#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 <linux/virtio_console.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"
/* 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];
};
struct virtio_pci_cfg_cap {
struct virtio_pci_cap cap;
- u32 window; /* Data for BAR access. */
+ u32 pci_cfg_data; /* Data for BAR access. */
};
struct virtio_pci_mmio {
struct virtio_pci_notify_cap notify;
struct virtio_pci_cap isr;
struct virtio_pci_cap device;
- /* FIXME: Implement this! */
struct virtio_pci_cfg_cap cfg_access;
};
/* 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;
/* 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;
/* 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;
#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)
{
}
/* 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;
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
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;
-}
-
/* Get some bytes which won't be mapped into the guest. */
static unsigned long get_mmio_region(size_t size)
{
* 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)
{
/*
* 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.
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;
wmb();
if (next >= max)
- errx(1, "Desc next is %u", next);
+ bad_driver(d, "Desc next is %u", next);
return next;
}
*/
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;
}
- /* For a PCI device, set isr to 1 (queue interrupt pending) */
- if (vq->dev->mmio)
- vq->dev->mmio->isr = 0x1;
+ /*
+ * 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);
}
/*
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;
/* 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
/* 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;
* 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)++;
* 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;
}
/* 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);
/* 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)) {
warn("Write to stdout gave %i (%d)", len, errno);
break;
}
- iov_consume(iov, out, NULL, len);
+ iov_consume(vq->dev, iov, out, NULL, len);
}
/*
/* 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!
*/
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
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;
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);
}
-/*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)
+static void cleanup_devices(void)
{
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);
+ for (i = 1; i < MAX_PCI_DEVICES; i++) {
+ struct device *d = devices.pci[i];
+ if (!d)
+ continue;
+ reset_device(d);
}
- 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:217
* We do PCI. This is mainly done to let us test the kernel virtio PCI
* code.
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_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;
&& 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;
}
- /* Complain about other writes. */
+ /*
+ * 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;
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);
}
}
/*
+ * 4.1.4.3.2:
+ *
+ * The driver MUST configure the other virtqueue fields before
+ * enabling the virtqueue with queue_enable.
+ *
* When they enable the virtqueue, we check that their setup is valid.
*/
-static void enable_virtqueue(struct device *d, struct virtqueue *vq)
+static void check_virtqueue(struct device *d, 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);
-
/* Because lguest is 32 bit, all the descriptor high bits must be 0 */
if (vq->pci_config.queue_desc_hi
|| vq->pci_config.queue_avail_hi
|| vq->pci_config.queue_used_hi)
- errx(1, "%s: invalid 64-bit queue address", d->name);
+ bad_driver_vq(vq, "invalid 64-bit queue address");
+
+ /*
+ * 2.4.1:
+ *
+ * The driver MUST ensure that the physical address of the first byte
+ * of each virtqueue part is a multiple of the specified alignment
+ * value in the above table.
+ */
+ if (vq->pci_config.queue_desc_lo % 16
+ || vq->pci_config.queue_avail_lo % 2
+ || vq->pci_config.queue_used_lo % 4)
+ bad_driver_vq(vq, "invalid alignment in queue addresses");
/* Initialize the virtqueue and check they're all in range. */
vq->vring.num = vq->pci_config.queue_size;
- vq->vring.desc = check_pointer(vq->pci_config.queue_desc_lo,
+ vq->vring.desc = check_pointer(vq->dev,
+ vq->pci_config.queue_desc_lo,
sizeof(*vq->vring.desc) * vq->vring.num);
- vq->vring.avail = check_pointer(vq->pci_config.queue_avail_lo,
+ vq->vring.avail = check_pointer(vq->dev,
+ vq->pci_config.queue_avail_lo,
sizeof(*vq->vring.avail)
+ (sizeof(vq->vring.avail->ring[0])
* vq->vring.num));
- vq->vring.used = check_pointer(vq->pci_config.queue_used_lo,
+ vq->vring.used = check_pointer(vq->dev,
+ vq->pci_config.queue_used_lo,
sizeof(*vq->vring.used)
+ (sizeof(vq->vring.used->ring[0])
* vq->vring.num));
+ /*
+ * 2.4.9.1:
+ *
+ * The driver MUST initialize flags in the used ring to 0
+ * when allocating the used ring.
+ */
+ if (vq->vring.used->flags != 0)
+ bad_driver_vq(vq, "invalid initial used.flags %#x",
+ vq->vring.used->flags);
+}
+
+static void start_virtqueue(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);
/* Create a zero-initialized eventfd. */
vq->eventfd = eventfd(0, 0);
err(1, "Creating clone");
}
-static void reset_pci_device(struct device *dev)
+static void start_virtqueues(struct device *d)
{
- /* FIXME */
+ struct virtqueue *vq;
+
+ for (vq = d->vq; vq; vq = vq->next) {
+ if (vq->pci_config.queue_enable)
+ start_virtqueue(vq);
+ }
}
static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask)
switch (off) {
case offsetof(struct virtio_pci_mmio, cfg.device_feature_select):
+ /*
+ * 4.1.4.3.1:
+ *
+ * The device MUST present the feature bits it is offering in
+ * device_feature, starting at bit device_feature_select ∗ 32
+ * for any device_feature_select written by the driver
+ */
if (val == 0)
d->mmio->cfg.device_feature = d->features;
else if (val == 1)
d->mmio->cfg.device_feature = (d->features >> 32);
else
d->mmio->cfg.device_feature = 0;
- goto write_through32;
+ goto feature_write_through32;
case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select):
if (val > 1)
- errx(1, "%s: Unexpected driver select %u",
- d->name, val);
- goto write_through32;
+ bad_driver(d, "Unexpected driver select %u", val);
+ goto feature_write_through32;
case offsetof(struct virtio_pci_mmio, cfg.guest_feature):
if (d->mmio->cfg.guest_feature_select == 0) {
d->features_accepted &= ~((u64)0xFFFFFFFF);
d->features_accepted |= val;
} else {
assert(d->mmio->cfg.guest_feature_select == 1);
- d->features_accepted &= ((u64)0xFFFFFFFF << 32);
+ d->features_accepted &= 0xFFFFFFFF;
d->features_accepted |= ((u64)val) << 32;
}
+ /*
+ * 2.2.1:
+ *
+ * The driver MUST NOT accept a feature which the device did
+ * not offer
+ */
if (d->features_accepted & ~d->features)
- errx(1, "%s: over-accepted features %#llx of %#llx",
- d->name, d->features_accepted, d->features);
- goto write_through32;
- case offsetof(struct virtio_pci_mmio, cfg.device_status):
+ bad_driver(d, "over-accepted features %#llx of %#llx",
+ d->features_accepted, d->features);
+ goto feature_write_through32;
+ case offsetof(struct virtio_pci_mmio, cfg.device_status): {
+ u8 prev;
+
verbose("%s: device status -> %#x\n", d->name, val);
- if (val == 0)
- reset_pci_device(d);
+ /*
+ * 4.1.4.3.1:
+ *
+ * The device MUST reset when 0 is written to device_status,
+ * and present a 0 in device_status once that is done.
+ */
+ if (val == 0) {
+ reset_device(d);
+ goto write_through8;
+ }
+
+ /* 2.1.1: The driver MUST NOT clear a device status bit. */
+ if (d->mmio->cfg.device_status & ~val)
+ bad_driver(d, "unset of device status bit %#x -> %#x",
+ d->mmio->cfg.device_status, val);
+
+ /*
+ * 2.1.2:
+ *
+ * The device MUST NOT consume buffers or notify the driver
+ * before DRIVER_OK.
+ */
+ if (val & VIRTIO_CONFIG_S_DRIVER_OK
+ && !(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK))
+ start_virtqueues(d);
+
+ /*
+ * 3.1.1:
+ *
+ * The driver MUST follow this sequence to initialize a device:
+ * - Reset the device.
+ * - Set the ACKNOWLEDGE status bit: the guest OS has
+ * notice the device.
+ * - Set the DRIVER status bit: the guest OS knows how
+ * to drive the device.
+ * - Read device feature bits, and write the subset
+ * of feature bits understood by the OS and driver
+ * to the device. During this step the driver MAY
+ * read (but MUST NOT write) the device-specific
+ * configuration fields to check that it can
+ * support the device before accepting it.
+ * - Set the FEATURES_OK status bit. The driver
+ * MUST not accept new feature bits after this
+ * step.
+ * - Re-read device status to ensure the FEATURES_OK
+ * bit is still set: otherwise, the device does
+ * not support our subset of features and the
+ * device is unusable.
+ * - Perform device-specific setup, including
+ * discovery of virtqueues for the device,
+ * optional per-bus setup, reading and possibly
+ * writing the device’s virtio configuration
+ * space, and population of virtqueues.
+ * - Set the DRIVER_OK status bit. At this point the
+ * device is “live”.
+ */
+ prev = 0;
+ switch (val & ~d->mmio->cfg.device_status) {
+ case VIRTIO_CONFIG_S_DRIVER_OK:
+ prev |= VIRTIO_CONFIG_S_FEATURES_OK; /* fall thru */
+ case VIRTIO_CONFIG_S_FEATURES_OK:
+ prev |= VIRTIO_CONFIG_S_DRIVER; /* fall thru */
+ case VIRTIO_CONFIG_S_DRIVER:
+ prev |= VIRTIO_CONFIG_S_ACKNOWLEDGE; /* fall thru */
+ case VIRTIO_CONFIG_S_ACKNOWLEDGE:
+ break;
+ default:
+ bad_driver(d, "unknown device status bit %#x -> %#x",
+ d->mmio->cfg.device_status, val);
+ }
+ if (d->mmio->cfg.device_status != prev)
+ bad_driver(d, "unexpected status transition %#x -> %#x",
+ d->mmio->cfg.device_status, val);
+
+ /* If they just wrote FEATURES_OK, we make sure they read */
+ switch (val & ~d->mmio->cfg.device_status) {
+ case VIRTIO_CONFIG_S_FEATURES_OK:
+ d->wrote_features_ok = true;
+ break;
+ case VIRTIO_CONFIG_S_DRIVER_OK:
+ if (d->wrote_features_ok)
+ bad_driver(d, "did not re-read FEATURES_OK");
+ break;
+ }
goto write_through8;
+ }
case offsetof(struct virtio_pci_mmio, cfg.queue_select):
vq = vq_by_num(d, val);
- /* Out of range? Return size 0 */
+ /*
+ * 4.1.4.3.1:
+ *
+ * The device MUST present a 0 in queue_size if the virtqueue
+ * corresponding to the current queue_select is unavailable.
+ */
if (!vq) {
d->mmio->cfg.queue_size = 0;
goto write_through16;
restore_vq_config(&d->mmio->cfg, vq);
goto write_through16;
case offsetof(struct virtio_pci_mmio, cfg.queue_size):
+ /*
+ * 4.1.4.3.2:
+ *
+ * The driver MUST NOT write a value which is not a power of 2
+ * to queue_size.
+ */
if (val & (val-1))
- errx(1, "%s: invalid queue size %u\n", d->name, val);
+ bad_driver(d, "invalid queue size %u", val);
if (d->mmio->cfg.queue_enable)
- errx(1, "%s: changing queue size on live device",
- d->name);
+ bad_driver(d, "changing queue size on live device");
goto write_through16;
case offsetof(struct virtio_pci_mmio, cfg.queue_msix_vector):
- errx(1, "%s: attempt to set MSIX vector to %u",
- d->name, val);
- case offsetof(struct virtio_pci_mmio, cfg.queue_enable):
+ bad_driver(d, "attempt to set MSIX vector to %u", val);
+ case offsetof(struct virtio_pci_mmio, cfg.queue_enable): {
+ struct virtqueue *vq = vq_by_num(d, d->mmio->cfg.queue_select);
+
+ /*
+ * 4.1.4.3.2:
+ *
+ * The driver MUST NOT write a 0 to queue_enable.
+ */
if (val != 1)
- errx(1, "%s: setting queue_enable to %u", d->name, val);
+ bad_driver(d, "setting queue_enable to %u", val);
+
+ /*
+ * 3.1.1:
+ *
+ * 7. Perform device-specific setup, including discovery of
+ * virtqueues for the device, optional per-bus setup,
+ * reading and possibly writing the device’s virtio
+ * configuration space, and population of virtqueues.
+ * 8. Set the DRIVER_OK status bit.
+ *
+ * All our devices require all virtqueues to be enabled, so
+ * they should have done that before setting DRIVER_OK.
+ */
+ if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK)
+ bad_driver(d, "enabling vq after DRIVER_OK");
+
d->mmio->cfg.queue_enable = val;
- save_vq_config(&d->mmio->cfg,
- vq_by_num(d, d->mmio->cfg.queue_select));
- enable_virtqueue(d, vq_by_num(d, d->mmio->cfg.queue_select));
+ save_vq_config(&d->mmio->cfg, vq);
+ check_virtqueue(d, vq);
goto write_through16;
+ }
case offsetof(struct virtio_pci_mmio, cfg.queue_notify_off):
- errx(1, "%s: attempt to write to queue_notify_off", d->name);
+ bad_driver(d, "attempt to write to queue_notify_off");
case offsetof(struct virtio_pci_mmio, cfg.queue_desc_lo):
case offsetof(struct virtio_pci_mmio, cfg.queue_desc_hi):
case offsetof(struct virtio_pci_mmio, cfg.queue_avail_lo):
case offsetof(struct virtio_pci_mmio, cfg.queue_avail_hi):
case offsetof(struct virtio_pci_mmio, cfg.queue_used_lo):
case offsetof(struct virtio_pci_mmio, cfg.queue_used_hi):
+ /*
+ * 4.1.4.3.2:
+ *
+ * The driver MUST configure the other virtqueue fields before
+ * enabling the virtqueue with queue_enable.
+ */
if (d->mmio->cfg.queue_enable)
- errx(1, "%s: changing queue on live device",
- d->name);
+ bad_driver(d, "changing queue on live device");
+
+ /*
+ * 3.1.1:
+ *
+ * The driver MUST follow this sequence to initialize a device:
+ *...
+ * 5. Set the FEATURES_OK status bit. The driver MUST not
+ * accept new feature bits after this step.
+ */
+ if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK))
+ bad_driver(d, "setting up vq before FEATURES_OK");
+
+ /*
+ * 6. Re-read device status to ensure the FEATURES_OK bit is
+ * still set...
+ */
+ if (d->wrote_features_ok)
+ bad_driver(d, "didn't re-read FEATURES_OK before setup");
+
goto write_through32;
case offsetof(struct virtio_pci_mmio, notify):
vq = vq_by_num(d, val);
if (!vq)
- errx(1, "Invalid vq notification on %u", val);
+ bad_driver(d, "Invalid vq notification on %u", val);
/* Notify the process handling this vq by adding 1 to eventfd */
write(vq->eventfd, "\1\0\0\0\0\0\0\0", 8);
goto write_through16;
case offsetof(struct virtio_pci_mmio, isr):
- errx(1, "%s: Unexpected write to isr", d->name);
+ bad_driver(d, "Unexpected write to isr");
+ /* Weird corner case: write to emerg_wr of console */
+ case sizeof(struct virtio_pci_mmio)
+ + offsetof(struct virtio_console_config, emerg_wr):
+ if (strcmp(d->name, "console") == 0) {
+ char c = val;
+ write(STDOUT_FILENO, &c, 1);
+ goto write_through32;
+ }
+ /* Fall through... */
default:
- errx(1, "%s: Unexpected write to offset %u", d->name, off);
+ /*
+ * 4.1.4.3.2:
+ *
+ * The driver MUST NOT write to device_feature, num_queues,
+ * config_generation or queue_notify_off.
+ */
+ bad_driver(d, "Unexpected write to offset %u", off);
}
+feature_write_through32:
+ /*
+ * 3.1.1:
+ *
+ * The driver MUST follow this sequence to initialize a device:
+ *...
+ * - Set the DRIVER status bit: the guest OS knows how
+ * to drive the device.
+ * - Read device feature bits, and write the subset
+ * of feature bits understood by the OS and driver
+ * to the device.
+ *...
+ * - Set the FEATURES_OK status bit. The driver MUST not
+ * accept new feature bits after this step.
+ */
+ if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER))
+ bad_driver(d, "feature write before VIRTIO_CONFIG_S_DRIVER");
+ if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK)
+ bad_driver(d, "feature write after VIRTIO_CONFIG_S_FEATURES_OK");
+
+ /*
+ * 4.1.3.1:
+ *
+ * The driver MUST access each field using the “natural” access
+ * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for
+ * 16-bit fields and 8-bit accesses for 8-bit fields.
+ */
write_through32:
if (mask != 0xFFFFFFFF) {
- errx(1, "%s: non-32-bit write to offset %u (%#x)",
- d->name, off, getreg(eip));
+ bad_driver(d, "non-32-bit write to offset %u (%#x)",
+ off, getreg(eip));
return;
}
memcpy((char *)d->mmio + off, &val, 4);
write_through16:
if (mask != 0xFFFF)
- errx(1, "%s: non-16-bit (%#x) write to offset %u (%#x)",
- d->name, mask, off, getreg(eip));
+ bad_driver(d, "non-16-bit write to offset %u (%#x)",
+ off, getreg(eip));
memcpy((char *)d->mmio + off, &val, 2);
return;
write_through8:
if (mask != 0xFF)
- errx(1, "%s: non-8-bit write to offset %u (%#x)",
- d->name, off, getreg(eip));
+ bad_driver(d, "non-8-bit write to offset %u (%#x)",
+ off, getreg(eip));
memcpy((char *)d->mmio + off, &val, 1);
return;
}
case offsetof(struct virtio_pci_mmio, cfg.device_feature):
case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select):
case offsetof(struct virtio_pci_mmio, cfg.guest_feature):
+ /*
+ * 3.1.1:
+ *
+ * The driver MUST follow this sequence to initialize a device:
+ *...
+ * - Set the DRIVER status bit: the guest OS knows how
+ * to drive the device.
+ * - Read device feature bits, and write the subset
+ * of feature bits understood by the OS and driver
+ * to the device.
+ */
+ if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER))
+ bad_driver(d,
+ "feature read before VIRTIO_CONFIG_S_DRIVER");
goto read_through32;
case offsetof(struct virtio_pci_mmio, cfg.msix_config):
- errx(1, "%s: read of msix_config", d->name);
+ bad_driver(d, "read of msix_config");
case offsetof(struct virtio_pci_mmio, cfg.num_queues):
goto read_through16;
case offsetof(struct virtio_pci_mmio, cfg.device_status):
+ /* As they did read, any write of FEATURES_OK is now fine. */
+ d->wrote_features_ok = false;
+ goto read_through8;
case offsetof(struct virtio_pci_mmio, cfg.config_generation):
+ /*
+ * 4.1.4.3.1:
+ *
+ * The device MUST present a changed config_generation after
+ * the driver has read a device-specific configuration value
+ * which has changed since any part of the device-specific
+ * configuration was last read.
+ *
+ * This is simple: none of our devices change config, so this
+ * is always 0.
+ */
goto read_through8;
case offsetof(struct virtio_pci_mmio, notify):
+ /*
+ * 3.1.1:
+ *
+ * The driver MUST NOT notify the device before setting
+ * DRIVER_OK.
+ */
+ if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK))
+ bad_driver(d, "notify before VIRTIO_CONFIG_S_DRIVER_OK");
goto read_through16;
case offsetof(struct virtio_pci_mmio, isr):
if (mask != 0xFF)
- errx(1, "%s: non-8-bit read from offset %u (%#x)",
- d->name, off, getreg(eip));
- /* Read resets the isr */
+ bad_driver(d, "non-8-bit read from offset %u (%#x)",
+ off, getreg(eip));
isr = d->mmio->isr;
+ /*
+ * 4.1.4.5.1:
+ *
+ * The device MUST reset ISR status to 0 on driver read.
+ */
d->mmio->isr = 0;
return isr;
case offsetof(struct virtio_pci_mmio, padding):
- errx(1, "%s: read from padding (%#x)",
- d->name, getreg(eip));
+ bad_driver(d, "read from padding (%#x)", getreg(eip));
default:
/* Read from device config space, beware unaligned overflow */
if (off > d->mmio_size - 4)
- errx(1, "%s: read past end (%#x)",
- d->name, getreg(eip));
+ bad_driver(d, "read past end (%#x)", getreg(eip));
+
+ /*
+ * 3.1.1:
+ * The driver MUST follow this sequence to initialize a device:
+ *...
+ * 3. Set the DRIVER status bit: the guest OS knows how to
+ * drive the device.
+ * 4. Read device feature bits, and write the subset of
+ * feature bits understood by the OS and driver to the
+ * device. During this step the driver MAY read (but MUST NOT
+ * write) the device-specific configuration fields to check
+ * that it can support the device before accepting it.
+ */
+ if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER))
+ bad_driver(d,
+ "config read before VIRTIO_CONFIG_S_DRIVER");
+
if (mask == 0xFFFFFFFF)
goto read_through32;
else if (mask == 0xFFFF)
goto read_through8;
}
+ /*
+ * 4.1.3.1:
+ *
+ * The driver MUST access each field using the “natural” access
+ * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for
+ * 16-bit fields and 8-bit accesses for 8-bit fields.
+ */
read_through32:
if (mask != 0xFFFFFFFF)
- errx(1, "%s: non-32-bit read to offset %u (%#x)",
- d->name, off, getreg(eip));
+ bad_driver(d, "non-32-bit read to offset %u (%#x)",
+ off, getreg(eip));
memcpy(&val, (char *)d->mmio + off, 4);
return val;
read_through16:
if (mask != 0xFFFF)
- errx(1, "%s: non-16-bit read to offset %u (%#x)",
- d->name, off, getreg(eip));
+ bad_driver(d, "non-16-bit read to offset %u (%#x)",
+ off, getreg(eip));
memcpy(&val, (char *)d->mmio + off, 2);
return val;
read_through8:
if (mask != 0xFF)
- errx(1, "%s: non-8-bit read to offset %u (%#x)",
- d->name, off, getreg(eip));
+ bad_driver(d, "non-8-bit read to offset %u (%#x)",
+ off, getreg(eip));
memcpy(&val, (char *)d->mmio + off, 1);
return val;
}
* 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;
-}
-
static void add_pci_virtqueue(struct device *dev,
- void (*service)(struct virtqueue *))
+ void (*service)(struct virtqueue *),
+ const char *name)
{
struct virtqueue **i, *vq = malloc(sizeof(*vq));
vq->next = NULL;
vq->last_avail_idx = 0;
vq->dev = dev;
+ vq->name = name;
/*
* This is the routine the service thread will run, and its Process ID
vq->thread = (pid_t)-1;
/* Initialize the configuration. */
- vq->pci_config.queue_size = VIRTQUEUE_NUM;
- vq->pci_config.queue_enable = 0;
+ reset_vq_pci_config(vq);
vq->pci_config.queue_notify_off = 0;
/* Add one to the number of queues */
vq->dev->mmio->cfg.num_queues++;
- /* FIXME: Do irq per virtqueue, not per device. */
- vq->config.irq = vq->dev->config.irq_line;
-
/*
* Add to tail of list, so dev->vq is first vq, dev->vq->next is
* second.
*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));
-}
-
+/* The Guest accesses the feature bits via the PCI common config MMIO region */
static void add_pci_feature(struct device *dev, unsigned bit)
{
dev->features |= (1ULL << 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);
-}
-
/* For devices with no config. */
static void no_device_config(struct device *dev)
{
dev->mmio = realloc(dev->mmio, dev->mmio_size);
memcpy(dev->mmio + 1, conf, len);
+ /*
+ * 4.1.4.6:
+ *
+ * The device MUST present at least one VIRTIO_PCI_CAP_DEVICE_CFG
+ * capability for any device type which has a device-specific
+ * configuration.
+ */
/* Hook up device cfg */
dev->config.cfg_access.cap.cap_next
= offsetof(struct pci_config, device);
+ /*
+ * 4.1.4.6.1:
+ *
+ * The offset for the device-specific configuration MUST be 4-byte
+ * aligned.
+ */
+ assert(dev->config.cfg_access.cap.cap_next % 4 == 0);
+
/* Fix up device cfg field length. */
dev->config.device.length = len;
{
size_t bar_offset, bar_len;
- /* Save typing: most thing are happy being zero. */
+ /*
+ * 4.1.4.4.1:
+ *
+ * The device MUST either present notify_off_multiplier as an even
+ * power of 2, or present notify_off_multiplier as 0.
+ *
+ * 2.1.2:
+ *
+ * The device MUST initialize device status to 0 upon reset.
+ */
memset(pci, 0, sizeof(*pci));
/* 4.1.2.1: Devices MUST have the PCI Vendor ID 0x1AF4 */
pci->subclass = subclass;
/*
- * 4.1.2.1 Non-transitional devices SHOULD have a PCI Revision
- * ID of 1 or higher
+ * 4.1.2.1:
+ *
+ * Non-transitional devices SHOULD have a PCI Revision ID of 1 or
+ * higher
*/
pci->revid = 1;
/*
- * 4.1.2.1 Non-transitional devices SHOULD have a PCI
- * Subsystem Device ID of 0x40 or higher.
+ * 4.1.2.1:
+ *
+ * Non-transitional devices SHOULD have a PCI Subsystem Device ID of
+ * 0x40 or higher.
*/
pci->subsystem_device_id = 0x40;
pci->status = (1 << 4);
/* Link them in. */
+ /*
+ * 4.1.4.3.1:
+ *
+ * The device MUST present at least one common configuration
+ * capability.
+ */
pci->capabilities = offsetof(struct pci_config, common);
+ /* 4.1.4.3.1 ... offset MUST be 4-byte aligned. */
+ assert(pci->capabilities % 4 == 0);
+
bar_offset = offsetof(struct virtio_pci_mmio, cfg);
bar_len = sizeof(((struct virtio_pci_mmio *)0)->cfg);
init_cap(&pci->common, sizeof(pci->common), VIRTIO_PCI_CAP_COMMON_CFG,
bar_offset, bar_len,
offsetof(struct pci_config, notify));
+ /*
+ * 4.1.4.4.1:
+ *
+ * The device MUST present at least one notification capability.
+ */
bar_offset += bar_len;
bar_len = sizeof(((struct virtio_pci_mmio *)0)->notify);
+
+ /*
+ * 4.1.4.4.1:
+ *
+ * The cap.offset MUST be 2-byte aligned.
+ */
+ assert(pci->common.cap_next % 2 == 0);
+
/* FIXME: Use a non-zero notify_off, for per-queue notification? */
+ /*
+ * 4.1.4.4.1:
+ *
+ * The value cap.length presented by the device MUST be at least 2 and
+ * MUST be large enough to support queue notification offsets for all
+ * supported queues in all possible configurations.
+ */
+ assert(bar_len >= 2);
+
init_cap(&pci->notify.cap, sizeof(pci->notify),
VIRTIO_PCI_CAP_NOTIFY_CFG,
bar_offset, bar_len,
bar_offset += bar_len;
bar_len = sizeof(((struct virtio_pci_mmio *)0)->isr);
+ /*
+ * 4.1.4.5.1:
+ *
+ * The device MUST present at least one VIRTIO_PCI_CAP_ISR_CFG
+ * capability.
+ */
init_cap(&pci->isr, sizeof(pci->isr),
VIRTIO_PCI_CAP_ISR_CFG,
bar_offset, bar_len,
offsetof(struct pci_config, cfg_access));
+ /*
+ * 4.1.4.7.1:
+ *
+ * The device MUST present at least one VIRTIO_PCI_CAP_PCI_CFG
+ * capability.
+ */
/* This doesn't have any presence in the BAR */
init_cap(&pci->cfg_access.cap, sizeof(pci->cfg_access),
VIRTIO_PCI_CAP_PCI_CFG,
}
/*
- * 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.
+ * This routine does all the creation and setup of a new device, but we don't
+ * actually place the MMIO region until we know the size (if any) of the
+ * device-specific config. And 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;
- dev->next = NULL;
-
- /*
- * 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;
-}
-
static struct device *new_pci_device(const char *name, u16 type,
u8 class, u8 subclass)
{
struct device *dev = malloc(sizeof(*dev));
/* Now we populate the fields one at a time. */
- dev->desc = NULL;
dev->name = name;
dev->vq = NULL;
- dev->feature_len = 0;
- dev->num_vq = 0;
dev->running = false;
- dev->next = NULL;
+ dev->wrote_features_ok = false;
dev->mmio_size = sizeof(struct virtio_pci_mmio);
dev->mmio = calloc(1, dev->mmio_size);
dev->features = (u64)1 << VIRTIO_F_VERSION_1;
dev->features_accepted = 0;
- if (devices.device_num + 1 >= 32)
+ if (devices.device_num + 1 >= MAX_PCI_DEVICES)
errx(1, "Can only handle 31 PCI devices");
init_pci_config(&dev->config, type, class, subclass);
static void setup_console(void)
{
struct device *dev;
+ struct virtio_console_config conf;
/* If we can save the initial standard input settings... */
if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
* stdin. When they put something in the output queue, we write it to
* stdout.
*/
- add_pci_virtqueue(dev, console_input);
- add_pci_virtqueue(dev, console_output);
+ add_pci_virtqueue(dev, console_input, "input");
+ add_pci_virtqueue(dev, console_output, "output");
- /* There's no configuration area for this device. */
- no_device_config(dev);
+ /* We need a configuration area for the emerg_wr early writes. */
+ add_pci_feature(dev, VIRTIO_CONSOLE_F_EMERG_WRITE);
+ set_device_config(dev, &conf, sizeof(conf));
verbose("device %u: console\n", devices.device_num);
}
* about our expanded header (which is called
* virtio_net_hdr_mrg_rxbuf in the legacy system).
*/
- vnet_hdr_sz = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ vnet_hdr_sz = sizeof(struct virtio_net_hdr_v1);
if (ioctl(netfd, TUNSETVNETHDRSZ, &vnet_hdr_sz) != 0)
err(1, "Setting tun header size to %u", vnet_hdr_sz);
dev->priv = net_info;
/* Network devices need a recv and a send queue, just like console. */
- add_pci_virtqueue(dev, net_input);
- add_pci_virtqueue(dev, net_output);
+ add_pci_virtqueue(dev, net_input, "rx");
+ add_pci_virtqueue(dev, net_output, "tx");
/*
* We need a socket to perform the magic network ioctls to bring up the
head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
/* Copy the output header from the front of the iov (adjusts iov) */
- iov_consume(iov, out_num, &out, sizeof(out));
+ iov_consume(vq->dev, iov, out_num, &out, sizeof(out));
/* Find and trim end of iov input array, for our status byte. */
in = NULL;
}
}
if (!in)
- errx(1, "Bad virtblk cmd with no room for status");
+ bad_driver_vq(vq, "Bad virtblk cmd with no room for status");
/*
* For historical reasons, block operations are expressed in 512 byte
/* 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);
+ bad_driver_vq(vq, "Write past end %llu+%u", off, ret);
}
wlen = sizeof(*in);
dev = new_pci_device("block", VIRTIO_ID_BLOCK, 0x01, 0x80);
/* The device has one virtqueue, where the Guest places requests. */
- add_pci_virtqueue(dev, blk_request);
+ add_pci_virtqueue(dev, blk_request, "request");
/* Allocate the room for our own bookkeeping */
vblk = dev->priv = malloc(sizeof(*vblk));
/* 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?");
+ bad_driver_vq(vq, "Output buffers in rng?");
/*
* Just like the console write, we loop to cover the whole iovec.
len = readv(rng_info->rfd, iov, in_num);
if (len <= 0)
err(1, "Read from /dev/urandom gave %i", len);
- iov_consume(iov, in_num, NULL, len);
+ iov_consume(vq->dev, iov, in_num, NULL, len);
totlen += len;
}
dev->priv = rng_info;
/* The device has one virtqueue, where the Guest places inbufs. */
- add_pci_virtqueue(dev, rng_input);
+ add_pci_virtqueue(dev, rng_input, "input");
/* We don't have any configuration space */
no_device_config(dev);
/* We read from the /dev/lguest device to run the Guest. */
readval = pread(lguest_fd, ¬ify, sizeof(notify), cpu_id);
-
- /* One unsigned long means the Guest did HCALL_NOTIFY */
if (readval == sizeof(notify)) {
- if (notify.trap == 0x1F) {
- verbose("Notify on address %#08x\n",
- notify.addr);
- handle_output(notify.addr);
- } else if (notify.trap == 13) {
+ if (notify.trap == 13) {
verbose("Emulating instruction at %#x\n",
getreg(eip));
emulate_insn(notify.insn);
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).
+ * First we initialize the device list. We remember 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. */
+ DEVICE_PAGES);
guest_limit = mem;
guest_max = guest_mmio = mem + DEVICE_PAGES*getpagesize();
- devices.descpage = get_pages(1);
break;
}
}
+ /* We always have a console device, and it's always device 1. */
+ setup_console();
+
/* The options are fairly straight-forward */
while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) {
switch (c) {
verbose("Guest base is at %p\n", guest_base);
- /* We always have a console device */
- setup_console();
-
/* Initialize the (fake) PCI host bridge device. */
init_pci_host_bridge();