static pteval_t xen_pte_val(pte_t pte)
{
pteval_t pteval = pte.pte;
-
+#if 0
/* If this is a WC pte, convert back from Xen WC to Linux WC */
if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
WARN_ON(!pat_enabled);
pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
}
-
+#endif
if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
return pteval;
static pte_t xen_make_pte(pteval_t pte)
{
phys_addr_t addr = (pte & PTE_PFN_MASK);
-
+#if 0
/* If Linux is trying to set a WC pte, then map to the Xen WC.
* If _PAGE_PAT is set, then it probably means it is really
* _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
}
-
+#endif
/*
* Unprivileged domains are allowed to do IOMAPpings for
* PCI passthrough, but not map ISA space. The ISA
#endif /* CONFIG_X86_64 */
static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
+ static unsigned char fake_ioapic_mapping[PAGE_SIZE] __page_aligned_bss;
static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
{
* We just don't map the IO APIC - all access is via
* hypercalls. Keep the address in the pte for reference.
*/
- pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
+ pte = pfn_pte(PFN_DOWN(__pa(fake_ioapic_mapping)), PAGE_KERNEL);
break;
#endif
pv_mmu_ops = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
+ memset(fake_ioapic_mapping, 0xfd, PAGE_SIZE);
}
/* Protected by xen_reservation_lock. */
static void __cpuinit cpu_bringup(void)
{
- int cpu = smp_processor_id();
+ int cpu;
cpu_init();
touch_softlockup_watchdog();
play_dead_common();
HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
cpu_bringup();
+ /*
+ * Balance out the preempt calls - as we are running in cpu_idle
+ * loop which has been called at bootup from cpu_bringup_and_idle.
+ * The cpucpu_bringup_and_idle called cpu_bringup which made a
+ * preempt_disable() So this preempt_enable will balance it out.
+ */
+ preempt_enable();
}
#else /* !CONFIG_HOTPLUG_CPU */
unsigned long shadow_free;
unsigned int feature_flush;
unsigned int flush_op;
- unsigned int feature_discard;
+ unsigned int feature_discard:1;
+ unsigned int feature_secdiscard:1;
unsigned int discard_granularity;
unsigned int discard_alignment;
int is_ready;
{
unsigned long free = info->shadow_free;
BUG_ON(free >= BLK_RING_SIZE);
- info->shadow_free = info->shadow[free].req.id;
- info->shadow[free].req.id = 0x0fffffee; /* debug */
+ info->shadow_free = info->shadow[free].req.u.rw.id;
+ info->shadow[free].req.u.rw.id = 0x0fffffee; /* debug */
return free;
}
static void add_id_to_freelist(struct blkfront_info *info,
unsigned long id)
{
- info->shadow[id].req.id = info->shadow_free;
+ info->shadow[id].req.u.rw.id = info->shadow_free;
info->shadow[id].request = NULL;
info->shadow_free = id;
}
if (end > nr_minors) {
unsigned long *bitmap, *old;
- bitmap = kzalloc(BITS_TO_LONGS(end) * sizeof(*bitmap),
+ bitmap = kcalloc(BITS_TO_LONGS(end), sizeof(*bitmap),
GFP_KERNEL);
if (bitmap == NULL)
return -ENOMEM;
id = get_id_from_freelist(info);
info->shadow[id].request = req;
- ring_req->id = id;
+ ring_req->u.rw.id = id;
ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
- ring_req->handle = info->handle;
+ ring_req->u.rw.handle = info->handle;
ring_req->operation = rq_data_dir(req) ?
BLKIF_OP_WRITE : BLKIF_OP_READ;
ring_req->operation = info->flush_op;
}
- if (unlikely(req->cmd_flags & REQ_DISCARD)) {
+ if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE))) {
/* id, sector_number and handle are set above. */
ring_req->operation = BLKIF_OP_DISCARD;
- ring_req->nr_segments = 0;
ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
+ if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
+ ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
+ else
+ ring_req->u.discard.flag = 0;
} else {
- ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg);
- BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ ring_req->u.rw.nr_segments = blk_rq_map_sg(req->q, req,
+ info->sg);
+ BUG_ON(ring_req->u.rw.nr_segments >
+ BLKIF_MAX_SEGMENTS_PER_REQUEST);
- for_each_sg(info->sg, sg, ring_req->nr_segments, i) {
+ for_each_sg(info->sg, sg, ring_req->u.rw.nr_segments, i) {
buffer_mfn = pfn_to_mfn(page_to_pfn(sg_page(sg)));
fsect = sg->offset >> 9;
lsect = fsect + (sg->length >> 9) - 1;
blk_queue_max_discard_sectors(rq, get_capacity(gd));
rq->limits.discard_granularity = info->discard_granularity;
rq->limits.discard_alignment = info->discard_alignment;
+ if (info->feature_secdiscard)
+ queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, rq);
}
/* Hard sector size and max sectors impersonate the equiv. hardware. */
static void blkif_completion(struct blk_shadow *s)
{
int i;
- for (i = 0; i < s->req.nr_segments; i++)
+ /* Do not let BLKIF_OP_DISCARD as nr_segment is in the same place
+ * flag. */
+ for (i = 0; i < s->req.u.rw.nr_segments; i++)
gnttab_end_foreign_access(s->req.u.rw.seg[i].gref, 0, 0UL);
}
id = bret->id;
req = info->shadow[id].request;
- blkif_completion(&info->shadow[id]);
+ if (bret->operation != BLKIF_OP_DISCARD)
+ blkif_completion(&info->shadow[id]);
add_id_to_freelist(info, id);
info->gd->disk_name);
error = -EOPNOTSUPP;
info->feature_discard = 0;
+ info->feature_secdiscard = 0;
queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
+ queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
}
__blk_end_request_all(req, error);
break;
error = -EOPNOTSUPP;
}
if (unlikely(bret->status == BLKIF_RSP_ERROR &&
- info->shadow[id].req.nr_segments == 0)) {
+ info->shadow[id].req.u.rw.nr_segments == 0)) {
printk(KERN_WARNING "blkfront: %s: empty write %s op failed\n",
info->flush_op == BLKIF_OP_WRITE_BARRIER ?
"barrier" : "flush disk cache",
INIT_WORK(&info->work, blkif_restart_queue);
for (i = 0; i < BLK_RING_SIZE; i++)
- info->shadow[i].req.id = i+1;
- info->shadow[BLK_RING_SIZE-1].req.id = 0x0fffffff;
+ info->shadow[i].req.u.rw.id = i+1;
+ info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
/* Front end dir is a number, which is used as the id. */
info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0);
/* Stage 2: Set up free list. */
memset(&info->shadow, 0, sizeof(info->shadow));
for (i = 0; i < BLK_RING_SIZE; i++)
- info->shadow[i].req.id = i+1;
+ info->shadow[i].req.u.rw.id = i+1;
info->shadow_free = info->ring.req_prod_pvt;
- info->shadow[BLK_RING_SIZE-1].req.id = 0x0fffffff;
+ info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
/* Stage 3: Find pending requests and requeue them. */
for (i = 0; i < BLK_RING_SIZE; i++) {
*req = copy[i].req;
/* We get a new request id, and must reset the shadow state. */
- req->id = get_id_from_freelist(info);
- memcpy(&info->shadow[req->id], ©[i], sizeof(copy[i]));
+ req->u.rw.id = get_id_from_freelist(info);
+ memcpy(&info->shadow[req->u.rw.id], ©[i], sizeof(copy[i]));
+ if (req->operation != BLKIF_OP_DISCARD) {
/* Rewrite any grant references invalidated by susp/resume. */
- for (j = 0; j < req->nr_segments; j++)
- gnttab_grant_foreign_access_ref(
- req->u.rw.seg[j].gref,
- info->xbdev->otherend_id,
- pfn_to_mfn(info->shadow[req->id].frame[j]),
- rq_data_dir(info->shadow[req->id].request));
- info->shadow[req->id].req = *req;
+ for (j = 0; j < req->u.rw.nr_segments; j++)
+ gnttab_grant_foreign_access_ref(
+ req->u.rw.seg[j].gref,
+ info->xbdev->otherend_id,
+ pfn_to_mfn(info->shadow[req->u.rw.id].frame[j]),
+ rq_data_dir(info->shadow[req->u.rw.id].request));
+ }
+ info->shadow[req->u.rw.id].req = *req;
info->ring.req_prod_pvt++;
}
char *type;
unsigned int discard_granularity;
unsigned int discard_alignment;
+ unsigned int discard_secure;
type = xenbus_read(XBT_NIL, info->xbdev->otherend, "type", NULL);
if (IS_ERR(type))
return;
+ info->feature_secdiscard = 0;
if (strncmp(type, "phy", 3) == 0) {
err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
"discard-granularity", "%u", &discard_granularity,
info->discard_granularity = discard_granularity;
info->discard_alignment = discard_alignment;
}
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "discard-secure", "%d", &discard_secure,
+ NULL);
+ if (!err)
+ info->feature_secdiscard = discard_secure;
+
} else if (strncmp(type, "file", 4) == 0)
info->feature_discard = 1;
if (!xen_domain())
return -ENODEV;
- if (!xen_platform_pci_unplug)
+ if (xen_hvm_domain() && !xen_platform_pci_unplug)
return -ENODEV;
if (register_blkdev(XENVBD_MAJOR, DEV_NAME)) {
#define NET_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
#define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
-#define TX_MAX_TARGET min_t(int, NET_RX_RING_SIZE, 256)
+#define TX_MAX_TARGET min_t(int, NET_TX_RING_SIZE, 256)
struct netfront_stats {
u64 rx_packets;
int frags = skb_shinfo(skb)->nr_frags;
unsigned int offset = offset_in_page(data);
unsigned int len = skb_headlen(skb);
+ unsigned long flags;
frags += DIV_ROUND_UP(offset + len, PAGE_SIZE);
if (unlikely(frags > MAX_SKB_FRAGS + 1)) {
goto drop;
}
- spin_lock_irq(&np->tx_lock);
+ spin_lock_irqsave(&np->tx_lock, flags);
if (unlikely(!netif_carrier_ok(dev) ||
(frags > 1 && !xennet_can_sg(dev)) ||
netif_needs_gso(skb, netif_skb_features(skb)))) {
- spin_unlock_irq(&np->tx_lock);
+ spin_unlock_irqrestore(&np->tx_lock, flags);
goto drop;
}
if (!netfront_tx_slot_available(np))
netif_stop_queue(dev);
- spin_unlock_irq(&np->tx_lock);
+ spin_unlock_irqrestore(&np->tx_lock, flags);
return NETDEV_TX_OK;
return 0;
}
+static irqreturn_t xennet_interrupt(int irq, void *dev_id)
+{
+ struct net_device *dev = dev_id;
+ struct netfront_info *np = netdev_priv(dev);
+ unsigned long flags;
+
+ spin_lock_irqsave(&np->tx_lock, flags);
+
+ if (likely(netif_carrier_ok(dev))) {
+ xennet_tx_buf_gc(dev);
+ /* Under tx_lock: protects access to rx shared-ring indexes. */
+ if (RING_HAS_UNCONSUMED_RESPONSES(&np->rx))
+ napi_schedule(&np->napi);
+ }
+
+ spin_unlock_irqrestore(&np->tx_lock, flags);
+
+ return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void xennet_poll_controller(struct net_device *dev)
+{
+ xennet_interrupt(0, dev);
+}
+#endif
+
static const struct net_device_ops xennet_netdev_ops = {
.ndo_open = xennet_open,
.ndo_uninit = xennet_uninit,
.ndo_validate_addr = eth_validate_addr,
.ndo_fix_features = xennet_fix_features,
.ndo_set_features = xennet_set_features,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = xennet_poll_controller,
+#endif
};
static struct net_device * __devinit xennet_create_dev(struct xenbus_device *dev)
struct netfront_info *np;
netdev = alloc_etherdev(sizeof(struct netfront_info));
- if (!netdev) {
- printk(KERN_WARNING "%s> alloc_etherdev failed.\n",
- __func__);
+ if (!netdev)
return ERR_PTR(-ENOMEM);
- }
np = netdev_priv(netdev);
np->xbdev = dev;
return 0;
}
-static irqreturn_t xennet_interrupt(int irq, void *dev_id)
-{
- struct net_device *dev = dev_id;
- struct netfront_info *np = netdev_priv(dev);
- unsigned long flags;
-
- spin_lock_irqsave(&np->tx_lock, flags);
-
- if (likely(netif_carrier_ok(dev))) {
- xennet_tx_buf_gc(dev);
- /* Under tx_lock: protects access to rx shared-ring indexes. */
- if (RING_HAS_UNCONSUMED_RESPONSES(&np->rx))
- napi_schedule(&np->napi);
- }
-
- spin_unlock_irqrestore(&np->tx_lock, flags);
-
- return IRQ_HANDLED;
-}
-
static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info)
{
struct xen_netif_tx_sring *txs;
if (xen_initial_domain())
return 0;
- if (!xen_platform_pci_unplug)
+ if (xen_hvm_domain() && !xen_platform_pci_unplug)
return -ENODEV;
printk(KERN_INFO "Initialising Xen virtual ethernet driver.\n");
if (verbose_request)
dev_info(&pdev->xdev->dev,
- "read dev=%04x:%02x:%02x.%01x - offset %x size %d\n",
+ "read dev=%04x:%02x:%02x.%d - offset %x size %d\n",
pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
PCI_FUNC(devfn), where, size);
if (verbose_request)
dev_info(&pdev->xdev->dev,
- "write dev=%04x:%02x:%02x.%01x - "
+ "write dev=%04x:%02x:%02x.%d - "
"offset %x size %d val %x\n",
pci_domain_nr(bus), bus->number,
PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
} else {
printk(KERN_DEBUG "enable msix get value %x\n",
op.value);
+ err = op.value;
}
} else {
dev_err(&dev->dev, "enable msix get err %x\n", err);
d = pci_scan_single_device(b, devfn);
if (d)
dev_info(&pdev->xdev->dev, "New device on "
- "%04x:%02x:%02x.%02x found.\n", domain, bus,
+ "%04x:%02x:%02x.%d found.\n", domain, bus,
PCI_SLOT(devfn), PCI_FUNC(devfn));
}
dev = container_of(bus->devices.next, struct pci_dev,
bus_list);
dev_dbg(&dev->dev, "removing device\n");
- pci_remove_bus_device(dev);
+ pci_stop_and_remove_bus_device(dev);
}
}
}
pdrv = pcidev->driver;
- if (get_driver(&pdrv->driver)) {
+ if (pdrv) {
if (pdrv->err_handler && pdrv->err_handler->error_detected) {
dev_dbg(&pcidev->dev,
"trying to call AER service\n");
}
}
}
- put_driver(&pdrv->driver);
}
if (!flag)
result = PCI_ERS_RESULT_NONE;
pci_dev = pci_get_slot(pci_bus, PCI_DEVFN(slot, func));
if (!pci_dev) {
dev_dbg(&pdev->xdev->dev,
- "Cannot get PCI device %04x:%02x:%02x.%02x\n",
+ "Cannot get PCI device %04x:%02x:%02x.%d\n",
domain, bus, slot, func);
continue;
}
- pci_remove_bus_device(pci_dev);
+ pci_stop_and_remove_bus_device(pci_dev);
pci_dev_put(pci_dev);
dev_dbg(&pdev->xdev->dev,
- "PCI device %04x:%02x:%02x.%02x removed.\n",
+ "PCI device %04x:%02x:%02x.%d removed.\n",
domain, bus, slot, func);
}