sf ../../../../include/uapi/linux/virtio_types.h $@
+
+lguest: include/linux/virtio_types.h
+
 clean:
 	rm -f lguest
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index 32cf2ce15d69..e44052483ed9 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -41,6 +41,8 @@
 #include <signal.h>
 #include <pwd.h>
 #include <grp.h>
+#include <sys/user.h>
+#include <linux/pci_regs.h>
 
 #ifndef VIRTIO_F_ANY_LAYOUT
 #define VIRTIO_F_ANY_LAYOUT		27
@@ -61,12 +63,19 @@ typedef uint16_t u16;
 typedef uint8_t u8;
 /*:*/
 
-#include <linux/virtio_config.h>
-#include <linux/virtio_net.h>
-#include <linux/virtio_blk.h>
-#include <linux/virtio_console.h>
-#include <linux/virtio_rng.h>
+#define VIRTIO_CONFIG_NO_LEGACY
+#define VIRTIO_PCI_NO_LEGACY
+#define VIRTIO_BLK_NO_LEGACY
+#define VIRTIO_NET_NO_LEGACY
+
+/* Use in-kernel ones, which defines VIRTIO_F_VERSION_1 */
+#include "../../include/uapi/linux/virtio_config.h"
+#include "../../include/uapi/linux/virtio_net.h"
+#include "../../include/uapi/linux/virtio_blk.h"
+#include "../../include/uapi/linux/virtio_console.h"
+#include "../../include/uapi/linux/virtio_rng.h"
 #include <linux/virtio_ring.h>
+#include "../../include/uapi/linux/virtio_pci.h"
 #include <asm/bootparam.h>
 #include "../../include/linux/lguest_launcher.h"
 
@@ -91,13 +100,16 @@ static bool verbose;
 /* 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;
+static unsigned long guest_limit, guest_max, guest_mmio;
 /* 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;
 
+/* 5 bit device number in the PCI_CONFIG_ADDR => 32 only */
+#define MAX_PCI_DEVICES 32
+
 /* This is our list of devices. */
 struct device_list {
 	/* Counter to assign interrupt numbers. */
@@ -106,30 +118,50 @@ struct device_list {
 	/* 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;
+	/* PCI devices. */
+	struct device *pci[MAX_PCI_DEVICES];
 };
 
 /* 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;
+struct virtio_pci_cfg_cap {
+	struct virtio_pci_cap cap;
+	u32 pci_cfg_data; /* Data for BAR access. */
+};
 
-	/* The device's descriptor, as mapped into the Guest. */
-	struct lguest_device_desc *desc;
+struct virtio_pci_mmio {
+	struct virtio_pci_common_cfg cfg;
+	u16 notify;
+	u8 isr;
+	u8 padding;
+	/* Device-specific configuration follows this. */
+};
 
-	/* We can't trust desc values once Guest has booted: we use these. */
-	unsigned int feature_len;
-	unsigned int num_vq;
+/* This is the layout (little-endian) of the PCI config space. */
+struct pci_config {
+	u16 vendor_id, device_id;
+	u16 command, status;
+	u8 revid, prog_if, subclass, class;
+	u8 cacheline_size, lat_timer, header_type, bist;
+	u32 bar[6];
+	u32 cardbus_cis_ptr;
+	u16 subsystem_vendor_id, subsystem_device_id;
+	u32 expansion_rom_addr;
+	u8 capabilities, reserved1[3];
+	u32 reserved2;
+	u8 irq_line, irq_pin, min_grant, max_latency;
+
+	/* Now, this is the linked capability list. */
+	struct virtio_pci_cap common;
+	struct virtio_pci_notify_cap notify;
+	struct virtio_pci_cap isr;
+	struct virtio_pci_cap device;
+	struct virtio_pci_cfg_cap cfg_access;
+};
 
+/* The device structure describes a single device. */
+struct device {
 	/* The name of this device, for --verbose. */
 	const char *name;
 
@@ -139,6 +171,25 @@ struct device {
 	/* Is it operational */
 	bool running;
 
+	/* Has it written FEATURES_OK but not re-checked it? */
+	bool wrote_features_ok;
+
+	/* PCI configuration */
+	union {
+		struct pci_config config;
+		u32 config_words[sizeof(struct pci_config) / sizeof(u32)];
+	};
+
+	/* Features we offer, and those accepted. */
+	u64 features, features_accepted;
+
+	/* Device-specific config hangs off the end of this. */
+	struct virtio_pci_mmio *mmio;
+
+	/* PCI MMIO resources (all in BAR0) */
+	size_t mmio_size;
+	u32 mmio_addr;
+
 	/* Device-specific data. */
 	void *priv;
 };
@@ -150,12 +201,15 @@ struct virtqueue {
 	/* Which device owns me. */
 	struct device *dev;
 
-	/* The configuration for this queue. */
-	struct lguest_vqconfig config;
+	/* Name for printing errors. */
+	const char *name;
 
 	/* The actual ring of buffers. */
 	struct vring vring;
 
+	/* The information about this virtqueue (we only use queue_size on) */
+	struct virtio_pci_common_cfg pci_config;
+
 	/* Last available index we saw. */
 	u16 last_avail_idx;
 
@@ -199,6 +253,16 @@ static struct termios orig_term;
 #define le32_to_cpu(v32) (v32)
 #define le64_to_cpu(v64) (v64)
 
+/*
+ * A real device would ignore weird/non-compliant driver behaviour.  We
+ * stop and flag it, to help debugging Linux problems.
+ */
+#define bad_driver(d, fmt, ...) \
+	errx(1, "%s: bad driver: " fmt, (d)->name, ## __VA_ARGS__)
+#define bad_driver_vq(vq, fmt, ...)			       \
+	errx(1, "%s vq %s: bad driver: " fmt, (vq)->dev->name, \
+	     vq->name, ## __VA_ARGS__)
+
 /* Is this iovec empty? */
 static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
 {
@@ -211,7 +275,8 @@ static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
 }
 
 /* Take len bytes from the front of this iovec. */
-static void iov_consume(struct iovec iov[], unsigned num_iov,
+static void iov_consume(struct device *d,
+			struct iovec iov[], unsigned num_iov,
 			void *dest, unsigned len)
 {
 	unsigned int i;
@@ -229,14 +294,7 @@ static void iov_consume(struct iovec iov[], unsigned num_iov,
 		len -= used;
 	}
 	if (len != 0)
-		errx(1, "iovec too short!");
-}
-
-/* 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);
+		bad_driver(d, "iovec too short!");
 }
 
 /*L:100
@@ -309,14 +367,20 @@ static void *map_zeroed_pages(unsigned int num)
 	return addr + getpagesize();
 }
 
-/* Get some more pages for a device. */
-static void *get_pages(unsigned int num)
+/* Get some bytes which won't be mapped into the guest. */
+static unsigned long get_mmio_region(size_t size)
 {
-	void *addr = from_guest_phys(guest_limit);
+	unsigned long addr = guest_mmio;
+	size_t i;
+
+	if (!size)
+		return addr;
+
+	/* Size has to be a power of 2 (and multiple of 16) */
+	for (i = 1; i < size; i <<= 1);
+
+	guest_mmio += i;
 
-	guest_limit += num * getpagesize();
-	if (guest_limit > guest_max)
-		errx(1, "Not enough memory for devices");
 	return addr;
 }
 
@@ -547,9 +611,11 @@ 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);
+				 guest_limit / getpagesize(), start,
+				 (guest_mmio+getpagesize()-1) / getpagesize() };
+	verbose("Guest: %p - %p (%#lx, MMIO %#lx)\n",
+		guest_base, guest_base + guest_limit,
+		guest_limit, guest_mmio);
 	lguest_fd = open_or_die("/dev/lguest", O_RDWR);
 	if (write(lguest_fd, args, sizeof(args)) < 0)
 		err(1, "Writing to /dev/lguest");
@@ -564,7 +630,8 @@ static void tell_kernel(unsigned long start)
  * 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,
+static void *_check_pointer(struct device *d,
+			    unsigned long addr, unsigned int size,
 			    unsigned int line)
 {
 	/*
@@ -572,7 +639,8 @@ static void *_check_pointer(unsigned long addr, unsigned int size,
 	 * or addr + size wraps around.
 	 */
 	if ((addr + size) > guest_limit || (addr + size) < addr)
-		errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr);
+		bad_driver(d, "%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.
@@ -580,14 +648,14 @@ static void *_check_pointer(unsigned long addr, unsigned int size,
 	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__)
+#define check_pointer(d,addr,size) _check_pointer(d, 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,
+static unsigned next_desc(struct device *d, struct vring_desc *desc,
 			  unsigned int i, unsigned int max)
 {
 	unsigned int next;
@@ -602,7 +670,7 @@ static unsigned next_desc(struct vring_desc *desc,
 	wmb();
 
 	if (next >= max)
-		errx(1, "Desc next is %u", next);
+		bad_driver(d, "Desc next is %u", next);
 
 	return next;
 }
@@ -613,21 +681,48 @@ static unsigned next_desc(struct vring_desc *desc,
  */
 static void trigger_irq(struct virtqueue *vq)
 {
-	unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
+	unsigned long buf[] = { LHREQ_IRQ, vq->dev->config.irq_line };
 
 	/* 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... */
+	/*
+	 * 2.4.7.1:
+	 *
+	 *  If the VIRTIO_F_EVENT_IDX feature bit is not negotiated:
+	 *    The driver MUST set flags to 0 or 1. 
+	 */
+	if (vq->vring.avail->flags > 1)
+		bad_driver_vq(vq, "avail->flags = %u\n", vq->vring.avail->flags);
+
+	/*
+	 * 2.4.7.2:
+	 *
+	 *  If the VIRTIO_F_EVENT_IDX feature bit is not negotiated:
+	 *
+	 *     - The device MUST ignore the used_event value.
+	 *     - After the device writes a descriptor index into the used ring:
+	 *         - If flags is 1, the device SHOULD NOT send an interrupt.
+	 *         - If flags is 0, the device MUST send an interrupt.
+	 */
 	if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) {
 		return;
 	}
 
+	/*
+	 * 4.1.4.5.1:
+	 *
+	 *  If MSI-X capability is disabled, the device MUST set the Queue
+	 *  Interrupt bit in ISR status before sending a virtqueue notification
+	 *  to the driver.
+	 */
+	vq->dev->mmio->isr = 0x1;
+
 	/* 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);
+		err(1, "Triggering irq %i", vq->dev->config.irq_line);
 }
 
 /*
@@ -646,6 +741,14 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	struct vring_desc *desc;
 	u16 last_avail = lg_last_avail(vq);
 
+	/*
+	 * 2.4.7.1:
+	 *
+	 *   The driver MUST handle spurious interrupts from the device.
+	 *
+	 * That's why this is a while loop.
+	 */
+
 	/* There's nothing available? */
 	while (last_avail == vq->vring.avail->idx) {
 		u64 event;
@@ -679,8 +782,8 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 
 	/* 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);
+		bad_driver_vq(vq, "Guest moved used index from %u to %u",
+			      last_avail, vq->vring.avail->idx);
 
 	/* 
 	 * Make sure we read the descriptor number *after* we read the ring
@@ -697,7 +800,7 @@ static unsigned wait_for_vq_desc(struct virtqueue *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);
+		bad_driver_vq(vq, "Guest says index %u is available", head);
 
 	/* When we start there are none of either input nor output. */
 	*out_num = *in_num = 0;
@@ -712,24 +815,73 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	 * that: no rmb() required.
 	 */
 
-	/*
-	 * 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");
+	do {
+		/*
+		 * 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) {
+			/* 2.4.5.3.1:
+			 *
+			 *  The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT
+			 *  flag unless the VIRTIO_F_INDIRECT_DESC feature was
+			 *  negotiated.
+			 */
+			if (!(vq->dev->features_accepted &
+			      (1<<VIRTIO_RING_F_INDIRECT_DESC)))
+				bad_driver_vq(vq, "vq indirect not negotiated");
 
-		max = desc[i].len / sizeof(struct vring_desc);
-		desc = check_pointer(desc[i].addr, desc[i].len);
-		i = 0;
-	}
+			/*
+			 * 2.4.5.3.1:
+			 *
+			 *   The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT
+			 *   flag within an indirect descriptor (ie. only one
+			 *   table per descriptor).
+			 */
+			if (desc != vq->vring.desc)
+				bad_driver_vq(vq, "Indirect within indirect");
+
+			/*
+			 * Proposed update VIRTIO-134 spells this out:
+			 *
+			 *   A driver MUST NOT set both VIRTQ_DESC_F_INDIRECT
+			 *   and VIRTQ_DESC_F_NEXT in flags.
+			 */
+			if (desc[i].flags & VRING_DESC_F_NEXT)
+				bad_driver_vq(vq, "indirect and next together");
+
+			if (desc[i].len % sizeof(struct vring_desc))
+				bad_driver_vq(vq,
+					      "Invalid size for indirect table");
+			/*
+			 * 2.4.5.3.2:
+			 *
+			 *  The device MUST ignore the write-only flag
+			 *  (flags&VIRTQ_DESC_F_WRITE) in the descriptor that
+			 *  refers to an indirect table.
+			 *
+			 * We ignore it here: :)
+			 */
+
+			max = desc[i].len / sizeof(struct vring_desc);
+			desc = check_pointer(vq->dev, desc[i].addr, desc[i].len);
+			i = 0;
+
+			/* 2.4.5.3.1:
+			 *
+			 *  A driver MUST NOT create a descriptor chain longer
+			 *  than the Queue Size of the device.
+			 */
+			if (max > vq->pci_config.queue_size)
+				bad_driver_vq(vq,
+					      "indirect has too many entries");
+		}
 
-	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);
+			= check_pointer(vq->dev, 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)++;
@@ -739,14 +891,15 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 			 * to come before any input descriptors.
 			 */
 			if (*in_num)
-				errx(1, "Descriptor has out after in");
+				bad_driver_vq(vq,
+					      "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);
+			bad_driver_vq(vq, "Looped descriptor");
+	} while ((i = next_desc(vq->dev, desc, i, max)) != max);
 
 	return head;
 }
@@ -803,7 +956,7 @@ static void console_input(struct virtqueue *vq)
 	/* 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?");
+		bad_driver_vq(vq, "Output buffers in console in queue?");
 
 	/* Read into it.  This is where we usually wait. */
 	len = readv(STDIN_FILENO, iov, in_num);
@@ -856,7 +1009,7 @@ static void console_output(struct virtqueue *vq)
 	/* 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?");
+		bad_driver_vq(vq, "Input buffers in console output queue?");
 
 	/* writev can return a partial write, so we loop here. */
 	while (!iov_empty(iov, out)) {
@@ -865,7 +1018,7 @@ static void console_output(struct virtqueue *vq)
 			warn("Write to stdout gave %i (%d)", len, errno);
 			break;
 		}
-		iov_consume(iov, out, NULL, len);
+		iov_consume(vq->dev, iov, out, NULL, len);
 	}
 
 	/*
@@ -894,7 +1047,7 @@ static void net_output(struct virtqueue *vq)
 	/* 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?");
+		bad_driver_vq(vq, "Input buffers in net output queue?");
 	/*
 	 * Send the whole thing through to /dev/net/tun.  It expects the exact
 	 * same format: what a coincidence!
@@ -942,7 +1095,7 @@ static void net_input(struct virtqueue *vq)
 	 */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (out)
-		errx(1, "Output buffers in net input queue?");
+		bad_driver_vq(vq, "Output buffers in net input queue?");
 
 	/*
 	 * If it looks like we'll block reading from the tun device, send them
@@ -986,6 +1139,12 @@ static void kill_launcher(int signal)
 	kill(0, SIGTERM);
 }
 
+static void reset_vq_pci_config(struct virtqueue *vq)
+{
+	vq->pci_config.queue_size = VIRTQUEUE_NUM;
+	vq->pci_config.queue_enable = 0;
+}
+
 static void reset_device(struct device *dev)
 {
 	struct virtqueue *vq;
@@ -993,53 +1152,705 @@ static void reset_device(struct device *dev)
 	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);
+	dev->features_accepted = 0;
 
 	/* We're going to be explicitly killing threads, so ignore them. */
 	signal(SIGCHLD, SIG_IGN);
 
-	/* Zero out the virtqueues, get rid of their threads */
+	/*
+	 * 4.1.4.3.1:
+	 *
+	 *   The device MUST present a 0 in queue_enable on reset. 
+	 *
+	 * This means we set it here, and reset the saved ones in every vq.
+	 */
+	dev->mmio->cfg.queue_enable = 0;
+
+	/* Get rid of the virtqueue threads */
 	for (vq = dev->vq; vq; vq = vq->next) {
+		vq->last_avail_idx = 0;
+		reset_vq_pci_config(vq);
 		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;
+	dev->wrote_features_ok = false;
 
 	/* Now we care if threads die. */
 	signal(SIGCHLD, (void *)kill_launcher);
 }
 
+static void cleanup_devices(void)
+{
+	unsigned int i;
+
+	for (i = 1; i < MAX_PCI_DEVICES; i++) {
+		struct device *d = devices.pci[i];
+		if (!d)
+			continue;
+		reset_device(d);
+	}
+
+	/* 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);
+}
+
+/*L:217
+ * We do PCI.  This is mainly done to let us test the kernel virtio PCI
+ * code.
+ */
+
+/* Linux expects a PCI host bridge: ours is a dummy, and first on the bus. */
+static struct device pci_host_bridge;
+
+static void init_pci_host_bridge(void)
+{
+	pci_host_bridge.name = "PCI Host Bridge";
+	pci_host_bridge.config.class = 0x06; /* bridge */
+	pci_host_bridge.config.subclass = 0; /* host bridge */
+	devices.pci[0] = &pci_host_bridge;
+}
+
+/* The IO ports used to read the PCI config space. */
+#define PCI_CONFIG_ADDR 0xCF8
+#define PCI_CONFIG_DATA 0xCFC
+
+/*
+ * Not really portable, but does help readability: this is what the Guest
+ * writes to the PCI_CONFIG_ADDR IO port.
+ */
+union pci_config_addr {
+	struct {
+		unsigned mbz: 2;
+		unsigned offset: 6;
+		unsigned funcnum: 3;
+		unsigned devnum: 5;
+		unsigned busnum: 8;
+		unsigned reserved: 7;
+		unsigned enabled : 1;
+	} bits;
+	u32 val;
+};
+
+/*
+ * We cache what they wrote to the address port, so we know what they're
+ * talking about when they access the data port.
+ */
+static union pci_config_addr pci_config_addr;
+
+static struct device *find_pci_device(unsigned int index)
+{
+	return devices.pci[index];
+}
+
+/* PCI can do 1, 2 and 4 byte reads; we handle that here. */
+static void ioread(u16 off, u32 v, u32 mask, u32 *val)
+{
+	assert(off < 4);
+	assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF);
+	*val = (v >> (off * 8)) & mask;
+}
+
+/* PCI can do 1, 2 and 4 byte writes; we handle that here. */
+static void iowrite(u16 off, u32 v, u32 mask, u32 *dst)
+{
+	assert(off < 4);
+	assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF);
+	*dst &= ~(mask << (off * 8));
+	*dst |= (v & mask) << (off * 8);
+}
+
+/*
+ * Where PCI_CONFIG_DATA accesses depends on the previous write to
+ * PCI_CONFIG_ADDR.
+ */
+static struct device *dev_and_reg(u32 *reg)
+{
+	if (!pci_config_addr.bits.enabled)
+		return NULL;
+
+	if (pci_config_addr.bits.funcnum != 0)
+		return NULL;
+
+	if (pci_config_addr.bits.busnum != 0)
+		return NULL;
+
+	if (pci_config_addr.bits.offset * 4 >= sizeof(struct pci_config))
+		return NULL;
+
+	*reg = pci_config_addr.bits.offset;
+	return find_pci_device(pci_config_addr.bits.devnum);
+}
+
+/*
+ * We can get invalid combinations of values while they're writing, so we
+ * only fault if they try to write with some invalid bar/offset/length.
+ */
+static bool valid_bar_access(struct device *d,
+			     struct virtio_pci_cfg_cap *cfg_access)
+{
+	/* We only have 1 bar (BAR0) */
+	if (cfg_access->cap.bar != 0)
+		return false;
+
+	/* Check it's within BAR0. */
+	if (cfg_access->cap.offset >= d->mmio_size
+	    || cfg_access->cap.offset + cfg_access->cap.length > d->mmio_size)
+		return false;
+
+	/* Check length is 1, 2 or 4. */
+	if (cfg_access->cap.length != 1
+	    && cfg_access->cap.length != 2
+	    && cfg_access->cap.length != 4)
+		return false;
+
+	/*
+	 * 4.1.4.7.2:
+	 *
+	 *  The driver MUST NOT write a cap.offset which is not a multiple of
+	 *  cap.length (ie. all accesses MUST be aligned).
+	 */
+	if (cfg_access->cap.offset % cfg_access->cap.length != 0)
+		return false;
+
+	/* Return pointer into word in BAR0. */
+	return true;
+}
+
+/* Is this accessing the PCI config address port?. */
+static bool is_pci_addr_port(u16 port)
+{
+	return port >= PCI_CONFIG_ADDR && port < PCI_CONFIG_ADDR + 4;
+}
+
+static bool pci_addr_iowrite(u16 port, u32 mask, u32 val)
+{
+	iowrite(port - PCI_CONFIG_ADDR, val, mask,
+		&pci_config_addr.val);
+	verbose("PCI%s: %#x/%x: bus %u dev %u func %u reg %u\n",
+		pci_config_addr.bits.enabled ? "" : " DISABLED",
+		val, mask,
+		pci_config_addr.bits.busnum,
+		pci_config_addr.bits.devnum,
+		pci_config_addr.bits.funcnum,
+		pci_config_addr.bits.offset);
+	return true;
+}
+
+static void pci_addr_ioread(u16 port, u32 mask, u32 *val)
+{
+	ioread(port - PCI_CONFIG_ADDR, pci_config_addr.val, mask, val);
+}
+
+/* Is this accessing the PCI config data port?. */
+static bool is_pci_data_port(u16 port)
+{
+	return port >= PCI_CONFIG_DATA && port < PCI_CONFIG_DATA + 4;
+}
+
+static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask);
+
+static bool pci_data_iowrite(u16 port, u32 mask, u32 val)
+{
+	u32 reg, portoff;
+	struct device *d = dev_and_reg(&reg);
+
+	/* Complain if they don't belong to a device. */
+	if (!d)
+		return false;
+
+	/* They can do 1 byte writes, etc. */
+	portoff = port - PCI_CONFIG_DATA;
+
+	/*
+	 * PCI uses a weird way to determine the BAR size: the OS
+	 * writes all 1's, and sees which ones stick.
+	 */
+	if (&d->config_words[reg] == &d->config.bar[0]) {
+		int i;
+
+		iowrite(portoff, val, mask, &d->config.bar[0]);
+		for (i = 0; (1 << i) < d->mmio_size; i++)
+			d->config.bar[0] &= ~(1 << i);
+		return true;
+	} else if ((&d->config_words[reg] > &d->config.bar[0]
+		    && &d->config_words[reg] <= &d->config.bar[6])
+		   || &d->config_words[reg] == &d->config.expansion_rom_addr) {
+		/* Allow writing to any other BAR, or expansion ROM */
+		iowrite(portoff, val, mask, &d->config_words[reg]);
+		return true;
+		/* We let them overide latency timer and cacheline size */
+	} else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) {
+		/* Only let them change the first two fields. */
+		if (mask == 0xFFFFFFFF)
+			mask = 0xFFFF;
+		iowrite(portoff, val, mask, &d->config_words[reg]);
+		return true;
+	} else if (&d->config_words[reg] == (void *)&d->config.command
+		   && mask == 0xFFFF) {
+		/* Ignore command writes. */
+		return true;
+	} else if (&d->config_words[reg]
+		   == (void *)&d->config.cfg_access.cap.bar
+		   || &d->config_words[reg]
+		   == &d->config.cfg_access.cap.length
+		   || &d->config_words[reg]
+		   == &d->config.cfg_access.cap.offset) {
+
+		/*
+		 * The VIRTIO_PCI_CAP_PCI_CFG capability
+		 * provides a backdoor to access the MMIO
+		 * regions without mapping them.  Weird, but
+		 * useful.
+		 */
+		iowrite(portoff, val, mask, &d->config_words[reg]);
+		return true;
+	} else if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) {
+		u32 write_mask;
+
+		/*
+		 * 4.1.4.7.1:
+		 *
+		 *  Upon detecting driver write access to pci_cfg_data, the
+		 *  device MUST execute a write access at offset cap.offset at
+		 *  BAR selected by cap.bar using the first cap.length bytes
+		 *  from pci_cfg_data.
+		 */
+
+		/* Must be bar 0 */
+		if (!valid_bar_access(d, &d->config.cfg_access))
+			return false;
+
+		iowrite(portoff, val, mask, &d->config.cfg_access.pci_cfg_data);
+
+		/*
+		 * Now emulate a write.  The mask we use is set by
+		 * len, *not* this write!
+		 */
+		write_mask = (1ULL<<(8*d->config.cfg_access.cap.length)) - 1;
+		verbose("Window writing %#x/%#x to bar %u, offset %u len %u\n",
+			d->config.cfg_access.pci_cfg_data, write_mask,
+			d->config.cfg_access.cap.bar,
+			d->config.cfg_access.cap.offset,
+			d->config.cfg_access.cap.length);
+
+		emulate_mmio_write(d, d->config.cfg_access.cap.offset,
+				   d->config.cfg_access.pci_cfg_data,
+				   write_mask);
+		return true;
+	}
+
+	/*
+	 * 4.1.4.1:
+	 *
+	 *  The driver MUST NOT write into any field of the capability
+	 *  structure, with the exception of those with cap_type
+	 *  VIRTIO_PCI_CAP_PCI_CFG...
+	 */
+	return false;
+}
+
+static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask);
+
+static void pci_data_ioread(u16 port, u32 mask, u32 *val)
+{
+	u32 reg;
+	struct device *d = dev_and_reg(&reg);
+
+	if (!d)
+		return;
+
+	/* Read through the PCI MMIO access window is special */
+	if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) {
+		u32 read_mask;
+
+		/*
+		 * 4.1.4.7.1:
+		 *
+		 *  Upon detecting driver read access to pci_cfg_data, the
+		 *  device MUST execute a read access of length cap.length at
+		 *  offset cap.offset at BAR selected by cap.bar and store the
+		 *  first cap.length bytes in pci_cfg_data.
+		 */
+		/* Must be bar 0 */
+		if (!valid_bar_access(d, &d->config.cfg_access))
+			bad_driver(d,
+			     "Invalid cfg_access to bar%u, offset %u len %u",
+			     d->config.cfg_access.cap.bar,
+			     d->config.cfg_access.cap.offset,
+			     d->config.cfg_access.cap.length);
+
+		/*
+		 * Read into the window.  The mask we use is set by
+		 * len, *not* this read!
+		 */
+		read_mask = (1ULL<<(8*d->config.cfg_access.cap.length))-1;
+		d->config.cfg_access.pci_cfg_data
+			= emulate_mmio_read(d,
+					    d->config.cfg_access.cap.offset,
+					    read_mask);
+		verbose("Window read %#x/%#x from bar %u, offset %u len %u\n",
+			d->config.cfg_access.pci_cfg_data, read_mask,
+			d->config.cfg_access.cap.bar,
+			d->config.cfg_access.cap.offset,
+			d->config.cfg_access.cap.length);
+	}
+	ioread(port - PCI_CONFIG_DATA, d->config_words[reg], mask, val);
+}
+
 /*L:216
- * This actually creates the thread which services the virtqueue for a device.
+ * This is where we emulate a handful of Guest instructions.  It's ugly
+ * and we used to do it in the kernel but it grew over time.
+ */
+
+/*
+ * We use the ptrace syscall's pt_regs struct to talk about registers
+ * to lguest: these macros convert the names to the offsets.
+ */
+#define getreg(name) getreg_off(offsetof(struct user_regs_struct, name))
+#define setreg(name, val) \
+	setreg_off(offsetof(struct user_regs_struct, name), (val))
+
+static u32 getreg_off(size_t offset)
+{
+	u32 r;
+	unsigned long args[] = { LHREQ_GETREG, offset };
+
+	if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
+		err(1, "Getting register %u", offset);
+	if (pread(lguest_fd, &r, sizeof(r), cpu_id) != sizeof(r))
+		err(1, "Reading register %u", offset);
+
+	return r;
+}
+
+static void setreg_off(size_t offset, u32 val)
+{
+	unsigned long args[] = { LHREQ_SETREG, offset, val };
+
+	if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
+		err(1, "Setting register %u", offset);
+}
+
+/* Get register by instruction encoding */
+static u32 getreg_num(unsigned regnum, u32 mask)
+{
+	/* 8 bit ops use regnums 4-7 for high parts of word */
+	if (mask == 0xFF && (regnum & 0x4))
+		return getreg_num(regnum & 0x3, 0xFFFF) >> 8;
+
+	switch (regnum) {
+	case 0: return getreg(eax) & mask;
+	case 1: return getreg(ecx) & mask;
+	case 2: return getreg(edx) & mask;
+	case 3: return getreg(ebx) & mask;
+	case 4: return getreg(esp) & mask;
+	case 5: return getreg(ebp) & mask;
+	case 6: return getreg(esi) & mask;
+	case 7: return getreg(edi) & mask;
+	}
+	abort();
+}
+
+/* Set register by instruction encoding */
+static void setreg_num(unsigned regnum, u32 val, u32 mask)
+{
+	/* Don't try to set bits out of range */
+	assert(~(val & ~mask));
+
+	/* 8 bit ops use regnums 4-7 for high parts of word */
+	if (mask == 0xFF && (regnum & 0x4)) {
+		/* Construct the 16 bits we want. */
+		val = (val << 8) | getreg_num(regnum & 0x3, 0xFF);
+		setreg_num(regnum & 0x3, val, 0xFFFF);
+		return;
+	}
+
+	switch (regnum) {
+	case 0: setreg(eax, val | (getreg(eax) & ~mask)); return;
+	case 1: setreg(ecx, val | (getreg(ecx) & ~mask)); return;
+	case 2: setreg(edx, val | (getreg(edx) & ~mask)); return;
+	case 3: setreg(ebx, val | (getreg(ebx) & ~mask)); return;
+	case 4: setreg(esp, val | (getreg(esp) & ~mask)); return;
+	case 5: setreg(ebp, val | (getreg(ebp) & ~mask)); return;
+	case 6: setreg(esi, val | (getreg(esi) & ~mask)); return;
+	case 7: setreg(edi, val | (getreg(edi) & ~mask)); return;
+	}
+	abort();
+}
+
+/* Get bytes of displacement appended to instruction, from r/m encoding */
+static u32 insn_displacement_len(u8 mod_reg_rm)
+{
+	/* Switch on the mod bits */
+	switch (mod_reg_rm >> 6) {
+	case 0: