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

Pull virtio & lguest updates from Rusty Russell:
 "Lots of virtio work which wasn't quite ready for last merge window.

  Plus I dived into lguest again, reworking the pagetable code so we can
  move the switcher page: our fixmaps sometimes take more than 2MB now..."

Ugh.  Annoying conflicts with the tcm_vhost -> vhost_scsi rename.
Hopefully correctly resolved.

* tag 'virtio-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux: (57 commits)
  caif_virtio: Remove bouncing email addresses
  lguest: improve code readability in lg_cpu_start.
  virtio-net: fill only rx queues which are being used
  lguest: map Switcher below fixmap.
  lguest: cache last cpu we ran on.
  lguest: map Switcher text whenever we allocate a new pagetable.
  lguest: don't share Switcher PTE pages between guests.
  lguest: expost switcher_pages array (as lg_switcher_pages).
  lguest: extract shadow PTE walking / allocating.
  lguest: make check_gpte et. al return bool.
  lguest: assume Switcher text is a single page.
  lguest: rename switcher_page to switcher_pages.
  lguest: remove RESERVE_MEM constant.
  lguest: check vaddr not pgd for Switcher protection.
  lguest: prepare to make SWITCHER_ADDR a variable.
  virtio: console: replace EMFILE with EBUSY for already-open port
  virtio-scsi: reset virtqueue affinity when doing cpu hotplug
  virtio-scsi: introduce multiqueue support
  virtio-scsi: push vq lock/unlock into virtscsi_vq_done
  virtio-scsi: pass struct virtio_scsi to virtqueue completion function
  ...

5 files changed, 342 insertions, 0 deletions

diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 2d8bdaef9611..bfc47e0de81c 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -172,6 +172,22 @@ static inline void sg_mark_end(struct scatterlist *sg)
 }
 
 /**
+ * sg_unmark_end - Undo setting the end of the scatterlist
+ * @sg:          SG entryScatterlist
+ *
+ * Description:
+ *   Removes the termination marker from the given entry of the scatterlist.
+ *
+ **/
+static inline void sg_unmark_end(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+        BUG_ON(sg->sg_magic != SG_MAGIC);
+#endif
+        sg->page_link &= ~0x02;
+}
+
+/**
  * sg_phys - Return physical address of an sg entry
  * @sg:      SG entry
  *
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 2d7a5e045908..9ff8645b7e0b 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -8,6 +8,7 @@
 #include <linux/device.h>
 #include <linux/mod_devicetable.h>
 #include <linux/gfp.h>
+#include <linux/vringh.h>
 
 /**
  * virtqueue - a queue to register buffers for sending or receiving.
@@ -40,6 +41,23 @@ int virtqueue_add_buf(struct virtqueue *vq,
                       void *data,
                       gfp_t gfp);
 
+int virtqueue_add_outbuf(struct virtqueue *vq,
+                         struct scatterlist sg[], unsigned int num,
+                         void *data,
+                         gfp_t gfp);
+
+int virtqueue_add_inbuf(struct virtqueue *vq,
+                        struct scatterlist sg[], unsigned int num,
+                        void *data,
+                        gfp_t gfp);
+
+int virtqueue_add_sgs(struct virtqueue *vq,
+                      struct scatterlist *sgs[],
+                      unsigned int out_sgs,
+                      unsigned int in_sgs,
+                      void *data,
+                      gfp_t gfp);
+
 void virtqueue_kick(struct virtqueue *vq);
 
 bool virtqueue_kick_prepare(struct virtqueue *vq);
@@ -64,6 +82,7 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *vq);
  * @dev: underlying device.
  * @id: the device type identification (used to match it with a driver).
  * @config: the configuration ops for this device.
+ * @vringh_config: configuration ops for host vrings.
  * @vqs: the list of virtqueues for this device.
  * @features: the features supported by both driver and device.
  * @priv: private pointer for the driver's use.
@@ -73,6 +92,7 @@ struct virtio_device {
         struct device dev;
         struct virtio_device_id id;
         const struct virtio_config_ops *config;
+        const struct vringh_config_ops *vringh_config;
         struct list_head vqs;
         /* Note that this is a Linux set_bit-style bitmap. */
         unsigned long features[1];
diff --git a/include/linux/virtio_caif.h b/include/linux/virtio_caif.h
new file mode 100644
index 000000000000..5d2d3124ca3d
--- /dev/null
+++ b/include/linux/virtio_caif.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) ST-Ericsson AB 2012
+ * Author: Sjur Brændeland <sjur.brandeland@stericsson.com>
+ *
+ * This header is BSD licensed so
+ * anyone can use the definitions to implement compatible remote processors
+ */
+
+#ifndef VIRTIO_CAIF_H
+#define VIRTIO_CAIF_H
+
+#include <linux/types.h>
+struct virtio_caif_transf_config {
+        u16 headroom;
+        u16 tailroom;
+        u32 mtu;
+        u8 reserved[4];
+};
+
+struct virtio_caif_config {
+        struct virtio_caif_transf_config uplink, downlink;
+        u8 reserved[8];
+};
+#endif
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index 63c6ea199519..ca3ad41c2c82 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -4,6 +4,63 @@
 #include <linux/irqreturn.h>
 #include <uapi/linux/virtio_ring.h>
 
+/*
+ * Barriers in virtio are tricky.  Non-SMP virtio guests can't assume
+ * they're not on an SMP host system, so they need to assume real
+ * barriers.  Non-SMP virtio hosts could skip the barriers, but does
+ * anyone care?
+ *
+ * For virtio_pci on SMP, we don't need to order with respect to MMIO
+ * accesses through relaxed memory I/O windows, so smp_mb() et al are
+ * sufficient.
+ *
+ * For using virtio to talk to real devices (eg. other heterogeneous
+ * CPUs) we do need real barriers.  In theory, we could be using both
+ * kinds of virtio, so it's a runtime decision, and the branch is
+ * actually quite cheap.
+ */
+
+#ifdef CONFIG_SMP
+static inline void virtio_mb(bool weak_barriers)
+{
+        if (weak_barriers)
+                smp_mb();
+        else
+                mb();
+}
+
+static inline void virtio_rmb(bool weak_barriers)
+{
+        if (weak_barriers)
+                smp_rmb();
+        else
+                rmb();
+}
+
+static inline void virtio_wmb(bool weak_barriers)
+{
+        if (weak_barriers)
+                smp_wmb();
+        else
+                wmb();
+}
+#else
+static inline void virtio_mb(bool weak_barriers)
+{
+        mb();
+}
+
+static inline void virtio_rmb(bool weak_barriers)
+{
+        rmb();
+}
+
+static inline void virtio_wmb(bool weak_barriers)
+{
+        wmb();
+}
+#endif
+
 struct virtio_device;
 struct virtqueue;
 
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
new file mode 100644
index 000000000000..749cde28728b
--- /dev/null
+++ b/include/linux/vringh.h
@@ -0,0 +1,225 @@
+/*
+ * Linux host-side vring helpers; for when the kernel needs to access
+ * someone else's vring.
+ *
+ * Copyright IBM Corporation, 2013.
+ * Parts taken from drivers/vhost/vhost.c Copyright 2009 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Written by: Rusty Russell <rusty@rustcorp.com.au>
+ */
+#ifndef _LINUX_VRINGH_H
+#define _LINUX_VRINGH_H
+#include <uapi/linux/virtio_ring.h>
+#include <linux/uio.h>
+#include <linux/slab.h>
+#include <asm/barrier.h>
+
+/* virtio_ring with information needed for host access. */
+struct vringh {
+        /* Guest publishes used event idx (note: we always do). */
+        bool event_indices;
+
+        /* Can we get away with weak barriers? */
+        bool weak_barriers;
+
+        /* Last available index we saw (ie. where we're up to). */
+        u16 last_avail_idx;
+
+        /* Last index we used. */
+        u16 last_used_idx;
+
+        /* How many descriptors we've completed since last need_notify(). */
+        u32 completed;
+
+        /* The vring (note: it may contain user pointers!) */
+        struct vring vring;
+
+        /* The function to call to notify the guest about added buffers */
+        void (*notify)(struct vringh *);
+};
+
+/**
+ * struct vringh_config_ops - ops for creating a host vring from a virtio driver
+ * @find_vrhs: find the host vrings and instantiate them
+ *      vdev: the virtio_device
+ *      nhvrs: the number of host vrings to find
+ *      hvrs: on success, includes new host vrings
+ *      callbacks: array of driver callbacks, for each host vring
+ *              include a NULL entry for vqs that do not need a callback
+ *      Returns 0 on success or error status
+ * @del_vrhs: free the host vrings found by find_vrhs().
+ */
+struct virtio_device;
+typedef void vrh_callback_t(struct virtio_device *, struct vringh *);
+struct vringh_config_ops {
+        int (*find_vrhs)(struct virtio_device *vdev, unsigned nhvrs,
+                         struct vringh *vrhs[], vrh_callback_t *callbacks[]);
+        void (*del_vrhs)(struct virtio_device *vdev);
+};
+
+/* The memory the vring can access, and what offset to apply. */
+struct vringh_range {
+        u64 start, end_incl;
+        u64 offset;
+};
+
+/**
+ * struct vringh_iov - iovec mangler.
+ *
+ * Mangles iovec in place, and restores it.
+ * Remaining data is iov + i, of used - i elements.
+ */
+struct vringh_iov {
+        struct iovec *iov;
+        size_t consumed; /* Within iov[i] */
+        unsigned i, used, max_num;
+};
+
+/**
+ * struct vringh_iov - kvec mangler.
+ *
+ * Mangles kvec in place, and restores it.
+ * Remaining data is iov + i, of used - i elements.
+ */
+struct vringh_kiov {
+        struct kvec *iov;
+        size_t consumed; /* Within iov[i] */
+        unsigned i, used, max_num;
+};
+
+/* Flag on max_num to indicate we're kmalloced. */
+#define VRINGH_IOV_ALLOCATED 0x8000000
+
+/* Helpers for userspace vrings. */
+int vringh_init_user(struct vringh *vrh, u32 features,
+                     unsigned int num, bool weak_barriers,
+                     struct vring_desc __user *desc,
+                     struct vring_avail __user *avail,
+                     struct vring_used __user *used);
+
+static inline void vringh_iov_init(struct vringh_iov *iov,
+                                   struct iovec *iovec, unsigned num)
+{
+        iov->used = iov->i = 0;
+        iov->consumed = 0;
+        iov->max_num = num;
+        iov->iov = iovec;
+}
+
+static inline void vringh_iov_reset(struct vringh_iov *iov)
+{
+        iov->iov[iov->i].iov_len += iov->consumed;
+        iov->iov[iov->i].iov_base -= iov->consumed;
+        iov->consumed = 0;
+        iov->i = 0;
+}
+
+static inline void vringh_iov_cleanup(struct vringh_iov *iov)
+{
+        if (iov->max_num & VRINGH_IOV_ALLOCATED)
+                kfree(iov->iov);
+        iov->max_num = iov->used = iov->i = iov->consumed = 0;
+        iov->iov = NULL;
+}
+
+/* Convert a descriptor into iovecs. */
+int vringh_getdesc_user(struct vringh *vrh,
+                        struct vringh_iov *riov,
+                        struct vringh_iov *wiov,
+                        bool (*getrange)(struct vringh *vrh,
+                                         u64 addr, struct vringh_range *r),
+                        u16 *head);
+
+/* Copy bytes from readable vsg, consuming it (and incrementing wiov->i). */
+ssize_t vringh_iov_pull_user(struct vringh_iov *riov, void *dst, size_t len);
+
+/* Copy bytes into writable vsg, consuming it (and incrementing wiov->i). */
+ssize_t vringh_iov_push_user(struct vringh_iov *wiov,
+                             const void *src, size_t len);
+
+/* Mark a descriptor as used. */
+int vringh_complete_user(struct vringh *vrh, u16 head, u32 len);
+int vringh_complete_multi_user(struct vringh *vrh,
+                               const struct vring_used_elem used[],
+                               unsigned num_used);
+
+/* Pretend we've never seen descriptor (for easy error handling). */
+void vringh_abandon_user(struct vringh *vrh, unsigned int num);
+
+/* Do we need to fire the eventfd to notify the other side? */
+int vringh_need_notify_user(struct vringh *vrh);
+
+bool vringh_notify_enable_user(struct vringh *vrh);
+void vringh_notify_disable_user(struct vringh *vrh);
+
+/* Helpers for kernelspace vrings. */
+int vringh_init_kern(struct vringh *vrh, u32 features,
+                     unsigned int num, bool weak_barriers,
+                     struct vring_desc *desc,
+                     struct vring_avail *avail,
+                     struct vring_used *used);
+
+static inline void vringh_kiov_init(struct vringh_kiov *kiov,
+                                    struct kvec *kvec, unsigned num)
+{
+        kiov->used = kiov->i = 0;
+        kiov->consumed = 0;
+        kiov->max_num = num;
+        kiov->iov = kvec;
+}
+
+static inline void vringh_kiov_reset(struct vringh_kiov *kiov)
+{
+        kiov->iov[kiov->i].iov_len += kiov->consumed;
+        kiov->iov[kiov->i].iov_base -= kiov->consumed;
+        kiov->consumed = 0;
+        kiov->i = 0;
+}
+
+static inline void vringh_kiov_cleanup(struct vringh_kiov *kiov)
+{
+        if (kiov->max_num & VRINGH_IOV_ALLOCATED)
+                kfree(kiov->iov);
+        kiov->max_num = kiov->used = kiov->i = kiov->consumed = 0;
+        kiov->iov = NULL;
+}
+
+int vringh_getdesc_kern(struct vringh *vrh,
+                        struct vringh_kiov *riov,
+                        struct vringh_kiov *wiov,
+                        u16 *head,
+                        gfp_t gfp);
+
+ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len);
+ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov,
+                             const void *src, size_t len);
+void vringh_abandon_kern(struct vringh *vrh, unsigned int num);
+int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len);
+
+bool vringh_notify_enable_kern(struct vringh *vrh);
+void vringh_notify_disable_kern(struct vringh *vrh);
+
+int vringh_need_notify_kern(struct vringh *vrh);
+
+/* Notify the guest about buffers added to the used ring */
+static inline void vringh_notify(struct vringh *vrh)
+{
+        if (vrh->notify)
+                vrh->notify(vrh);
+}
+
+#endif /* _LINUX_VRINGH_H */