diff options
Diffstat (limited to 'drivers')
35 files changed, 594 insertions, 256 deletions
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index a0aabd904a51..46b8136c31bb 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -321,7 +321,6 @@ static void pcd_init_units(void) strcpy(disk->disk_name, cd->name); /* umm... */ disk->fops = &pcd_bdops; disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; - disk->events = DISK_EVENT_MEDIA_CHANGE; } } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 6ecf89cdf006..079c08808d8a 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -6,10 +6,13 @@ #include <linux/virtio.h> #include <linux/virtio_blk.h> #include <linux/scatterlist.h> +#include <linux/string_helpers.h> +#include <scsi/scsi_cmnd.h> #define PART_BITS 4 static int major, index; +struct workqueue_struct *virtblk_wq; struct virtio_blk { @@ -26,6 +29,9 @@ struct virtio_blk mempool_t *pool; + /* Process context for config space updates */ + struct work_struct config_work; + /* What host tells us, plus 2 for header & tailer. */ unsigned int sg_elems; @@ -141,7 +147,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk, num = blk_rq_map_sg(q, vbr->req, vblk->sg + out); if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) { - sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96); + sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, SCSI_SENSE_BUFFERSIZE); sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr, sizeof(vbr->in_hdr)); } @@ -291,6 +297,46 @@ static ssize_t virtblk_serial_show(struct device *dev, } DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL); +static void virtblk_config_changed_work(struct work_struct *work) +{ + struct virtio_blk *vblk = + container_of(work, struct virtio_blk, config_work); + struct virtio_device *vdev = vblk->vdev; + struct request_queue *q = vblk->disk->queue; + char cap_str_2[10], cap_str_10[10]; + u64 capacity, size; + + /* Host must always specify the capacity. */ + vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity), + &capacity, sizeof(capacity)); + + /* If capacity is too big, truncate with warning. */ + if ((sector_t)capacity != capacity) { + dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n", + (unsigned long long)capacity); + capacity = (sector_t)-1; + } + + size = capacity * queue_logical_block_size(q); + string_get_size(size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2)); + string_get_size(size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10)); + + dev_notice(&vdev->dev, + "new size: %llu %d-byte logical blocks (%s/%s)\n", + (unsigned long long)capacity, + queue_logical_block_size(q), + cap_str_10, cap_str_2); + + set_capacity(vblk->disk, capacity); +} + +static void virtblk_config_changed(struct virtio_device *vdev) +{ + struct virtio_blk *vblk = vdev->priv; + + queue_work(virtblk_wq, &vblk->config_work); +} + static int __devinit virtblk_probe(struct virtio_device *vdev) { struct virtio_blk *vblk; @@ -327,6 +373,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) vblk->vdev = vdev; vblk->sg_elems = sg_elems; sg_init_table(vblk->sg, vblk->sg_elems); + INIT_WORK(&vblk->config_work, virtblk_config_changed_work); /* We expect one virtqueue, for output. */ vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests"); @@ -477,6 +524,8 @@ static void __devexit virtblk_remove(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; + flush_work(&vblk->config_work); + /* Nothing should be pending. */ BUG_ON(!list_empty(&vblk->reqs)); @@ -508,27 +557,47 @@ static unsigned int features[] = { * Use __refdata to avoid this warning. */ static struct virtio_driver __refdata virtio_blk = { - .feature_table = features, - .feature_table_size = ARRAY_SIZE(features), - .driver.name = KBUILD_MODNAME, - .driver.owner = THIS_MODULE, - .id_table = id_table, - .probe = virtblk_probe, - .remove = __devexit_p(virtblk_remove), + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = id_table, + .probe = virtblk_probe, + .remove = __devexit_p(virtblk_remove), + .config_changed = virtblk_config_changed, }; static int __init init(void) { + int error; + + virtblk_wq = alloc_workqueue("virtio-blk", 0, 0); + if (!virtblk_wq) + return -ENOMEM; + major = register_blkdev(0, "virtblk"); - if (major < 0) - return major; - return register_virtio_driver(&virtio_blk); + if (major < 0) { + error = major; + goto out_destroy_workqueue; + } + + error = register_virtio_driver(&virtio_blk); + if (error) + goto out_unregister_blkdev; + return 0; + +out_unregister_blkdev: + unregister_blkdev(major, "virtblk"); +out_destroy_workqueue: + destroy_workqueue(virtblk_wq); + return error; } static void __exit fini(void) { unregister_blkdev(major, "virtblk"); unregister_virtio_driver(&virtio_blk); + destroy_workqueue(virtblk_wq); } module_init(init); module_exit(fini); diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index b3f01996318f..48ad2a7ab080 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -355,29 +355,24 @@ static void hci_uart_tty_wakeup(struct tty_struct *tty) * flags pointer to flags for data * count count of received data in bytes * - * Return Value: Number of bytes received + * Return Value: None */ -static unsigned int hci_uart_tty_receive(struct tty_struct *tty, - const u8 *data, char *flags, int count) +static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data, char *flags, int count) { struct hci_uart *hu = (void *)tty->disc_data; - int received; if (!hu || tty != hu->tty) - return -ENODEV; + return; if (!test_bit(HCI_UART_PROTO_SET, &hu->flags)) - return -EINVAL; + return; spin_lock(&hu->rx_lock); - received = hu->proto->recv(hu, (void *) data, count); - if (received > 0) - hu->hdev->stat.byte_rx += received; + hu->proto->recv(hu, (void *) data, count); + hu->hdev->stat.byte_rx += count; spin_unlock(&hu->rx_lock); tty_unthrottle(tty); - - return received; } static int hci_uart_register_dev(struct hci_uart *hu) diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c index ae15a4ddaa9b..7878da89d29e 100644 --- a/drivers/cdrom/viocd.c +++ b/drivers/cdrom/viocd.c @@ -627,7 +627,6 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id) gendisk->fops = &viocd_fops; gendisk->flags = GENHD_FL_CD | GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; - gendisk->events = DISK_EVENT_MEDIA_CHANGE; set_capacity(gendisk, 0); gendisk->private_data = d; d->viocd_disk = gendisk; diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 838568a7dbf5..fb68b1295373 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1677,17 +1677,12 @@ static int __devinit virtcons_probe(struct virtio_device *vdev) portdev->config.max_nr_ports = 1; if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) { multiport = true; - vdev->features[0] |= 1 << VIRTIO_CONSOLE_F_MULTIPORT; - vdev->config->get(vdev, offsetof(struct virtio_console_config, max_nr_ports), &portdev->config.max_nr_ports, sizeof(portdev->config.max_nr_ports)); } - /* Let the Host know we support multiple ports.*/ - vdev->config->finalize_features(vdev); - err = init_vqs(portdev); if (err < 0) { dev_err(&vdev->dev, "Error %d initializing vqs\n", err); diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 6e5123b1d341..144d27261e43 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -1782,7 +1782,6 @@ static int ide_cd_probe(ide_drive_t *drive) ide_cd_read_toc(drive, &sense); g->fops = &idecd_ops; g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; - g->events = DISK_EVENT_MEDIA_CHANGE; add_disk(g); return 0; diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c index f3698967edf6..8755f5f3ad37 100644 --- a/drivers/input/serio/serport.c +++ b/drivers/input/serio/serport.c @@ -120,21 +120,17 @@ static void serport_ldisc_close(struct tty_struct *tty) * 'interrupt' routine. */ -static unsigned int serport_ldisc_receive(struct tty_struct *tty, - const unsigned char *cp, char *fp, int count) +static void serport_ldisc_receive(struct tty_struct *tty, const unsigned char *cp, char *fp, int count) { struct serport *serport = (struct serport*) tty->disc_data; unsigned long flags; unsigned int ch_flags; - int ret = 0; int i; spin_lock_irqsave(&serport->lock, flags); - if (!test_bit(SERPORT_ACTIVE, &serport->flags)) { - ret = -EINVAL; + if (!test_bit(SERPORT_ACTIVE, &serport->flags)) goto out; - } for (i = 0; i < count; i++) { switch (fp[i]) { @@ -156,8 +152,6 @@ static unsigned int serport_ldisc_receive(struct tty_struct *tty, out: spin_unlock_irqrestore(&serport->lock, flags); - - return ret == 0 ? count : ret; } /* diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c index 1d44d470897c..86a5c4f7775e 100644 --- a/drivers/isdn/gigaset/ser-gigaset.c +++ b/drivers/isdn/gigaset/ser-gigaset.c @@ -674,7 +674,7 @@ gigaset_tty_ioctl(struct tty_struct *tty, struct file *file, * cflags buffer containing error flags for received characters (ignored) * count number of received characters */ -static unsigned int +static void gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf, char *cflags, int count) { @@ -683,12 +683,12 @@ gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf, struct inbuf_t *inbuf; if (!cs) - return -ENODEV; + return; inbuf = cs->inbuf; if (!inbuf) { dev_err(cs->dev, "%s: no inbuf\n", __func__); cs_put(cs); - return -EINVAL; + return; } tail = inbuf->tail; @@ -725,8 +725,6 @@ gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf, gig_dbg(DEBUG_INTR, "%s-->BH", __func__); gigaset_schedule_event(cs); cs_put(cs); - - return count; } /* diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c index b0c56313dbbb..8cebec5e85ee 100644 --- a/drivers/misc/kgdbts.c +++ b/drivers/misc/kgdbts.c @@ -304,7 +304,10 @@ static int check_and_rewind_pc(char *put_str, char *arg) return 1; } /* Readjust the instruction pointer if needed */ - instruction_pointer_set(&kgdbts_regs, ip + offset); + ip += offset; +#ifdef GDB_ADJUSTS_BREAK_OFFSET + instruction_pointer_set(&kgdbts_regs, ip); +#endif return 0; } diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c index 1a05fe08e2cb..f91f82eabda7 100644 --- a/drivers/misc/ti-st/st_core.c +++ b/drivers/misc/ti-st/st_core.c @@ -747,8 +747,8 @@ static void st_tty_close(struct tty_struct *tty) pr_debug("%s: done ", __func__); } -static unsigned int st_tty_receive(struct tty_struct *tty, - const unsigned char *data, char *tty_flags, int count) +static void st_tty_receive(struct tty_struct *tty, const unsigned char *data, + char *tty_flags, int count) { #ifdef VERBOSE print_hex_dump(KERN_DEBUG, ">in>", DUMP_PREFIX_NONE, @@ -761,8 +761,6 @@ static unsigned int st_tty_receive(struct tty_struct *tty, */ st_recv(tty->disc_data, data, count); pr_debug("done %s", __func__); - - return count; } /* wake-up function called in from the TTY layer diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index 73c7e03617ec..3df0c0f8b8bf 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -167,8 +167,8 @@ static inline void debugfs_tx(struct ser_device *ser, const u8 *data, int size) #endif -static unsigned int ldisc_receive(struct tty_struct *tty, - const u8 *data, char *flags, int count) +static void ldisc_receive(struct tty_struct *tty, const u8 *data, + char *flags, int count) { struct sk_buff *skb = NULL; struct ser_device *ser; @@ -215,8 +215,6 @@ static unsigned int ldisc_receive(struct tty_struct *tty, } else ++ser->dev->stats.rx_dropped; update_tty_status(ser); - - return count; } static int handle_tx(struct ser_device *ser) diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 75622d54581f..1b49df6b2470 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -425,17 +425,16 @@ static void slc_setup(struct net_device *dev) * in parallel */ -static unsigned int slcan_receive_buf(struct tty_struct *tty, +static void slcan_receive_buf(struct tty_struct *tty, const unsigned char *cp, char *fp, int count) { struct slcan *sl = (struct slcan *) tty->disc_data; - int bytes = count; if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev)) - return -ENODEV; + return; /* Read the characters out of the buffer */ - while (bytes--) { + while (count--) { if (fp && *fp++) { if (!test_and_set_bit(SLF_ERROR, &sl->flags)) sl->dev->stats.rx_errors++; @@ -444,8 +443,6 @@ static unsigned int slcan_receive_buf(struct tty_struct *tty, } slcan_unesc(sl, *cp++); } - - return count; } /************************************ diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 992089639ea4..3e5d0b6b6516 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -456,7 +456,7 @@ out: * a block of 6pack data has been received, which can now be decapsulated * and sent on to some IP layer for further processing. */ -static unsigned int sixpack_receive_buf(struct tty_struct *tty, +static void sixpack_receive_buf(struct tty_struct *tty, const unsigned char *cp, char *fp, int count) { struct sixpack *sp; @@ -464,11 +464,11 @@ static unsigned int sixpack_receive_buf(struct tty_struct *tty, int count1; if (!count) - return 0; + return; sp = sp_get(tty); if (!sp) - return -ENODEV; + return; memcpy(buf, cp, count < sizeof(buf) ? count : sizeof(buf)); @@ -487,8 +487,6 @@ static unsigned int sixpack_receive_buf(struct tty_struct *tty, sp_put(sp); tty_unthrottle(tty); - - return count1; } /* diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 0e4f23531140..4c628393c8b1 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -923,14 +923,13 @@ static long mkiss_compat_ioctl(struct tty_struct *tty, struct file *file, * a block of data has been received, which can now be decapsulated * and sent on to the AX.25 layer for further processing. */ -static unsigned int mkiss_receive_buf(struct tty_struct *tty, - const unsigned char *cp, char *fp, int count) +static void mkiss_receive_buf(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count) { struct mkiss *ax = mkiss_get(tty); - int bytes = count; if (!ax) - return -ENODEV; + return; /* * Argh! mtu change time! - costs us the packet part received @@ -940,7 +939,7 @@ static unsigned int mkiss_receive_buf(struct tty_struct *tty, ax_changedmtu(ax); /* Read the characters out of the buffer */ - while (bytes--) { + while (count--) { if (fp != NULL && *fp++) { if (!test_and_set_bit(AXF_ERROR, &ax->flags)) ax->dev->stats.rx_errors++; @@ -953,8 +952,6 @@ static unsigned int mkiss_receive_buf(struct tty_struct *tty, mkiss_put(ax); tty_unthrottle(tty); - - return count; } /* diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c index 035861d8acb1..3352b2443e58 100644 --- a/drivers/net/irda/irtty-sir.c +++ b/drivers/net/irda/irtty-sir.c @@ -216,23 +216,23 @@ static int irtty_do_write(struct sir_dev *dev, const unsigned char *ptr, size_t * usbserial: urb-complete-interrupt / softint */ -static unsigned int irtty_receive_buf(struct tty_struct *tty, - const unsigned char *cp, char *fp, int count) +static void irtty_receive_buf(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count) { struct sir_dev *dev; struct sirtty_cb *priv = tty->disc_data; int i; - IRDA_ASSERT(priv != NULL, return -ENODEV;); - IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return -EINVAL;); + IRDA_ASSERT(priv != NULL, return;); + IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return;); if (unlikely(count==0)) /* yes, this happens */ - return 0; + return; dev = priv->dev; if (!dev) { IRDA_WARNING("%s(), not ready yet!\n", __func__); - return -ENODEV; + return; } for (i = 0; i < count; i++) { @@ -242,13 +242,11 @@ static unsigned int irtty_receive_buf(struct tty_struct *tty, if (fp && *fp++) { IRDA_DEBUG(0, "Framing or parity error!\n"); sirdev_receive(dev, NULL, 0); /* notify sir_dev (updating stats) */ - return -EINVAL; + return; } } sirdev_receive(dev, cp, count); - - return count; } /* diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c index 53872d7d7382..a1b82c9c67d2 100644 --- a/drivers/net/ppp_async.c +++ b/drivers/net/ppp_async.c @@ -340,7 +340,7 @@ ppp_asynctty_poll(struct tty_struct *tty, struct file *file, poll_table *wait) } /* May sleep, don't call from interrupt level or with interrupts disabled */ -static unsigned int +static void ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf, char *cflags, int count) { @@ -348,7 +348,7 @@ ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf, unsigned long flags; if (!ap) - return -ENODEV; + return; spin_lock_irqsave(&ap->recv_lock, flags); ppp_async_input(ap, buf, cflags, count); spin_unlock_irqrestore(&ap->recv_lock, flags); @@ -356,8 +356,6 @@ ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf, tasklet_schedule(&ap->tsk); ap_put(ap); tty_unthrottle(tty); - - return count; } static void diff --git a/drivers/net/ppp_synctty.c b/drivers/net/ppp_synctty.c index 0815790a5cf9..2573f525f11c 100644 --- a/drivers/net/ppp_synctty.c +++ b/drivers/net/ppp_synctty.c @@ -381,7 +381,7 @@ ppp_sync_poll(struct tty_struct *tty, struct file *file, poll_table *wait) } /* May sleep, don't call from interrupt level or with interrupts disabled */ -static unsigned int +static void ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf, char *cflags, int count) { @@ -389,7 +389,7 @@ ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf, unsigned long flags; if (!ap) - return -ENODEV; + return; spin_lock_irqsave(&ap->recv_lock, flags); ppp_sync_input(ap, buf, cflags, count); spin_unlock_irqrestore(&ap->recv_lock, flags); @@ -397,8 +397,6 @@ ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf, tasklet_schedule(&ap->tsk); sp_put(ap); tty_unthrottle(tty); - - return count; } static void diff --git a/drivers/net/slip.c b/drivers/net/slip.c index 584809c656d5..8ec1a9a0bb9a 100644 --- a/drivers/net/slip.c +++ b/drivers/net/slip.c @@ -670,17 +670,16 @@ static void sl_setup(struct net_device *dev) * in parallel */ -static unsigned int slip_receive_buf(struct tty_struct *tty, - const unsigned char *cp, char *fp, int count) +static void slip_receive_buf(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count) { struct slip *sl = tty->disc_data; - int bytes = count; if (!sl || sl->magic != SLIP_MAGIC || !netif_running(sl->dev)) - return -ENODEV; + return; /* Read the characters out of the buffer */ - while (bytes--) { + while (count--) { if (fp && *fp++) { if (!test_and_set_bit(SLF_ERROR, &sl->flags)) sl->dev->stats.rx_errors++; @@ -694,8 +693,6 @@ static unsigned int slip_receive_buf(struct tty_struct *tty, #endif slip_unesc(sl, *cp++); } - - return count; } /************************************ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0cb0b0632672..f6853247a620 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -609,7 +609,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) * before it gets out of hand. Naturally, this wastes entries. */ if (capacity < 2+MAX_SKB_FRAGS) { netif_stop_queue(dev); - if (unlikely(!virtqueue_enable_cb(vi->svq))) { + if (unlikely(!virtqueue_enable_cb_delayed(vi->svq))) { /* More just got used, free them then recheck. */ capacity += free_old_xmit_skbs(vi); if (capacity >= 2+MAX_SKB_FRAGS) { diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index 40398bf7d036..24297b274cd4 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -517,18 +517,17 @@ static int x25_asy_close(struct net_device *dev) * and sent on to some IP layer for further processing. */ -static unsigned int x25_asy_receive_buf(struct tty_struct *tty, +static void x25_asy_receive_buf(struct tty_struct *tty, const unsigned char *cp, char *fp, int count) { struct x25_asy *sl = tty->disc_data; - int bytes = count; if (!sl || sl->magic != X25_ASY_MAGIC || !netif_running(sl->dev)) return; /* Read the characters out of the buffer */ - while (bytes--) { + while (count--) { if (fp && *fp++) { if (!test_and_set_bit(SLF_ERROR, &sl->flags)) sl->dev->stats.rx_errors++; @@ -537,8 +536,6 @@ static unsigned int x25_asy_receive_buf(struct tty_struct *tty, } x25_asy_unesc(sl, *cp++); } - - return count; } /* diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c index 12e02bf92c4a..3dc9befa5aec 100644 --- a/drivers/pci/dmar.c +++ b/drivers/pci/dmar.c @@ -698,12 +698,7 @@ int __init detect_intel_iommu(void) { #ifdef CONFIG_INTR_REMAP struct acpi_table_dmar *dmar; - /* - * for now we will disable dma-remapping when interrupt - * remapping is enabled. - * When support for queued invalidation for IOTLB invalidation - * is added, we will not need this any more. - */ + dmar = (struct acpi_table_dmar *) dmar_tbl; if (ret && cpu_has_x2apic && dmar->flags & 0x1) printk(KERN_INFO diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 6af6b628175b..59f17acf7f68 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -47,6 +47,8 @@ #define ROOT_SIZE VTD_PAGE_SIZE #define CONTEXT_SIZE VTD_PAGE_SIZE +#define IS_BRIDGE_HOST_DEVICE(pdev) \ + ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST) #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY) #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e) @@ -116,6 +118,11 @@ static inline unsigned long align_to_level(unsigned long pfn, int level) return (pfn + level_size(level) - 1) & level_mask(level); } +static inline unsigned long lvl_to_nr_pages(unsigned int lvl) +{ + return 1 << ((lvl - 1) * LEVEL_STRIDE); +} + /* VT-d pages must always be _smaller_ than MM pages. Otherwise things are never going to work. */ static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn) @@ -143,6 +150,12 @@ static void __init check_tylersburg_isoch(void); static int rwbf_quirk; /* + * set to 1 to panic kernel if can't successfully enable VT-d + * (used when kernel is launched w/ TXT) + */ +static int force_on = 0; + +/* * 0: Present * 1-11: Reserved * 12-63: Context Ptr (12 - (haw-1)) @@ -338,6 +351,9 @@ struct dmar_domain { int iommu_coherency;/* indicate coherency of iommu access */ int iommu_snooping; /* indicate snooping control feature*/ int iommu_count; /* reference count of iommu */ + int iommu_superpage;/* Level of superpages supported: + 0 == 4KiB (no superpages), 1 == 2MiB, + 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ spinlock_t iommu_lock; /* protect iommu set in domain */ u64 max_addr; /* maximum mapped address */ }; @@ -387,6 +403,7 @@ int dmar_disabled = 1; static int dmar_map_gfx = 1; static int dmar_forcedac; static int intel_iommu_strict; +static int intel_iommu_superpage = 1; #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1)) static DEFINE_SPINLOCK(device_domain_lock); @@ -417,6 +434,10 @@ static int __init intel_iommu_setup(char *str) printk(KERN_INFO "Intel-IOMMU: disable batched IOTLB flush\n"); intel_iommu_strict = 1; + } else if (!strncmp(str, "sp_off", 6)) { + printk(KERN_INFO + "Intel-IOMMU: disable supported super page\n"); + intel_iommu_superpage = 0; } str += strcspn(str, ","); @@ -555,11 +576,32 @@ static void domain_update_iommu_snooping(struct dmar_domain *domain) } } +static void domain_update_iommu_superpage(struct dmar_domain *domain) +{ + int i, mask = 0xf; + + if (!intel_iommu_superpage) { + domain->iommu_superpage = 0; + return; + } + + domain->iommu_superpage = 4; /* 1TiB */ + + for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) { + mask |= cap_super_page_val(g_iommus[i]->cap); + if (!mask) { + break; + } + } + domain->iommu_superpage = fls(mask); +} + /* Some capabilities may be different across iommus */ static void domain_update_iommu_cap(struct dmar_domain *domain) { domain_update_iommu_coherency(domain); domain_update_iommu_snooping(domain); + domain_update_iommu_superpage(domain); } static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn) @@ -689,23 +731,31 @@ out: } static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, - unsigned long pfn) + unsigned long pfn, int large_level) { int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; struct dma_pte *parent, *pte = NULL; int level = agaw_to_level(domain->agaw); - int offset; + int offset, target_level; BUG_ON(!domain->pgd); BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width); parent = domain->pgd; + /* Search pte */ + if (!large_level) + target_level = 1; + else + target_level = large_level; + while (level > 0) { void *tmp_page; offset = pfn_level_offset(pfn, level); pte = &parent[offset]; - if (level == 1) + if (!large_level && (pte->val & DMA_PTE_LARGE_PAGE)) + break; + if (level == target_level) break; if (!dma_pte_present(pte)) { @@ -733,10 +783,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, return pte; } + /* return address's pte at specific level */ static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain, unsigned long pfn, - int level) + int level, int *large_page) { struct dma_pte *parent, *pte = NULL; int total = agaw_to_level(domain->agaw); @@ -749,8 +800,16 @@ static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain, if (level == total) return pte; - if (!dma_pte_present(pte)) + if (!dma_pte_present(pte)) { + *large_page = total; break; + } + + if (pte->val & DMA_PTE_LARGE_PAGE) { + *large_page = total; + return pte; + } + parent = phys_to_virt(dma_pte_addr(pte)); total--; } @@ -763,6 +822,7 @@ static void dma_pte_clear_range(struct dmar_domain *domain, unsigned long last_pfn) { int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; + unsigned int large_page = 1; struct dma_pte *first_pte, *pte; BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width); @@ -771,14 +831,15 @@ static void dma_pte_clear_range(struct dmar_domain *domain, /* we don't need lock here; nobody else touches the iova range */ do { - first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1); + large_page = 1; + first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1, &large_page); if (!pte) { - start_pfn = align_to_level(start_pfn + 1, 2); + start_pfn = align_to_level(start_pfn + 1, large_page + 1); continue; } - do { + do { dma_clear_pte(pte); - start_pfn++; + start_pfn += lvl_to_nr_pages(large_page); pte++; } while (start_pfn <= last_pfn && !first_pte_in_page(pte)); @@ -798,6 +859,7 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain, int total = agaw_to_level(domain->agaw); int level; unsigned long tmp; + int large_page = 2; BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width); BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width); @@ -813,7 +875,10 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain, return; do { - first_pte = pte = dma_pfn_level_pte(domain, tmp, level); + large_page = level; + first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page); + if (large_page > level) + level = large_page + 1; if (!pte) { tmp = align_to_level(tmp + 1, level + 1); continue; @@ -1397,6 +1462,7 @@ static int domain_init(struct dmar_domain *domain, int guest_width) else domain->iommu_snooping = 0; + domain->iommu_superpage = fls(cap_super_page_val(iommu->cap)); domain->iommu_count = 1; domain->nid = iommu->node; @@ -1417,6 +1483,10 @@ static void domain_exit(struct dmar_domain *domain) if (!domain) return; + /* Flush any lazy unmaps that may reference this domain */ + if (!intel_iommu_strict) + flush_unmaps_timeout(0); + domain_remove_dev_info(domain); /* destroy iovas */ put_iova_domain(&domain->iovad); @@ -1648,6 +1718,34 @@ static inline unsigned long aligned_nrpages(unsigned long host_addr, return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; } +/* Return largest possible superpage level for a given mapping */ +static inline int hardware_largepage_caps(struct dmar_domain *domain, + unsigned long iov_pfn, + unsigned long phy_pfn, + unsigned long pages) +{ + int support, level = 1; + unsigned long pfnmerge; + + support = domain->iommu_superpage; + + /* To use a large page, the virtual *and* physical addresses + must be aligned to 2MiB/1GiB/etc. Lower bits set in either + of them will mean we have to use smaller pages. So just + merge them and check both at once. */ + pfnmerge = iov_pfn | phy_pfn; + + while (support && !(pfnmerge & ~VTD_STRIDE_MASK)) { + pages >>= VTD_STRIDE_SHIFT; + if (!pages) + break; + pfnmerge >>= VTD_STRIDE_SHIFT; + level++; + support--; + } + return level; +} + static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, struct scatterlist *sg, unsigned long phys_pfn, unsigned long nr_pages, int prot) @@ -1656,6 +1754,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, phys_addr_t uninitialized_var(pteval); int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; unsigned long sg_res; + unsigned int largepage_lvl = 0; + unsigned long lvl_pages = 0; BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width); @@ -1671,7 +1771,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot; } - while (nr_pages--) { + while (nr_pages > 0) { uint64_t tmp; if (!sg_res) { @@ -1679,11 +1779,21 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset; sg->dma_length = sg->length; pteval = page_to_phys(sg_page(sg)) | prot; + phys_pfn = pteval >> VTD_PAGE_SHIFT; } + if (!pte) { - first_pte = pte = pfn_to_dma_pte(domain, iov_pfn); + largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res); + + first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, largepage_lvl); if (!pte) return -ENOMEM; + /* It is large page*/ + if (largepage_lvl > 1) + pteval |= DMA_PTE_LARGE_PAGE; + else + pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE; + } /* We don't need lock here, nobody else * touches the iova range @@ -1699,16 +1809,38 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, } WARN_ON(1); } + + lvl_pages = lvl_to_nr_pages(largepage_lvl); + + BUG_ON(nr_pages < lvl_pages); + BUG_ON(sg_res < lvl_pages); + + nr_pages -= lvl_pages; + iov_pfn += lvl_pages; + phys_pfn += lvl_pages; + pteval += lvl_pages * VTD_PAGE_SIZE; + sg_res -= lvl_pages; + + /* If the next PTE would be the first in a new page, then we + need to flush the cache on the entries we've just written. + And then we'll need to recalculate 'pte', so clear it and + let it get set again in the if (!pte) block above. + + If we're done (!nr_pages) we need to flush the cache too. + + Also if we've been setting superpages, we may need to + recalculate 'pte' and switch back to smaller pages for the + end of the mapping, if the trailing size is not enough to + use another superpage (i.e. sg_res < lvl_pages). */ pte++; - if (!nr_pages || first_pte_in_page(pte)) { + if (!nr_pages || first_pte_in_page(pte) || + (largepage_lvl > 1 && sg_res < lvl_pages)) { domain_flush_cache(domain, first_pte, (void *)pte - (void *)first_pte); pte = NULL; } - iov_pfn++; - pteval += VTD_PAGE_SIZE; - sg_res--; - if (!sg_res) + + if (!sg_res && nr_pages) sg = sg_next(sg); } return 0; @@ -2016,7 +2148,7 @@ static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr, if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO) return 0; return iommu_prepare_identity_map(pdev, rmrr->base_address, - rmrr->end_address + 1); + rmrr->end_address); } #ifdef CONFIG_DMAR_FLOPPY_WA @@ -2030,7 +2162,7 @@ static inline void iommu_prepare_isa(void) return; printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n"); - ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024); + ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024 - 1); if (ret) printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; " @@ -2106,10 +2238,10 @@ static int identity_mapping(struct pci_dev *pdev) if (likely(!iommu_identity_mapping)) return 0; + info = pdev->dev.archdata.iommu; + if (info && info != DUMMY_DEVICE_DOMAIN_INFO) + return (info->domain == si_domain); - list_for_each_entry(info, &si_domain->devices, link) - if (info->dev == pdev) - return 1; return 0; } @@ -2187,8 +2319,19 @@ static int iommu_should_identity_map(struct pci_dev *pdev, int startup) * Assume that they will -- if they turn out not to be, then we can * take them out of the 1:1 domain later. */ - if (!startup) - return pdev->dma_mask > DMA_BIT_MASK(32); + if (!startup) { + /* + * If the device's dma_mask is less than the system's memory + * size then this is not a candidate for identity mapping. + */ + u64 dma_mask = pdev->dma_mask; + + if (pdev->dev.coherent_dma_mask && + pdev->dev.coherent_dma_mask < dma_mask) + dma_mask = pdev->dev.coherent_dma_mask; + + return dma_mask >= dma_get_required_mask(&pdev->dev); + } return 1; } @@ -2203,6 +2346,9 @@ static int __init iommu_prepare_static_identity_mapping(int hw) return -EFAULT; for_each_pci_dev(pdev) { + /* Skip Host/PCI Bridge devices */ + if (IS_BRIDGE_HOST_DEVICE(pdev)) + continue; if (iommu_should_identity_map(pdev, 1)) { printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n", hw ? "hardware" : "software", pci_name(pdev)); @@ -2218,7 +2364,7 @@ static int __init iommu_prepare_static_identity_mapping(int hw) return 0; } -static int __init init_dmars(int force_on) +static int __init init_dmars(void) { struct dmar_drhd_unit *drhd; struct dmar_rmrr_unit *rmrr; @@ -2592,8 +2738,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, iommu = domain_get_iommu(domain); size = aligned_nrpages(paddr, size); - iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), - pdev->dma_mask); + iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), dma_mask); if (!iova) goto error; @@ -3118,7 +3263,17 @@ static int init_iommu_hw(void) if (iommu->qi) dmar_reenable_qi(iommu); - for_each_active_iommu(iommu, drhd) { + for_each_iommu(iommu, drhd) { + if (drhd->ignored) { + /* + * we always have to disable PMRs or DMA may fail on + * this device + */ + if (force_on) + iommu_disable_protect_mem_regions(iommu); + continue; + } + iommu_flush_write_buffer(iommu); iommu_set_root_entry(iommu); @@ -3127,7 +3282,8 @@ static int init_iommu_hw(void) DMA_CCMD_GLOBAL_INVL); iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); - iommu_enable_translation(iommu); + if (iommu_enable_translation(iommu)) + return 1; iommu_disable_protect_mem_regions(iommu); } @@ -3194,7 +3350,10 @@ static void iommu_resume(void) unsigned long flag; if (init_iommu_hw()) { - WARN(1, "IOMMU setup failed, DMAR can not resume!\n"); + if (force_on) + panic("tboot: IOMMU setup failed, DMAR can not resume!\n"); + else + WARN(1, "IOMMU setup failed, DMAR can not resume!\n"); return; } @@ -3271,7 +3430,6 @@ static struct notifier_block device_nb = { int __init intel_iommu_init(void) { int ret = 0; - int force_on = 0; /* VT-d is required for a TXT/tboot launch, so enforce that */ force_on = tboot_force_iommu(); @@ -3309,7 +3467,7 @@ int __init intel_iommu_init(void) init_no_remapping_devices(); - ret = init_dmars(force_on); + ret = init_dmars(); if (ret) { if (force_on) panic("tboot: Failed to initialize DMARs\n"); @@ -3380,8 +3538,8 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain, spin_lock_irqsave(&device_domain_lock, flags); list_for_each_safe(entry, tmp, &domain->devices) { info = list_entry(entry, struct device_domain_info, link); - /* No need to compare PCI domain; it has to be the same */ - if (info->bus == pdev->bus->number && + if (info->segment == pci_domain_nr(pdev->bus) && + info->bus == pdev->bus->number && info->devfn == pdev->devfn) { list_del(&info->link); list_del(&info->global); @@ -3419,10 +3577,13 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain, domain_update_iommu_cap(domain); spin_unlock_irqrestore(&domain->iommu_lock, tmp_flags); - spin_lock_irqsave(&iommu->lock, tmp_flags); - clear_bit(domain->id, iommu->domain_ids); - iommu->domains[domain->id] = NULL; - spin_unlock_irqrestore(&iommu->lock, tmp_flags); + if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) && + !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)) { + spin_lock_irqsave(&iommu->lock, tmp_flags); + clear_bit(domain->id, iommu->domain_ids); + iommu->domains[domain->id] = NULL; + spin_unlock_irqrestore(&iommu->lock, tmp_flags); + } } spin_unlock_irqrestore(&device_domain_lock, flags); @@ -3505,6 +3666,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) domain->iommu_count = 0; domain->iommu_coherency = 0; domain->iommu_snooping = 0; + domain->iommu_superpage = 0; domain->max_addr = 0; domain->nid = -1; @@ -3720,7 +3882,7 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, struct dma_pte *pte; u64 phys = 0; - pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT); + pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, 0); if (pte) phys = dma_pte_addr(pte); diff --git a/drivers/pci/iova.c b/drivers/pci/iova.c index 9606e599a475..c5c274ab5c5a 100644 --- a/drivers/pci/iova.c +++ b/drivers/pci/iova.c @@ -63,8 +63,16 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) curr = iovad->cached32_node; cached_iova = container_of(curr, struct iova, node); - if (free->pfn_lo >= cached_iova->pfn_lo) - iovad->cached32_node = rb_next(&free->node); + if (free->pfn_lo >= cached_iova->pfn_lo) { + struct rb_node *node = rb_next(&free->node); + struct iova *iova = container_of(node, struct iova, node); + + /* only cache if it's below 32bit pfn */ + if (node && iova->pfn_lo < iovad->dma_32bit_pfn) + iovad->cached32_node = node; + else + iovad->cached32_node = NULL; + } } /* Computes the padding size required, to make the diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index a4c42a75a3bf..09e8c7d53af3 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2128,8 +2128,8 @@ static void gsmld_detach_gsm(struct tty_struct *tty, struct gsm_mux *gsm) gsm->tty = NULL; } -static unsigned int gsmld_receive_buf(struct tty_struct *tty, - const unsigned char *cp, char *fp, int count) +static void gsmld_receive_buf(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count) { struct gsm_mux *gsm = tty->disc_data; const unsigned char *dp; @@ -2162,8 +2162,6 @@ static unsigned int gsmld_receive_buf(struct tty_struct *tty, } /* FASYNC if needed ? */ /* If clogged call tty_throttle(tty); */ - - return count; } /** diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index cac666314aef..cea56033b34c 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -188,8 +188,8 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp, poll_table *wait); static int n_hdlc_tty_open(struct tty_struct *tty); static void n_hdlc_tty_close(struct tty_struct *tty); -static unsigned int n_hdlc_tty_receive(struct tty_struct *tty, - const __u8 *cp, char *fp, int count); +static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *cp, + char *fp, int count); static void n_hdlc_tty_wakeup(struct tty_struct *tty); #define bset(p,b) ((p)[(b) >> 5] |= (1 << ((b) & 0x1f))) @@ -509,8 +509,8 @@ static void n_hdlc_tty_wakeup(struct tty_struct *tty) * Called by tty low level driver when receive data is available. Data is * interpreted as one HDLC frame. */ -static unsigned int n_hdlc_tty_receive(struct tty_struct *tty, - const __u8 *data, char *flags, int count) +static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *data, + char *flags, int count) { register struct n_hdlc *n_hdlc = tty2n_hdlc (tty); register struct n_hdlc_buf *buf; @@ -521,20 +521,20 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty, /* This can happen if stuff comes in on the backup tty */ if (!n_hdlc || tty != n_hdlc->tty) - return -ENODEV; + return; /* verify line is using HDLC discipline */ if (n_hdlc->magic != HDLC_MAGIC) { printk("%s(%d) line not using HDLC discipline\n", __FILE__,__LINE__); - return -EINVAL; + return; } if ( count>maxframe ) { if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d) rx count>maxframesize, data discarded\n", __FILE__,__LINE__); - return -EINVAL; + return; } /* get a free HDLC buffer */ @@ -550,7 +550,7 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty, if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d) no more rx buffers, data discarded\n", __FILE__,__LINE__); - return -EINVAL; + return; } /* copy received data to HDLC buffer */ @@ -565,8 +565,6 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty, if (n_hdlc->tty->fasync != NULL) kill_fasync (&n_hdlc->tty->fasync, SIGIO, POLL_IN); - return count; - } /* end of n_hdlc_tty_receive() */ /** diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c index a4bc39c21a43..5c6c31459a2f 100644 --- a/drivers/tty/n_r3964.c +++ b/drivers/tty/n_r3964.c @@ -139,8 +139,8 @@ static int r3964_ioctl(struct tty_struct *tty, struct file *file, static void r3964_set_termios(struct tty_struct *tty, struct ktermios *old); static unsigned int r3964_poll(struct tty_struct *tty, struct file *file, struct poll_table_struct *wait); -static unsigned int r3964_receive_buf(struct tty_struct *tty, - const unsigned char *cp, char *fp, int count); +static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count); static struct tty_ldisc_ops tty_ldisc_N_R3964 = { .owner = THIS_MODULE, @@ -1239,8 +1239,8 @@ static unsigned int r3964_poll(struct tty_struct *tty, struct file *file, return result; } -static unsigned int r3964_receive_buf(struct tty_struct *tty, - const unsigned char *cp, char *fp, int count) +static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count) { struct r3964_info *pInfo = tty->disc_data; const unsigned char *p; @@ -1257,8 +1257,6 @@ static unsigned int r3964_receive_buf(struct tty_struct *tty, } } - - return count; } MODULE_LICENSE("GPL"); diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 95d0a9c2dd13..0ad32888091c 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -81,6 +81,38 @@ static inline int tty_put_user(struct tty_struct *tty, unsigned char x, return put_user(x, ptr); } +/** + * n_tty_set__room - receive space + * @tty: terminal + * + * Called by the driver to find out how much data it is + * permitted to feed to the line discipline without any being lost + * and thus to manage flow control. Not serialized. Answers for the + * "instant". + */ + +static void n_tty_set_room(struct tty_struct *tty) +{ + /* tty->read_cnt is not read locked ? */ + int left = N_TTY_BUF_SIZE - tty->read_cnt - 1; + int old_left; + + /* + * If we are doing input canonicalization, and there are no + * pending newlines, let characters through without limit, so + * that erase characters will be handled. Other excess + * characters will be beeped. + */ + if (left <= 0) + left = tty->icanon && !tty->canon_data; + old_left = tty->receive_room; + tty->receive_room = left; + + /* Did this open up the receive buffer? We may need to flip */ + if (left && !old_left) + schedule_work(&tty->buf.work); +} + static void put_tty_queue_nolock(unsigned char c, struct tty_struct *tty) { if (tty->read_cnt < N_TTY_BUF_SIZE) { @@ -152,6 +184,7 @@ static void reset_buffer_flags(struct tty_struct *tty) tty->canon_head = tty->canon_data = tty->erasing = 0; memset(&tty->read_flags, 0, sizeof tty->read_flags); + n_tty_set_room(tty); check_unthrottle(tty); } @@ -1327,19 +1360,17 @@ static void n_tty_write_wakeup(struct tty_struct *tty) * calls one at a time and in order (or using flush_to_ldisc) */ -static unsigned int n_tty_receive_buf(struct tty_struct *tty, - const unsigned char *cp, char *fp, int count) +static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count) { const unsigned char *p; char *f, flags = TTY_NORMAL; int i; char buf[64]; unsigned long cpuflags; - int left; - int ret = 0; if (!tty->read_buf) - return 0; + return; if (tty->real_raw) { spin_lock_irqsave(&tty->read_lock, cpuflags); @@ -1349,7 +1380,6 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty, memcpy(tty->read_buf + tty->read_head, cp, i); tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1); tty->read_cnt += i; - ret += i; cp += i; count -= i; @@ -1359,10 +1389,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty, memcpy(tty->read_buf + tty->read_head, cp, i); tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1); tty->read_cnt += i; - ret += i; spin_unlock_irqrestore(&tty->read_lock, cpuflags); } else { - ret = count; for (i = count, p = cp, f = fp; i; i--, p++) { if (f) flags = *f++; @@ -1390,6 +1418,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty, tty->ops->flush_chars(tty); } + n_tty_set_room(tty); + if ((!tty->icanon && (tty->read_cnt >= tty->minimum_to_wake)) || L_EXTPROC(tty)) { kill_fasync(&tty->fasync, SIGIO, POLL_IN); @@ -1402,12 +1432,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty, * mode. We don't want to throttle the driver if we're in * canonical mode and don't have a newline yet! */ - left = N_TTY_BUF_SIZE - tty->read_cnt - 1; - - if (left < TTY_THRESHOLD_THROTTLE) + if (tty->receive_room < TTY_THRESHOLD_THROTTLE) tty_throttle(tty); - - return ret; } int is_ignored(int sig) @@ -1451,6 +1477,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old) if (test_bit(TTY_HW_COOK_IN, &tty->flags)) { tty->raw = 1; tty->real_raw = 1; + n_tty_set_room(tty); return; } if (I_ISTRIP(tty) || I_IUCLC(tty) || I_IGNCR(tty) || @@ -1503,6 +1530,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old) else tty->real_raw = 0; } + n_tty_set_room(tty); /* The termios change make the tty ready for I/O */ wake_up_interruptible(&tty->write_wait); wake_up_interruptible(&tty->read_wait); @@ -1784,6 +1812,8 @@ do_it_again: retval = -ERESTARTSYS; break; } + /* FIXME: does n_tty_set_room need locking ? */ + n_tty_set_room(tty); timeout = schedule_timeout(timeout); continue; } @@ -1855,8 +1885,10 @@ do_it_again: * longer than TTY_THRESHOLD_UNTHROTTLE in canonical mode, * we won't get any more characters. */ - if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE) + if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE) { + n_tty_set_room(tty); check_unthrottle(tty); + } if (b - buf >= minimum) break; @@ -1878,6 +1910,7 @@ do_it_again: } else if (test_and_clear_bit(TTY_PUSH, &tty->flags)) goto do_it_again; + n_tty_set_room(tty); return retval; } diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 46de2e075dac..f1a7918d71aa 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -416,7 +416,6 @@ static void flush_to_ldisc(struct work_struct *work) struct tty_buffer *head, *tail = tty->buf.tail; int seen_tail = 0; while ((head = tty->buf.head) != NULL) { - int copied; int count; char *char_buf; unsigned char *flag_buf; @@ -443,19 +442,17 @@ static void flush_to_ldisc(struct work_struct *work) line discipline as we want to empty the queue */ if (test_bit(TTY_FLUSHPENDING, &tty->flags)) break; + if (!tty->receive_room || seen_tail) + break; + if (count > tty->receive_room) + count = tty->receive_room; char_buf = head->char_buf_ptr + head->read; flag_buf = head->flag_buf_ptr + head->read; + head->read += count; spin_unlock_irqrestore(&tty->buf.lock, flags); - copied = disc->ops->receive_buf(tty, char_buf, + disc->ops->receive_buf(tty, char_buf, flag_buf, count); spin_lock_irqsave(&tty->buf.lock, flags); - - head->read += copied; - - if (copied == 0 || seen_tail) { - schedule_work(&tty->buf.work); - break; - } } clear_bit(TTY_FLUSHING, &tty->flags); } diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c index 67b1d0d7c8ac..fb864e7fcd13 100644 --- a/drivers/tty/vt/selection.c +++ b/drivers/tty/vt/selection.c @@ -332,7 +332,8 @@ int paste_selection(struct tty_struct *tty) continue; } count = sel_buffer_lth - pasted; - count = tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted, + count = min(count, tty->receive_room); + tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted, NULL, count); pasted += count; } diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 2f7c76a85e53..e224a92baa16 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -144,7 +144,7 @@ static void handle_tx(struct vhost_net *net) } mutex_lock(&vq->mutex); - vhost_disable_notify(vq); + vhost_disable_notify(&net->dev, vq); if (wmem < sock->sk->sk_sndbuf / 2) tx_poll_stop(net); @@ -166,8 +166,8 @@ static void handle_tx(struct vhost_net *net) set_bit(SOCK_ASYNC_NOSPACE, &sock->flags); break; } - if (unlikely(vhost_enable_notify(vq))) { - vhost_disable_notify(vq); + if (unlikely(vhost_enable_notify(&net->dev, vq))) { + vhost_disable_notify(&net->dev, vq); continue; } break; @@ -315,7 +315,7 @@ static void handle_rx(struct vhost_net *net) return; mutex_lock(&vq->mutex); - vhost_disable_notify(vq); + vhost_disable_notify(&net->dev, vq); vhost_hlen = vq->vhost_hlen; sock_hlen = vq->sock_hlen; @@ -334,10 +334,10 @@ static void handle_rx(struct vhost_net *net) break; /* OK, now we need to know about added descriptors. */ if (!headcount) { - if (unlikely(vhost_enable_notify(vq))) { + if (unlikely(vhost_enable_notify(&net->dev, vq))) { /* They have slipped one in as we were * doing that: check again. */ - vhost_disable_notify(vq); + vhost_disable_notify(&net->dev, vq); continue; } /* Nothing new? Wait for eventfd to tell us diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index 099f30230d06..734e1d74ad80 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -49,7 +49,7 @@ static void handle_vq(struct vhost_test *n) return; mutex_lock(&vq->mutex); - vhost_disable_notify(vq); + vhost_disable_notify(&n->dev, vq); for (;;) { head = vhost_get_vq_desc(&n->dev, vq, vq->iov, @@ -61,8 +61,8 @@ static void handle_vq(struct vhost_test *n) break; /* Nothing new? Wait for eventfd to tell us they refilled. */ if (head == vq->num) { - if (unlikely(vhost_enable_notify(vq))) { - vhost_disable_notify(vq); + if (unlikely(vhost_enable_notify(&n->dev, vq))) { + vhost_disable_notify(&n->dev, vq); continue; } break; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 7aa4eea930f1..ea966b356352 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -37,6 +37,9 @@ enum { VHOST_MEMORY_F_LOG = 0x1, }; +#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num]) +#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num]) + static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh, poll_table *pt) { @@ -161,6 +164,8 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->last_avail_idx = 0; vq->avail_idx = 0; vq->last_used_idx = 0; + vq->signalled_used = 0; + vq->signalled_used_valid = false; vq->used_flags = 0; vq->log_used = false; vq->log_addr = -1ull; @@ -489,16 +494,17 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem, return 1; } -static int vq_access_ok(unsigned int num, +static int vq_access_ok(struct vhost_dev *d, unsigned int num, struct vring_desc __user *desc, struct vring_avail __user *avail, struct vring_used __user *used) { + size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; return access_ok(VERIFY_READ, desc, num * sizeof *desc) && access_ok(VERIFY_READ, avail, - sizeof *avail + num * sizeof *avail->ring) && + sizeof *avail + num * sizeof *avail->ring + s) && access_ok(VERIFY_WRITE, used, - sizeof *used + num * sizeof *used->ring); + sizeof *used + num * sizeof *used->ring + s); } /* Can we log writes? */ @@ -514,9 +520,11 @@ int vhost_log_access_ok(struct vhost_dev *dev) /* Verify access for write logging. */ /* Caller should have vq mutex and device mutex */ -static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base) +static int vq_log_access_ok(struct vhost_dev *d, struct vhost_virtqueue *vq, + void __user *log_base) { struct vhost_memory *mp; + size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; mp = rcu_dereference_protected(vq->dev->memory, lockdep_is_held(&vq->mutex)); @@ -524,15 +532,15 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base) vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) && (!vq->log_used || log_access_ok(log_base, vq->log_addr, sizeof *vq->used + - vq->num * sizeof *vq->used->ring)); + vq->num * sizeof *vq->used->ring + s)); } /* Can we start vq? */ /* Caller should have vq mutex and device mutex */ int vhost_vq_access_ok(struct vhost_virtqueue *vq) { - return vq_access_ok(vq->num, vq->desc, vq->avail, vq->used) && - vq_log_access_ok(vq, vq->log_base); + return vq_access_ok(vq->dev, vq->num, vq->desc, vq->avail, vq->used) && + vq_log_access_ok(vq->dev, vq, vq->log_base); } static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) @@ -577,6 +585,7 @@ static int init_used(struct vhost_virtqueue *vq, if (r) return r; + vq->signalled_used_valid = false; return get_user(vq->last_used_idx, &used->idx); } @@ -674,7 +683,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) * If it is not, we don't as size might not have been setup. * We will verify when backend is configured. */ if (vq->private_data) { - if (!vq_access_ok(vq->num, + if (!vq_access_ok(d, vq->num, (void __user *)(unsigned long)a.desc_user_addr, (void __user *)(unsigned long)a.avail_user_addr, (void __user *)(unsigned long)a.used_user_addr)) { @@ -818,7 +827,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg) vq = d->vqs + i; mutex_lock(&vq->mutex); /* If ring is inactive, will check when it's enabled. */ - if (vq->private_data && !vq_log_access_ok(vq, base)) + if (vq->private_data && !vq_log_access_ok(d, vq, base)) r = -EFAULT; else vq->log_base = base; @@ -1219,6 +1228,10 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, /* On success, increment avail index. */ vq->last_avail_idx++; + + /* Assume notifications from guest are disabled at this point, + * if they aren't we would need to update avail_event index. */ + BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY)); return head; } @@ -1267,6 +1280,12 @@ int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len) eventfd_signal(vq->log_ctx, 1); } vq->last_used_idx++; + /* If the driver never bothers to signal in a very long while, + * used index might wrap around. If that happens, invalidate + * signalled_used index we stored. TODO: make sure driver + * signals at least once in 2^16 and remove this. */ + if (unlikely(vq->last_used_idx == vq->signalled_used)) + vq->signalled_used_valid = false; return 0; } @@ -1275,6 +1294,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq, unsigned count) { struct vring_used_elem __user *used; + u16 old, new; int start; start = vq->last_used_idx % vq->num; @@ -1292,7 +1312,14 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq, ((void __user *)used - (void __user *)vq->used), count * sizeof *used); } - vq->last_used_idx += count; + old = vq->last_used_idx; + new = (vq->last_used_idx += count); + /* If the driver never bothers to signal in a very long while, + * used index might wrap around. If that happens, invalidate + * signalled_used index we stored. TODO: make sure driver + * signals at least once in 2^16 and remove this. */ + if (unlikely((u16)(new - vq->signalled_used) < (u16)(new - old))) + vq->signalled_used_valid = false; return 0; } @@ -1331,29 +1358,47 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, return r; } -/* This actually signals the guest, using eventfd. */ -void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq) +static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) { - __u16 flags; - + __u16 old, new, event; + bool v; /* Flush out used index updates. This is paired * with the barrier that the Guest executes when enabling * interrupts. */ smp_mb(); - if (__get_user(flags, &vq->avail->flags)) { - vq_err(vq, "Failed to get flags"); - return; + if (vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY) && + unlikely(vq->avail_idx == vq->last_avail_idx)) + return true; + + if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) { + __u16 flags; + if (__get_user(flags, &vq->avail->flags)) { + vq_err(vq, "Failed to get flags"); + return true; + } + return !(flags & VRING_AVAIL_F_NO_INTERRUPT); } + old = vq->signalled_used; + v = vq->signalled_used_valid; + new = vq->signalled_used = vq->last_used_idx; + vq->signalled_used_valid = true; - /* If they don't want an interrupt, don't signal, unless empty. */ - if ((flags & VRING_AVAIL_F_NO_INTERRUPT) && - (vq->avail_idx != vq->last_avail_idx || - !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY))) - return; + if (unlikely(!v)) + return true; + if (get_user(event, vhost_used_event(vq))) { + vq_err(vq, "Failed to get used event idx"); + return true; + } + return vring_need_event(event, new, old); +} + +/* This actually signals the guest, using eventfd. */ +void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq) +{ /* Signal the Guest tell them we used something up. */ - if (vq->call_ctx) + if (vq->call_ctx && vhost_notify(dev, vq)) eventfd_signal(vq->call_ctx, 1); } @@ -1376,7 +1421,7 @@ void vhost_add_used_and_signal_n(struct vhost_dev *dev, } /* OK, now we need to know about added descriptors. */ -bool vhost_enable_notify(struct vhost_virtqueue *vq) +bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) { u16 avail_idx; int r; @@ -1384,11 +1429,34 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq) if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY)) return false; vq->used_flags &= ~VRING_USED_F_NO_NOTIFY; - r = put_user(vq->used_flags, &vq->used->flags); - if (r) { - vq_err(vq, "Failed to enable notification at %p: %d\n", - &vq->used->flags, r); - return false; + if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) { + r = put_user(vq->used_flags, &vq->used->flags); + if (r) { + vq_err(vq, "Failed to enable notification at %p: %d\n", + &vq->used->flags, r); + return false; + } + } else { + r = put_user(vq->avail_idx, vhost_avail_event(vq)); + if (r) { + vq_err(vq, "Failed to update avail event index at %p: %d\n", + vhost_avail_event(vq), r); + return false; + } + } + if (unlikely(vq->log_used)) { + void __user *used; + /* Make sure data is seen before log. */ + smp_wmb(); + used = vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX) ? + &vq->used->flags : vhost_avail_event(vq); + /* Log used flags or event index entry write. Both are 16 bit + * fields. */ + log_write(vq->log_base, vq->log_addr + + (used - (void __user *)vq->used), + sizeof(u16)); + if (vq->log_ctx) + eventfd_signal(vq->log_ctx, 1); } /* They could have slipped one in as we were doing that: make * sure it's written, then check again. */ @@ -1404,15 +1472,17 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq) } /* We don't need to be notified again. */ -void vhost_disable_notify(struct vhost_virtqueue *vq) +void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) { int r; if (vq->used_flags & VRING_USED_F_NO_NOTIFY) return; vq->used_flags |= VRING_USED_F_NO_NOTIFY; - r = put_user(vq->used_flags, &vq->used->flags); - if (r) - vq_err(vq, "Failed to enable notification at %p: %d\n", - &vq->used->flags, r); + if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) { + r = put_user(vq->used_flags, &vq->used->flags); + if (r) + vq_err(vq, "Failed to enable notification at %p: %d\n", + &vq->used->flags, r); + } } diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index b3363ae38518..8e03379dd30f 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -84,6 +84,12 @@ struct vhost_virtqueue { /* Used flags */ u16 used_flags; + /* Last used index value we have signalled on */ + u16 signalled_used; + + /* Last used index value we have signalled on */ + bool signalled_used_valid; + /* Log writes to used structure. */ bool log_used; u64 log_addr; @@ -149,8 +155,8 @@ void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *, void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *, struct vring_used_elem *heads, unsigned count); void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *); -void vhost_disable_notify(struct vhost_virtqueue *); -bool vhost_enable_notify(struct vhost_virtqueue *); +void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *); +bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *); int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log, unsigned int log_num, u64 len); @@ -162,11 +168,12 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log, } while (0) enum { - VHOST_FEATURES = (1 << VIRTIO_F_NOTIFY_ON_EMPTY) | - (1 << VIRTIO_RING_F_INDIRECT_DESC) | - (1 << VHOST_F_LOG_ALL) | - (1 << VHOST_NET_F_VIRTIO_NET_HDR) | - (1 << VIRTIO_NET_F_MRG_RXBUF), + VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) | + (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | + (1ULL << VIRTIO_RING_F_EVENT_IDX) | + (1ULL << VHOST_F_LOG_ALL) | + (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) | + (1ULL << VIRTIO_NET_F_MRG_RXBUF), }; static inline int vhost_has_feature(struct vhost_dev *dev, int bit) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 0f1da45ba47d..e058ace2a4ad 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -40,9 +40,6 @@ struct virtio_balloon /* Waiting for host to ack the pages we released. */ struct completion acked; - /* Do we have to tell Host *before* we reuse pages? */ - bool tell_host_first; - /* The pages we've told the Host we're not using. */ unsigned int num_pages; struct list_head pages; @@ -151,13 +148,14 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num) vb->num_pages--; } - if (vb->tell_host_first) { - tell_host(vb, vb->deflate_vq); - release_pages_by_pfn(vb->pfns, vb->num_pfns); - } else { - release_pages_by_pfn(vb->pfns, vb->num_pfns); - tell_host(vb, vb->deflate_vq); - } + + /* + * Note that if + * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST); + * is true, we *have* to do it in this order + */ + tell_host(vb, vb->deflate_vq); + release_pages_by_pfn(vb->pfns, vb->num_pfns); } static inline void update_stat(struct virtio_balloon *vb, int idx, @@ -325,9 +323,6 @@ static int virtballoon_probe(struct virtio_device *vdev) goto out_del_vqs; } - vb->tell_host_first - = virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST); - return 0; out_del_vqs: diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index b0043fb26a4d..68b9136847af 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -82,6 +82,9 @@ struct vring_virtqueue /* Host supports indirect buffers */ bool indirect; + /* Host publishes avail event idx */ + bool event; + /* Number of free buffers */ unsigned int num_free; /* Head of free buffer list. */ @@ -237,18 +240,22 @@ EXPORT_SYMBOL_GPL(virtqueue_add_buf_gfp); void virtqueue_kick(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); + u16 new, old; START_USE(vq); /* Descriptors and available array need to be set before we expose the * new available array entries. */ virtio_wmb(); - vq->vring.avail->idx += vq->num_added; + old = vq->vring.avail->idx; + new = vq->vring.avail->idx = old + vq->num_added; vq->num_added = 0; /* Need to update avail index before checking if we should notify */ virtio_mb(); - if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY)) + if (vq->event ? + vring_need_event(vring_avail_event(&vq->vring), new, old) : + !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY)) /* Prod other side to tell it about changes. */ vq->notify(&vq->vq); @@ -324,6 +331,14 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) ret = vq->data[i]; detach_buf(vq, i); vq->last_used_idx++; + /* If we expect an interrupt for the next entry, tell host + * by writing event index and flush out the write before + * the read in the next get_buf call. */ + if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) { + vring_used_event(&vq->vring) = vq->last_used_idx; + virtio_mb(); + } + END_USE(vq); return ret; } @@ -345,7 +360,11 @@ bool virtqueue_enable_cb(struct virtqueue *_vq) /* We optimistically turn back on interrupts, then check if there was * more to do. */ + /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to + * either clear the flags bit or point the event index at the next + * entry. Always do both to keep code simple. */ vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT; + vring_used_event(&vq->vring) = vq->last_used_idx; virtio_mb(); if (unlikely(more_used(vq))) { END_USE(vq); @@ -357,6 +376,33 @@ bool virtqueue_enable_cb(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(virtqueue_enable_cb); +bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + u16 bufs; + + START_USE(vq); + + /* We optimistically turn back on interrupts, then check if there was + * more to do. */ + /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to + * either clear the flags bit or point the event index at the next + * entry. Always do both to keep code simple. */ + vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT; + /* TODO: tune this threshold */ + bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4; + vring_used_event(&vq->vring) = vq->last_used_idx + bufs; + virtio_mb(); + if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) { + END_USE(vq); + return false; + } + + END_USE(vq); + return true; +} +EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed); + void *virtqueue_detach_unused_buf(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); @@ -438,6 +484,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int num, #endif vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC); + vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); /* No callback? Tell other side not to bother us. */ if (!callback) @@ -472,6 +519,8 @@ void vring_transport_features(struct virtio_device *vdev) switch (i) { case VIRTIO_RING_F_INDIRECT_DESC: break; + case VIRTIO_RING_F_EVENT_IDX: + break; default: /* We don't understand this bit. */ clear_bit(i, vdev->features); |