* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
+#include "qemu/osdep.h"
#include "hw/hw.h"
#include "hw/i386/pc.h"
#include "hw/pci/pci.h"
+#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
#include "sysemu/kvm.h"
#include "migration/migration.h"
#include "qemu/event_notifier.h"
#include "qemu/fifo8.h"
#include "sysemu/char.h"
+#include "sysemu/hostmem.h"
+#include "qapi/visitor.h"
+#include "exec/ram_addr.h"
+
+#include "hw/misc/ivshmem.h"
#include <sys/mman.h>
-#include <sys/types.h>
-#include <limits.h>
#define PCI_VENDOR_ID_IVSHMEM PCI_VENDOR_ID_REDHAT_QUMRANET
#define PCI_DEVICE_ID_IVSHMEM 0x1110
+#define IVSHMEM_MAX_PEERS UINT16_MAX
#define IVSHMEM_IOEVENTFD 0
#define IVSHMEM_MSI 1
#define IVSHMEM_REG_BAR_SIZE 0x100
-//#define DEBUG_IVSHMEM
-#ifdef DEBUG_IVSHMEM
-#define IVSHMEM_DPRINTF(fmt, ...) \
- do {printf("IVSHMEM: " fmt, ## __VA_ARGS__); } while (0)
-#else
-#define IVSHMEM_DPRINTF(fmt, ...)
-#endif
+#define IVSHMEM_DEBUG 0
+#define IVSHMEM_DPRINTF(fmt, ...) \
+ do { \
+ if (IVSHMEM_DEBUG) { \
+ printf("IVSHMEM: " fmt, ## __VA_ARGS__); \
+ } \
+ } while (0)
#define TYPE_IVSHMEM "ivshmem"
#define IVSHMEM(obj) \
EventNotifier *eventfds;
} Peer;
-typedef struct EventfdEntry {
+typedef struct MSIVector {
PCIDevice *pdev;
- int vector;
-} EventfdEntry;
+ int virq;
+} MSIVector;
typedef struct IVShmemState {
/*< private >*/
PCIDevice parent_obj;
/*< public >*/
+ HostMemoryBackend *hostmem;
uint32_t intrmask;
uint32_t intrstatus;
- CharDriverState **eventfd_chr;
CharDriverState *server_chr;
Fifo8 incoming_fifo;
MemoryRegion ivshmem_mmio;
MemoryRegion ivshmem;
uint64_t ivshmem_size; /* size of shared memory region */
uint32_t ivshmem_64bit;
- int shm_fd; /* shared memory file descriptor */
Peer *peers;
- int nb_peers; /* how many guests we have space for */
- int max_peer; /* maximum numbered peer */
+ int nb_peers; /* space in @peers[] */
int vm_id;
uint32_t vectors;
uint32_t features;
- EventfdEntry *eventfd_table;
+ MSIVector *msi_vectors;
Error *migration_blocker;
return (ivs->features & (1 << feature));
}
-static inline bool is_power_of_two(uint64_t x) {
- return (x & (x - 1)) == 0;
-}
-
-/* accessing registers - based on rtl8139 */
-static void ivshmem_update_irq(IVShmemState *s, int val)
+static void ivshmem_update_irq(IVShmemState *s)
{
PCIDevice *d = PCI_DEVICE(s);
- int isr;
- isr = (s->intrstatus & s->intrmask) & 0xffffffff;
+ uint32_t isr = s->intrstatus & s->intrmask;
+
+ /* No INTx with msi=on, whether the guest enabled MSI-X or not */
+ if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
+ return;
+ }
/* don't print ISR resets */
if (isr) {
isr ? 1 : 0, s->intrstatus, s->intrmask);
}
- pci_set_irq(d, (isr != 0));
+ pci_set_irq(d, isr != 0);
}
static void ivshmem_IntrMask_write(IVShmemState *s, uint32_t val)
IVSHMEM_DPRINTF("IntrMask write(w) val = 0x%04x\n", val);
s->intrmask = val;
-
- ivshmem_update_irq(s, val);
+ ivshmem_update_irq(s);
}
static uint32_t ivshmem_IntrMask_read(IVShmemState *s)
uint32_t ret = s->intrmask;
IVSHMEM_DPRINTF("intrmask read(w) val = 0x%04x\n", ret);
-
return ret;
}
IVSHMEM_DPRINTF("IntrStatus write(w) val = 0x%04x\n", val);
s->intrstatus = val;
-
- ivshmem_update_irq(s, val);
+ ivshmem_update_irq(s);
}
static uint32_t ivshmem_IntrStatus_read(IVShmemState *s)
/* reading ISR clears all interrupts */
s->intrstatus = 0;
-
- ivshmem_update_irq(s, 0);
-
+ ivshmem_update_irq(s);
return ret;
}
case DOORBELL:
/* check that dest VM ID is reasonable */
- if (dest > s->max_peer) {
+ if (dest >= s->nb_peers) {
IVSHMEM_DPRINTF("Invalid destination VM ID (%d)\n", dest);
break;
}
if (vector < s->peers[dest].nb_eventfds) {
IVSHMEM_DPRINTF("Notifying VM %d on vector %d\n", dest, vector);
event_notifier_set(&s->peers[dest].eventfds[vector]);
+ } else {
+ IVSHMEM_DPRINTF("Invalid destination vector %d on VM %d\n",
+ vector, dest);
}
break;
default:
- IVSHMEM_DPRINTF("Invalid VM Doorbell VM %d\n", dest);
+ IVSHMEM_DPRINTF("Unhandled write " TARGET_FMT_plx "\n", addr);
}
}
break;
case IVPOSITION:
- /* return my VM ID if the memory is mapped */
- if (s->shm_fd > 0) {
- ret = s->vm_id;
- } else {
- ret = -1;
- }
+ ret = s->vm_id;
break;
default:
},
};
-static void ivshmem_receive(void *opaque, const uint8_t *buf, int size)
+static int ivshmem_can_receive(void * opaque)
{
- IVShmemState *s = opaque;
-
- ivshmem_IntrStatus_write(s, *buf);
-
- IVSHMEM_DPRINTF("ivshmem_receive 0x%02x\n", *buf);
+ return sizeof(int64_t);
}
-static int ivshmem_can_receive(void * opaque)
+static void ivshmem_vector_notify(void *opaque)
{
- return sizeof(long);
+ MSIVector *entry = opaque;
+ PCIDevice *pdev = entry->pdev;
+ IVShmemState *s = IVSHMEM(pdev);
+ int vector = entry - s->msi_vectors;
+ EventNotifier *n = &s->peers[s->vm_id].eventfds[vector];
+
+ if (!event_notifier_test_and_clear(n)) {
+ return;
+ }
+
+ IVSHMEM_DPRINTF("interrupt on vector %p %d\n", pdev, vector);
+ if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
+ if (msix_enabled(pdev)) {
+ msix_notify(pdev, vector);
+ }
+ } else {
+ ivshmem_IntrStatus_write(s, 1);
+ }
}
-static void ivshmem_event(void *opaque, int event)
+static int ivshmem_vector_unmask(PCIDevice *dev, unsigned vector,
+ MSIMessage msg)
{
- IVSHMEM_DPRINTF("ivshmem_event %d\n", event);
-}
+ IVShmemState *s = IVSHMEM(dev);
+ EventNotifier *n = &s->peers[s->vm_id].eventfds[vector];
+ MSIVector *v = &s->msi_vectors[vector];
+ int ret;
-static void fake_irqfd(void *opaque, const uint8_t *buf, int size) {
+ IVSHMEM_DPRINTF("vector unmask %p %d\n", dev, vector);
- EventfdEntry *entry = opaque;
- PCIDevice *pdev = entry->pdev;
+ ret = kvm_irqchip_update_msi_route(kvm_state, v->virq, msg, dev);
+ if (ret < 0) {
+ return ret;
+ }
- IVSHMEM_DPRINTF("interrupt on vector %p %d\n", pdev, entry->vector);
- msix_notify(pdev, entry->vector);
+ return kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, n, NULL, v->virq);
}
-static CharDriverState* create_eventfd_chr_device(void * opaque, EventNotifier *n,
- int vector)
+static void ivshmem_vector_mask(PCIDevice *dev, unsigned vector)
{
- /* create a event character device based on the passed eventfd */
- IVShmemState *s = opaque;
- CharDriverState * chr;
- int eventfd = event_notifier_get_fd(n);
+ IVShmemState *s = IVSHMEM(dev);
+ EventNotifier *n = &s->peers[s->vm_id].eventfds[vector];
+ int ret;
- chr = qemu_chr_open_eventfd(eventfd);
+ IVSHMEM_DPRINTF("vector mask %p %d\n", dev, vector);
- if (chr == NULL) {
- error_report("creating eventfd for eventfd %d failed", eventfd);
- exit(1);
+ ret = kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, n,
+ s->msi_vectors[vector].virq);
+ if (ret != 0) {
+ error_report("remove_irqfd_notifier_gsi failed");
}
- qemu_chr_fe_claim_no_fail(chr);
+}
- /* if MSI is supported we need multiple interrupts */
- if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
- s->eventfd_table[vector].pdev = PCI_DEVICE(s);
- s->eventfd_table[vector].vector = vector;
+static void ivshmem_vector_poll(PCIDevice *dev,
+ unsigned int vector_start,
+ unsigned int vector_end)
+{
+ IVShmemState *s = IVSHMEM(dev);
+ unsigned int vector;
- qemu_chr_add_handlers(chr, ivshmem_can_receive, fake_irqfd,
- ivshmem_event, &s->eventfd_table[vector]);
- } else {
- qemu_chr_add_handlers(chr, ivshmem_can_receive, ivshmem_receive,
- ivshmem_event, s);
+ IVSHMEM_DPRINTF("vector poll %p %d-%d\n", dev, vector_start, vector_end);
+
+ vector_end = MIN(vector_end, s->vectors);
+
+ for (vector = vector_start; vector < vector_end; vector++) {
+ EventNotifier *notifier = &s->peers[s->vm_id].eventfds[vector];
+
+ if (!msix_is_masked(dev, vector)) {
+ continue;
+ }
+
+ if (event_notifier_test_and_clear(notifier)) {
+ msix_set_pending(dev, vector);
+ }
}
+}
- return chr;
+static void watch_vector_notifier(IVShmemState *s, EventNotifier *n,
+ int vector)
+{
+ int eventfd = event_notifier_get_fd(n);
+
+ assert(!s->msi_vectors[vector].pdev);
+ s->msi_vectors[vector].pdev = PCI_DEVICE(s);
+ qemu_set_fd_handler(eventfd, ivshmem_vector_notify,
+ NULL, &s->msi_vectors[vector]);
}
-static int check_shm_size(IVShmemState *s, int fd) {
+static int check_shm_size(IVShmemState *s, int fd, Error **errp)
+{
/* check that the guest isn't going to try and map more memory than the
* the object has allocated return -1 to indicate error */
struct stat buf;
if (fstat(fd, &buf) < 0) {
- error_report("exiting: fstat on fd %d failed: %s",
- fd, strerror(errno));
+ error_setg(errp, "exiting: fstat on fd %d failed: %s",
+ fd, strerror(errno));
return -1;
}
if (s->ivshmem_size > buf.st_size) {
- error_report("Requested memory size greater"
- " than shared object size (%" PRIu64 " > %" PRIu64")",
- s->ivshmem_size, (uint64_t)buf.st_size);
+ error_setg(errp, "Requested memory size greater"
+ " than shared object size (%" PRIu64 " > %" PRIu64")",
+ s->ivshmem_size, (uint64_t)buf.st_size);
return -1;
} else {
return 0;
/* create the shared memory BAR when we are not using the server, so we can
* create the BAR and map the memory immediately */
-static void create_shared_memory_BAR(IVShmemState *s, int fd, uint8_t attr) {
-
+static int create_shared_memory_BAR(IVShmemState *s, int fd, uint8_t attr,
+ Error **errp)
+{
void * ptr;
- s->shm_fd = fd;
-
ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
+ if (ptr == MAP_FAILED) {
+ error_setg_errno(errp, errno, "Failed to mmap shared memory");
+ return -1;
+ }
memory_region_init_ram_ptr(&s->ivshmem, OBJECT(s), "ivshmem.bar2",
s->ivshmem_size, ptr);
+ qemu_set_ram_fd(memory_region_get_ram_addr(&s->ivshmem), fd);
vmstate_register_ram(&s->ivshmem, DEVICE(s));
memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
/* region for shared memory */
pci_register_bar(PCI_DEVICE(s), 2, attr, &s->bar);
+
+ return 0;
}
static void ivshmem_add_eventfd(IVShmemState *s, int posn, int i)
&s->peers[posn].eventfds[i]);
}
-static void close_guest_eventfds(IVShmemState *s, int posn)
+static void close_peer_eventfds(IVShmemState *s, int posn)
{
- int i, guest_curr_max;
+ int i, n;
- if (!ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
- return;
- }
- if (posn < 0 || posn >= s->nb_peers) {
- return;
- }
-
- guest_curr_max = s->peers[posn].nb_eventfds;
+ assert(posn >= 0 && posn < s->nb_peers);
+ n = s->peers[posn].nb_eventfds;
- memory_region_transaction_begin();
- for (i = 0; i < guest_curr_max; i++) {
- ivshmem_del_eventfd(s, posn, i);
+ if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
+ memory_region_transaction_begin();
+ for (i = 0; i < n; i++) {
+ ivshmem_del_eventfd(s, posn, i);
+ }
+ memory_region_transaction_commit();
}
- memory_region_transaction_commit();
- for (i = 0; i < guest_curr_max; i++) {
+
+ for (i = 0; i < n; i++) {
event_notifier_cleanup(&s->peers[posn].eventfds[i]);
}
s->peers[posn].nb_eventfds = 0;
}
-/* this function increase the dynamic storage need to store data about other
- * guests */
-static int increase_dynamic_storage(IVShmemState *s, int new_min_size)
+static void resize_peers(IVShmemState *s, int nb_peers)
{
+ int old_nb_peers = s->nb_peers;
+ int i;
- int j, old_nb_alloc;
-
- /* check for integer overflow */
- if (new_min_size >= INT_MAX / sizeof(Peer) - 1 || new_min_size <= 0) {
- return -1;
- }
-
- old_nb_alloc = s->nb_peers;
-
- if (new_min_size >= s->nb_peers) {
- /* +1 because #new_min_size is used as last array index */
- s->nb_peers = new_min_size + 1;
- } else {
- return 0;
- }
+ assert(nb_peers > old_nb_peers);
+ IVSHMEM_DPRINTF("bumping storage to %d peers\n", nb_peers);
- IVSHMEM_DPRINTF("bumping storage to %d guests\n", s->nb_peers);
- s->peers = g_realloc(s->peers, s->nb_peers * sizeof(Peer));
+ s->peers = g_realloc(s->peers, nb_peers * sizeof(Peer));
+ s->nb_peers = nb_peers;
- /* zero out new pointers */
- for (j = old_nb_alloc; j < s->nb_peers; j++) {
- s->peers[j].eventfds = NULL;
- s->peers[j].nb_eventfds = 0;
+ for (i = old_nb_peers; i < nb_peers; i++) {
+ s->peers[i].eventfds = g_new0(EventNotifier, s->vectors);
+ s->peers[i].nb_eventfds = 0;
}
-
- return 0;
}
static bool fifo_update_and_get(IVShmemState *s, const uint8_t *buf, int size,
const uint8_t *p;
uint32_t num;
- assert(len <= sizeof(long)); /* limitation of the fifo */
+ assert(len <= sizeof(int64_t)); /* limitation of the fifo */
if (fifo8_is_empty(&s->incoming_fifo) && size == len) {
memcpy(data, buf, size);
return true;
IVSHMEM_DPRINTF("short read of %d bytes\n", size);
- num = MIN(size, sizeof(long) - fifo8_num_used(&s->incoming_fifo));
+ num = MIN(size, sizeof(int64_t) - fifo8_num_used(&s->incoming_fifo));
fifo8_push_all(&s->incoming_fifo, buf, num);
if (fifo8_num_used(&s->incoming_fifo) < len) {
return true;
}
-static void ivshmem_read(void *opaque, const uint8_t *buf, int size)
+static bool fifo_update_and_get_i64(IVShmemState *s,
+ const uint8_t *buf, int size, int64_t *i64)
{
- IVShmemState *s = opaque;
- int incoming_fd;
- int guest_max_eventfd;
- long incoming_posn;
-
- if (!fifo_update_and_get(s, buf, size,
- &incoming_posn, sizeof(incoming_posn))) {
- return;
+ if (fifo_update_and_get(s, buf, size, i64, sizeof(*i64))) {
+ *i64 = GINT64_FROM_LE(*i64);
+ return true;
}
- if (incoming_posn < -1) {
- IVSHMEM_DPRINTF("invalid incoming_posn %ld\n", incoming_posn);
+ return false;
+}
+
+static void ivshmem_add_kvm_msi_virq(IVShmemState *s, int vector,
+ Error **errp)
+{
+ PCIDevice *pdev = PCI_DEVICE(s);
+ MSIMessage msg = msix_get_message(pdev, vector);
+ int ret;
+
+ IVSHMEM_DPRINTF("ivshmem_add_kvm_msi_virq vector:%d\n", vector);
+ assert(!s->msi_vectors[vector].pdev);
+
+ ret = kvm_irqchip_add_msi_route(kvm_state, msg, pdev);
+ if (ret < 0) {
+ error_setg(errp, "kvm_irqchip_add_msi_route failed");
return;
}
- /* pick off s->server_chr->msgfd and store it, posn should accompany msg */
- incoming_fd = qemu_chr_fe_get_msgfd(s->server_chr);
- IVSHMEM_DPRINTF("posn is %ld, fd is %d\n", incoming_posn, incoming_fd);
+ s->msi_vectors[vector].virq = ret;
+ s->msi_vectors[vector].pdev = pdev;
+}
- /* make sure we have enough space for this guest */
- if (incoming_posn >= s->nb_peers) {
- if (increase_dynamic_storage(s, incoming_posn) < 0) {
- error_report("increase_dynamic_storage() failed");
- if (incoming_fd != -1) {
- close(incoming_fd);
- }
+static void setup_interrupt(IVShmemState *s, int vector, Error **errp)
+{
+ EventNotifier *n = &s->peers[s->vm_id].eventfds[vector];
+ bool with_irqfd = kvm_msi_via_irqfd_enabled() &&
+ ivshmem_has_feature(s, IVSHMEM_MSI);
+ PCIDevice *pdev = PCI_DEVICE(s);
+ Error *err = NULL;
+
+ IVSHMEM_DPRINTF("setting up interrupt for vector: %d\n", vector);
+
+ if (!with_irqfd) {
+ IVSHMEM_DPRINTF("with eventfd\n");
+ watch_vector_notifier(s, n, vector);
+ } else if (msix_enabled(pdev)) {
+ IVSHMEM_DPRINTF("with irqfd\n");
+ ivshmem_add_kvm_msi_virq(s, vector, &err);
+ if (err) {
+ error_propagate(errp, err);
return;
}
- }
- if (incoming_fd == -1) {
- /* if posn is positive and unseen before then this is our posn*/
- if ((incoming_posn >= 0) &&
- (s->peers[incoming_posn].eventfds == NULL)) {
- /* receive our posn */
- s->vm_id = incoming_posn;
- return;
- } else {
- /* otherwise an fd == -1 means an existing guest has gone away */
- IVSHMEM_DPRINTF("posn %ld has gone away\n", incoming_posn);
- close_guest_eventfds(s, incoming_posn);
- return;
+ if (!msix_is_masked(pdev, vector)) {
+ kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, n, NULL,
+ s->msi_vectors[vector].virq);
+ /* TODO handle error */
}
+ } else {
+ /* it will be delayed until msix is enabled, in write_config */
+ IVSHMEM_DPRINTF("with irqfd, delayed until msix enabled\n");
+ }
+}
+
+static void process_msg_shmem(IVShmemState *s, int fd, Error **errp)
+{
+ Error *err = NULL;
+ void *ptr;
+
+ if (memory_region_is_mapped(&s->ivshmem)) {
+ error_setg(errp, "server sent unexpected shared memory message");
+ close(fd);
+ return;
}
- /* if the position is -1, then it's shared memory region fd */
- if (incoming_posn == -1) {
+ if (check_shm_size(s, fd, &err) == -1) {
+ error_propagate(errp, err);
+ close(fd);
+ return;
+ }
- void * map_ptr;
+ /* mmap the region and map into the BAR2 */
+ ptr = mmap(0, s->ivshmem_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ if (ptr == MAP_FAILED) {
+ error_setg_errno(errp, errno, "Failed to mmap shared memory");
+ close(fd);
+ return;
+ }
+ memory_region_init_ram_ptr(&s->ivshmem, OBJECT(s),
+ "ivshmem.bar2", s->ivshmem_size, ptr);
+ qemu_set_ram_fd(memory_region_get_ram_addr(&s->ivshmem), fd);
+ vmstate_register_ram(&s->ivshmem, DEVICE(s));
+ memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
+}
- s->max_peer = 0;
+static void process_msg_disconnect(IVShmemState *s, uint16_t posn,
+ Error **errp)
+{
+ IVSHMEM_DPRINTF("posn %d has gone away\n", posn);
+ if (posn >= s->nb_peers || posn == s->vm_id) {
+ error_setg(errp, "invalid peer %d", posn);
+ return;
+ }
+ close_peer_eventfds(s, posn);
+}
- if (check_shm_size(s, incoming_fd) == -1) {
- exit(1);
- }
+static void process_msg_connect(IVShmemState *s, uint16_t posn, int fd,
+ Error **errp)
+{
+ Peer *peer = &s->peers[posn];
+ int vector;
- /* mmap the region and map into the BAR2 */
- map_ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED,
- incoming_fd, 0);
- memory_region_init_ram_ptr(&s->ivshmem, OBJECT(s),
- "ivshmem.bar2", s->ivshmem_size, map_ptr);
- vmstate_register_ram(&s->ivshmem, DEVICE(s));
+ /*
+ * The N-th connect message for this peer comes with the file
+ * descriptor for vector N-1. Count messages to find the vector.
+ */
+ if (peer->nb_eventfds >= s->vectors) {
+ error_setg(errp, "Too many eventfd received, device has %d vectors",
+ s->vectors);
+ close(fd);
+ return;
+ }
+ vector = peer->nb_eventfds++;
- IVSHMEM_DPRINTF("guest h/w addr = %p, size = %" PRIu64 "\n",
- map_ptr, s->ivshmem_size);
+ IVSHMEM_DPRINTF("eventfds[%d][%d] = %d\n", posn, vector, fd);
+ event_notifier_init_fd(&peer->eventfds[vector], fd);
+ fcntl_setfl(fd, O_NONBLOCK); /* msix/irqfd poll non block */
+
+ if (posn == s->vm_id) {
+ setup_interrupt(s, vector, errp);
+ /* TODO do we need to handle the error? */
+ }
- memory_region_add_subregion(&s->bar, 0, &s->ivshmem);
+ if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
+ ivshmem_add_eventfd(s, posn, vector);
+ }
+}
- /* only store the fd if it is successfully mapped */
- s->shm_fd = incoming_fd;
+static void process_msg(IVShmemState *s, int64_t msg, int fd, Error **errp)
+{
+ IVSHMEM_DPRINTF("posn is %" PRId64 ", fd is %d\n", msg, fd);
+ if (msg < -1 || msg > IVSHMEM_MAX_PEERS) {
+ error_setg(errp, "server sent invalid message %" PRId64, msg);
+ close(fd);
return;
}
- /* each guest has an array of eventfds, and we keep track of how many
- * guests for each VM */
- guest_max_eventfd = s->peers[incoming_posn].nb_eventfds;
+ if (msg == -1) {
+ process_msg_shmem(s, fd, errp);
+ return;
+ }
- if (guest_max_eventfd == 0) {
- /* one eventfd per MSI vector */
- s->peers[incoming_posn].eventfds = g_new(EventNotifier, s->vectors);
+ if (msg >= s->nb_peers) {
+ resize_peers(s, msg + 1);
}
- /* this is an eventfd for a particular guest VM */
- IVSHMEM_DPRINTF("eventfds[%ld][%d] = %d\n", incoming_posn,
- guest_max_eventfd, incoming_fd);
- event_notifier_init_fd(&s->peers[incoming_posn].eventfds[guest_max_eventfd],
- incoming_fd);
+ if (fd >= 0) {
+ process_msg_connect(s, msg, fd, errp);
+ } else if (s->vm_id == -1) {
+ s->vm_id = msg;
+ } else {
+ process_msg_disconnect(s, msg, errp);
+ }
+}
- /* increment count for particular guest */
- s->peers[incoming_posn].nb_eventfds++;
+static void ivshmem_read(void *opaque, const uint8_t *buf, int size)
+{
+ IVShmemState *s = opaque;
+ Error *err = NULL;
+ int fd;
+ int64_t msg;
- /* keep track of the maximum VM ID */
- if (incoming_posn > s->max_peer) {
- s->max_peer = incoming_posn;
+ if (!fifo_update_and_get_i64(s, buf, size, &msg)) {
+ return;
}
- if (incoming_posn == s->vm_id) {
- s->eventfd_chr[guest_max_eventfd] = create_eventfd_chr_device(s,
- &s->peers[s->vm_id].eventfds[guest_max_eventfd],
- guest_max_eventfd);
+ fd = qemu_chr_fe_get_msgfd(s->server_chr);
+ IVSHMEM_DPRINTF("posn is %" PRId64 ", fd is %d\n", msg, fd);
+
+ process_msg(s, msg, fd, &err);
+ if (err) {
+ error_report_err(err);
}
+}
- if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
- ivshmem_add_eventfd(s, incoming_posn, guest_max_eventfd);
+static int64_t ivshmem_recv_msg(IVShmemState *s, int *pfd, Error **errp)
+{
+ int64_t msg;
+ int n, ret;
+
+ n = 0;
+ do {
+ ret = qemu_chr_fe_read_all(s->server_chr, (uint8_t *)&msg + n,
+ sizeof(msg) - n);
+ if (ret < 0 && ret != -EINTR) {
+ error_setg_errno(errp, -ret, "read from server failed");
+ return INT64_MIN;
+ }
+ n += ret;
+ } while (n < sizeof(msg));
+
+ *pfd = qemu_chr_fe_get_msgfd(s->server_chr);
+ return msg;
+}
+
+static void ivshmem_recv_setup(IVShmemState *s, Error **errp)
+{
+ Error *err = NULL;
+ int64_t msg;
+ int fd;
+
+ msg = ivshmem_recv_msg(s, &fd, &err);
+ if (err) {
+ error_propagate(errp, err);
+ return;
}
+ if (msg != IVSHMEM_PROTOCOL_VERSION) {
+ error_setg(errp, "server sent version %" PRId64 ", expecting %d",
+ msg, IVSHMEM_PROTOCOL_VERSION);
+ return;
+ }
+ if (fd != -1) {
+ error_setg(errp, "server sent invalid version message");
+ return;
+ }
+
+ /*
+ * Receive more messages until we got shared memory.
+ */
+ do {
+ msg = ivshmem_recv_msg(s, &fd, &err);
+ if (err) {
+ error_propagate(errp, err);
+ return;
+ }
+ process_msg(s, msg, fd, &err);
+ if (err) {
+ error_propagate(errp, err);
+ return;
+ }
+ } while (msg != -1);
+
+ /*
+ * This function must either map the shared memory or fail. The
+ * loop above ensures that: it terminates normally only after it
+ * successfully processed the server's shared memory message.
+ * Assert that actually mapped the shared memory:
+ */
+ assert(memory_region_is_mapped(&s->ivshmem));
}
/* Select the MSI-X vectors used by device.
* ivshmem maps events to vectors statically, so
* we just enable all vectors on init and after reset. */
-static void ivshmem_use_msix(IVShmemState * s)
+static void ivshmem_msix_vector_use(IVShmemState *s)
{
PCIDevice *d = PCI_DEVICE(s);
int i;
- if (!msix_present(d)) {
- return;
- }
-
for (i = 0; i < s->vectors; i++) {
msix_vector_use(d, i);
}
IVShmemState *s = IVSHMEM(d);
s->intrstatus = 0;
- ivshmem_use_msix(s);
-}
-
-static uint64_t ivshmem_get_size(IVShmemState * s) {
-
- uint64_t value;
- char *ptr;
-
- value = strtoull(s->sizearg, &ptr, 10);
- switch (*ptr) {
- case 0: case 'M': case 'm':
- value <<= 20;
- break;
- case 'G': case 'g':
- value <<= 30;
- break;
- default:
- error_report("invalid ram size: %s", s->sizearg);
- exit(1);
- }
-
- /* BARs must be a power of 2 */
- if (!is_power_of_two(value)) {
- error_report("size must be power of 2");
- exit(1);
+ s->intrmask = 0;
+ if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
+ ivshmem_msix_vector_use(s);
}
-
- return value;
}
-static void ivshmem_setup_msi(IVShmemState * s)
+static int ivshmem_setup_interrupts(IVShmemState *s)
{
- if (msix_init_exclusive_bar(PCI_DEVICE(s), s->vectors, 1)) {
- IVSHMEM_DPRINTF("msix initialization failed\n");
- exit(1);
- }
+ /* allocate QEMU callback data for receiving interrupts */
+ s->msi_vectors = g_malloc0(s->vectors * sizeof(MSIVector));
- IVSHMEM_DPRINTF("msix initialized (%d vectors)\n", s->vectors);
+ if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
+ if (msix_init_exclusive_bar(PCI_DEVICE(s), s->vectors, 1)) {
+ return -1;
+ }
- /* allocate QEMU char devices for receiving interrupts */
- s->eventfd_table = g_malloc0(s->vectors * sizeof(EventfdEntry));
+ IVSHMEM_DPRINTF("msix initialized (%d vectors)\n", s->vectors);
+ ivshmem_msix_vector_use(s);
+ }
- ivshmem_use_msix(s);
+ return 0;
}
-static void ivshmem_save(QEMUFile* f, void *opaque)
+static void ivshmem_enable_irqfd(IVShmemState *s)
{
- IVShmemState *proxy = opaque;
- PCIDevice *pci_dev = PCI_DEVICE(proxy);
+ PCIDevice *pdev = PCI_DEVICE(s);
+ int i;
- IVSHMEM_DPRINTF("ivshmem_save\n");
- pci_device_save(pci_dev, f);
+ for (i = 0; i < s->peers[s->vm_id].nb_eventfds; i++) {
+ Error *err = NULL;
- if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) {
- msix_save(pci_dev, f);
- } else {
- qemu_put_be32(f, proxy->intrstatus);
- qemu_put_be32(f, proxy->intrmask);
+ ivshmem_add_kvm_msi_virq(s, i, &err);
+ if (err) {
+ error_report_err(err);
+ /* TODO do we need to handle the error? */
+ }
}
+ if (msix_set_vector_notifiers(pdev,
+ ivshmem_vector_unmask,
+ ivshmem_vector_mask,
+ ivshmem_vector_poll)) {
+ error_report("ivshmem: msix_set_vector_notifiers failed");
+ }
}
-static int ivshmem_load(QEMUFile* f, void *opaque, int version_id)
+static void ivshmem_remove_kvm_msi_virq(IVShmemState *s, int vector)
{
- IVSHMEM_DPRINTF("ivshmem_load\n");
-
- IVShmemState *proxy = opaque;
- PCIDevice *pci_dev = PCI_DEVICE(proxy);
- int ret;
+ IVSHMEM_DPRINTF("ivshmem_remove_kvm_msi_virq vector:%d\n", vector);
- if (version_id > 0) {
- return -EINVAL;
+ if (s->msi_vectors[vector].pdev == NULL) {
+ return;
}
- if (proxy->role_val == IVSHMEM_PEER) {
- error_report("'peer' devices are not migratable");
- return -EINVAL;
- }
+ /* it was cleaned when masked in the frontend. */
+ kvm_irqchip_release_virq(kvm_state, s->msi_vectors[vector].virq);
- ret = pci_device_load(pci_dev, f);
- if (ret) {
- return ret;
- }
+ s->msi_vectors[vector].pdev = NULL;
+}
- if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) {
- msix_load(pci_dev, f);
- ivshmem_use_msix(proxy);
- } else {
- proxy->intrstatus = qemu_get_be32(f);
- proxy->intrmask = qemu_get_be32(f);
+static void ivshmem_disable_irqfd(IVShmemState *s)
+{
+ PCIDevice *pdev = PCI_DEVICE(s);
+ int i;
+
+ for (i = 0; i < s->peers[s->vm_id].nb_eventfds; i++) {
+ ivshmem_remove_kvm_msi_virq(s, i);
}
- return 0;
+ msix_unset_vector_notifiers(pdev);
}
-static void ivshmem_write_config(PCIDevice *pci_dev, uint32_t address,
- uint32_t val, int len)
+static void ivshmem_write_config(PCIDevice *pdev, uint32_t address,
+ uint32_t val, int len)
{
- pci_default_write_config(pci_dev, address, val, len);
+ IVShmemState *s = IVSHMEM(pdev);
+ int is_enabled, was_enabled = msix_enabled(pdev);
+
+ pci_default_write_config(pdev, address, val, len);
+ is_enabled = msix_enabled(pdev);
+
+ if (kvm_msi_via_irqfd_enabled()) {
+ if (!was_enabled && is_enabled) {
+ ivshmem_enable_irqfd(s);
+ } else if (was_enabled && !is_enabled) {
+ ivshmem_disable_irqfd(s);
+ }
+ }
}
-static int pci_ivshmem_init(PCIDevice *dev)
+static void pci_ivshmem_realize(PCIDevice *dev, Error **errp)
{
IVShmemState *s = IVSHMEM(dev);
+ Error *err = NULL;
uint8_t *pci_conf;
uint8_t attr = PCI_BASE_ADDRESS_SPACE_MEMORY |
PCI_BASE_ADDRESS_MEM_PREFETCH;
- if (s->sizearg == NULL)
- s->ivshmem_size = 4 << 20; /* 4 MB default */
- else {
- s->ivshmem_size = ivshmem_get_size(s);
+ if (!!s->server_chr + !!s->shmobj + !!s->hostmem != 1) {
+ error_setg(errp,
+ "You must specify either 'shm', 'chardev' or 'x-memdev'");
+ return;
}
- fifo8_create(&s->incoming_fifo, sizeof(long));
+ if (s->hostmem) {
+ MemoryRegion *mr;
- register_savevm(DEVICE(dev), "ivshmem", 0, 0, ivshmem_save, ivshmem_load,
- dev);
+ if (s->sizearg) {
+ g_warning("size argument ignored with hostmem");
+ }
+
+ mr = host_memory_backend_get_memory(s->hostmem, &error_abort);
+ s->ivshmem_size = memory_region_size(mr);
+ } else if (s->sizearg == NULL) {
+ s->ivshmem_size = 4 << 20; /* 4 MB default */
+ } else {
+ char *end;
+ int64_t size = qemu_strtosz(s->sizearg, &end);
+ if (size < 0 || *end != '\0' || !is_power_of_2(size)) {
+ error_setg(errp, "Invalid size %s", s->sizearg);
+ return;
+ }
+ s->ivshmem_size = size;
+ }
/* IRQFD requires MSI */
if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) &&
!ivshmem_has_feature(s, IVSHMEM_MSI)) {
- error_report("ioeventfd/irqfd requires MSI");
- exit(1);
+ error_setg(errp, "ioeventfd/irqfd requires MSI");
+ return;
}
/* check that role is reasonable */
} else if (strncmp(s->role, "master", 7) == 0) {
s->role_val = IVSHMEM_MASTER;
} else {
- error_report("'role' must be 'peer' or 'master'");
- exit(1);
+ error_setg(errp, "'role' must be 'peer' or 'master'");
+ return;
}
} else {
s->role_val = IVSHMEM_MASTER; /* default */
}
- if (s->role_val == IVSHMEM_PEER) {
- error_setg(&s->migration_blocker,
- "Migration is disabled when using feature 'peer mode' in device 'ivshmem'");
- migrate_add_blocker(s->migration_blocker);
- }
-
pci_conf = dev->config;
pci_conf[PCI_COMMAND] = PCI_COMMAND_IO | PCI_COMMAND_MEMORY;
+ /*
+ * Note: we don't use INTx with IVSHMEM_MSI at all, so this is a
+ * bald-faced lie then. But it's a backwards compatible lie.
+ */
pci_config_set_interrupt_pin(pci_conf, 1);
- s->shm_fd = 0;
-
memory_region_init_io(&s->ivshmem_mmio, OBJECT(s), &ivshmem_mmio_ops, s,
"ivshmem-mmio", IVSHMEM_REG_BAR_SIZE);
attr |= PCI_BASE_ADDRESS_MEM_TYPE_64;
}
- if ((s->server_chr != NULL) &&
- (strncmp(s->server_chr->filename, "unix:", 5) == 0)) {
- /* if we get a UNIX socket as the parameter we will talk
- * to the ivshmem server to receive the memory region */
+ if (s->hostmem != NULL) {
+ MemoryRegion *mr;
- if (s->shmobj != NULL) {
- error_report("WARNING: do not specify both 'chardev' "
- "and 'shm' with ivshmem");
+ IVSHMEM_DPRINTF("using hostmem\n");
+
+ mr = host_memory_backend_get_memory(MEMORY_BACKEND(s->hostmem),
+ &error_abort);
+ vmstate_register_ram(mr, DEVICE(s));
+ memory_region_add_subregion(&s->bar, 0, mr);
+ pci_register_bar(PCI_DEVICE(s), 2, attr, &s->bar);
+ } else if (s->server_chr != NULL) {
+ /* FIXME do not rely on what chr drivers put into filename */
+ if (strncmp(s->server_chr->filename, "unix:", 5)) {
+ error_setg(errp, "chardev is not a unix client socket");
+ return;
}
+ /* if we get a UNIX socket as the parameter we will talk
+ * to the ivshmem server to receive the memory region */
+
IVSHMEM_DPRINTF("using shared memory server (socket = %s)\n",
s->server_chr->filename);
- if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
- ivshmem_setup_msi(s);
- }
-
- /* we allocate enough space for 16 guests and grow as needed */
- s->nb_peers = 16;
+ /* we allocate enough space for 16 peers and grow as needed */
+ resize_peers(s, 16);
s->vm_id = -1;
- /* allocate/initialize space for interrupt handling */
- s->peers = g_malloc0(s->nb_peers * sizeof(Peer));
-
pci_register_bar(dev, 2, attr, &s->bar);
- s->eventfd_chr = g_malloc0(s->vectors * sizeof(CharDriverState *));
+ /*
+ * Receive setup messages from server synchronously.
+ * Older versions did it asynchronously, but that creates a
+ * number of entertaining race conditions.
+ */
+ ivshmem_recv_setup(s, &err);
+ if (err) {
+ error_propagate(errp, err);
+ return;
+ }
+
+ qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive,
+ ivshmem_read, NULL, s);
- qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive, ivshmem_read,
- ivshmem_event, s);
+ if (ivshmem_setup_interrupts(s) < 0) {
+ error_setg(errp, "failed to initialize interrupts");
+ return;
+ }
} else {
/* just map the file immediately, we're not using a server */
int fd;
- if (s->shmobj == NULL) {
- error_report("Must specify 'chardev' or 'shm' to ivshmem");
- exit(1);
- }
-
IVSHMEM_DPRINTF("using shm_open (shm object = %s)\n", s->shmobj);
/* try opening with O_EXCL and if it succeeds zero the memory
} else if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR,
S_IRWXU|S_IRWXG|S_IRWXO)) < 0) {
- error_report("could not open shared file");
- exit(1);
-
+ error_setg(errp, "could not open shared file");
+ return;
}
- if (check_shm_size(s, fd) == -1) {
- exit(1);
+ if (check_shm_size(s, fd, errp) == -1) {
+ return;
}
- create_shared_memory_BAR(s, fd, attr);
+ create_shared_memory_BAR(s, fd, attr, &err);
+ if (err) {
+ error_propagate(errp, err);
+ return;
+ }
}
- dev->config_write = ivshmem_write_config;
+ fifo8_create(&s->incoming_fifo, sizeof(int64_t));
- return 0;
+ if (s->role_val == IVSHMEM_PEER) {
+ error_setg(&s->migration_blocker,
+ "Migration is disabled when using feature 'peer mode' in device 'ivshmem'");
+ migrate_add_blocker(s->migration_blocker);
+ }
}
-static void pci_ivshmem_uninit(PCIDevice *dev)
+static void pci_ivshmem_exit(PCIDevice *dev)
{
IVShmemState *s = IVSHMEM(dev);
+ int i;
+
+ fifo8_destroy(&s->incoming_fifo);
if (s->migration_blocker) {
migrate_del_blocker(s->migration_blocker);
error_free(s->migration_blocker);
}
- memory_region_del_subregion(&s->bar, &s->ivshmem);
- vmstate_unregister_ram(&s->ivshmem, DEVICE(dev));
- unregister_savevm(DEVICE(dev), "ivshmem", s);
- fifo8_destroy(&s->incoming_fifo);
+ if (memory_region_is_mapped(&s->ivshmem)) {
+ if (!s->hostmem) {
+ void *addr = memory_region_get_ram_ptr(&s->ivshmem);
+ int fd;
+
+ if (munmap(addr, s->ivshmem_size) == -1) {
+ error_report("Failed to munmap shared memory %s",
+ strerror(errno));
+ }
+
+ fd = qemu_get_ram_fd(memory_region_get_ram_addr(&s->ivshmem));
+ if (fd != -1) {
+ close(fd);
+ }
+ }
+
+ vmstate_unregister_ram(&s->ivshmem, DEVICE(dev));
+ memory_region_del_subregion(&s->bar, &s->ivshmem);
+ }
+
+ if (s->peers) {
+ for (i = 0; i < s->nb_peers; i++) {
+ close_peer_eventfds(s, i);
+ }
+ g_free(s->peers);
+ }
+
+ if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
+ msix_uninit_exclusive_bar(dev);
+ }
+
+ g_free(s->msi_vectors);
+}
+
+static bool test_msix(void *opaque, int version_id)
+{
+ IVShmemState *s = opaque;
+
+ return ivshmem_has_feature(s, IVSHMEM_MSI);
+}
+
+static bool test_no_msix(void *opaque, int version_id)
+{
+ return !test_msix(opaque, version_id);
+}
+
+static int ivshmem_pre_load(void *opaque)
+{
+ IVShmemState *s = opaque;
+
+ if (s->role_val == IVSHMEM_PEER) {
+ error_report("'peer' devices are not migratable");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int ivshmem_post_load(void *opaque, int version_id)
+{
+ IVShmemState *s = opaque;
+
+ if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
+ ivshmem_msix_vector_use(s);
+ }
+ return 0;
+}
+
+static int ivshmem_load_old(QEMUFile *f, void *opaque, int version_id)
+{
+ IVShmemState *s = opaque;
+ PCIDevice *pdev = PCI_DEVICE(s);
+ int ret;
+
+ IVSHMEM_DPRINTF("ivshmem_load_old\n");
+
+ if (version_id != 0) {
+ return -EINVAL;
+ }
+
+ if (s->role_val == IVSHMEM_PEER) {
+ error_report("'peer' devices are not migratable");
+ return -EINVAL;
+ }
+
+ ret = pci_device_load(pdev, f);
+ if (ret) {
+ return ret;
+ }
+
+ if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
+ msix_load(pdev, f);
+ ivshmem_msix_vector_use(s);
+ } else {
+ s->intrstatus = qemu_get_be32(f);
+ s->intrmask = qemu_get_be32(f);
+ }
+
+ return 0;
}
+static const VMStateDescription ivshmem_vmsd = {
+ .name = "ivshmem",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .pre_load = ivshmem_pre_load,
+ .post_load = ivshmem_post_load,
+ .fields = (VMStateField[]) {
+ VMSTATE_PCI_DEVICE(parent_obj, IVShmemState),
+
+ VMSTATE_MSIX_TEST(parent_obj, IVShmemState, test_msix),
+ VMSTATE_UINT32_TEST(intrstatus, IVShmemState, test_no_msix),
+ VMSTATE_UINT32_TEST(intrmask, IVShmemState, test_no_msix),
+
+ VMSTATE_END_OF_LIST()
+ },
+ .load_state_old = ivshmem_load_old,
+ .minimum_version_id_old = 0
+};
+
static Property ivshmem_properties[] = {
DEFINE_PROP_CHR("chardev", IVShmemState, server_chr),
DEFINE_PROP_STRING("size", IVShmemState, sizearg),
DeviceClass *dc = DEVICE_CLASS(klass);
PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
- k->init = pci_ivshmem_init;
- k->exit = pci_ivshmem_uninit;
+ k->realize = pci_ivshmem_realize;
+ k->exit = pci_ivshmem_exit;
+ k->config_write = ivshmem_write_config;
k->vendor_id = PCI_VENDOR_ID_IVSHMEM;
k->device_id = PCI_DEVICE_ID_IVSHMEM;
k->class_id = PCI_CLASS_MEMORY_RAM;
dc->reset = ivshmem_reset;
dc->props = ivshmem_properties;
+ dc->vmsd = &ivshmem_vmsd;
set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+ dc->desc = "Inter-VM shared memory";
+}
+
+static void ivshmem_check_memdev_is_busy(Object *obj, const char *name,
+ Object *val, Error **errp)
+{
+ MemoryRegion *mr;
+
+ mr = host_memory_backend_get_memory(MEMORY_BACKEND(val), &error_abort);
+ if (memory_region_is_mapped(mr)) {
+ char *path = object_get_canonical_path_component(val);
+ error_setg(errp, "can't use already busy memdev: %s", path);
+ g_free(path);
+ } else {
+ qdev_prop_allow_set_link_before_realize(obj, name, val, errp);
+ }
+}
+
+static void ivshmem_init(Object *obj)
+{
+ IVShmemState *s = IVSHMEM(obj);
+
+ object_property_add_link(obj, "x-memdev", TYPE_MEMORY_BACKEND,
+ (Object **)&s->hostmem,
+ ivshmem_check_memdev_is_busy,
+ OBJ_PROP_LINK_UNREF_ON_RELEASE,
+ &error_abort);
}
static const TypeInfo ivshmem_info = {
.name = TYPE_IVSHMEM,
.parent = TYPE_PCI_DEVICE,
.instance_size = sizeof(IVShmemState),
+ .instance_init = ivshmem_init,
.class_init = ivshmem_class_init,
};
projects / mirror_qemu.git / blobdiff