Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-f…

…or-linus

* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
  lguest: struct device - replace bus_id with dev_name()
  lguest: move the initial guest page table creation code to the host
  kvm-s390: implement config_changed for virtio on s390
  virtio_console: support console resizing
  virtio: add PCI device release() function
  virtio_blk: fix type warning
  virtio: block: dynamic maximum segments
  virtio: set max_segment_size and max_sectors to infinite.
  virtio: avoid implicit use of Linux page size in balloon interface
  virtio: hand virtio ring alignment as argument to vring_new_virtqueue
  virtio: use KVM_S390_VIRTIO_RING_ALIGN instead of relying on pagesize
  virtio: use LGUEST_VRING_ALIGN instead of relying on pagesize
  virtio: Don't use PAGE_SIZE for vring alignment in virtio_pci.
  virtio: rename 'pagesize' arg to vring_init/vring_size
  virtio: Don't use PAGE_SIZE in virtio_pci.c
  virtio: struct device - replace bus_id with dev_name(), dev_set_name()
  virtio-pci queue allocation not page-aligned

Documentation/lguest/lguest.c

@@ -481,51 +481,6 @@ static unsigned long load_initrd(const char *name, unsigned long mem)
 	/* We return the initrd size. */
 	return len;
 }
-
-/* Once we know how much memory we have we can construct simple linear page
- * tables which set virtual == physical which will get the Guest far enough
- * into the boot to create its own.
- *
- * We lay them out of the way, just below the initrd (which is why we need to
- * know its size here). */
-static unsigned long setup_pagetables(unsigned long mem,
-				      unsigned long initrd_size)
-{
-	unsigned long *pgdir, *linear;
-	unsigned int mapped_pages, i, linear_pages;
-	unsigned int ptes_per_page = getpagesize()/sizeof(void *);
-
-	mapped_pages = mem/getpagesize();
-
-	/* Each PTE page can map ptes_per_page pages: how many do we need? */
-	linear_pages = (mapped_pages + ptes_per_page-1)/ptes_per_page;
-
-	/* We put the toplevel page directory page at the top of memory. */
-	pgdir = from_guest_phys(mem) - initrd_size - getpagesize();
-
-	/* Now we use the next linear_pages pages as pte pages */
-	linear = (void *)pgdir - linear_pages*getpagesize();
-
-	/* Linear mapping is easy: put every page's address into the mapping in
-	 * order.  PAGE_PRESENT contains the flags Present, Writable and
-	 * Executable. */
-	for (i = 0; i < mapped_pages; i++)
-		linear[i] = ((i * getpagesize()) | PAGE_PRESENT);
-
-	/* The top level points to the linear page table pages above. */
-	for (i = 0; i < mapped_pages; i += ptes_per_page) {
-		pgdir[i/ptes_per_page]
-			= ((to_guest_phys(linear) + i*sizeof(void *))
-			   | PAGE_PRESENT);
-	}
-
-	verbose("Linear mapping of %u pages in %u pte pages at %#lx\n",
-		mapped_pages, linear_pages, to_guest_phys(linear));
-
-	/* We return the top level (guest-physical) address: the kernel needs
-	 * to know where it is. */
-	return to_guest_phys(pgdir);
-}
 /*:*/
 
 /* Simple routine to roll all the commandline arguments together with spaces
@@ -548,13 +503,13 @@ static void concat(char *dst, char *args[])
 
 /*L:185 This is where we actually tell the kernel to initialize the Guest.  We
  * saw the arguments it expects when we looked at initialize() in lguest_user.c:
- * the base of Guest "physical" memory, the top physical page to allow, the
- * top level pagetable and the entry point for the Guest. */
-static int tell_kernel(unsigned long pgdir, unsigned long start)
+ * the base of Guest "physical" memory, the top physical page to allow and the
+ * entry point for the Guest. */
+static int tell_kernel(unsigned long start)
 {
 	unsigned long args[] = { LHREQ_INITIALIZE,
 				 (unsigned long)guest_base,
-				 guest_limit / getpagesize(), pgdir, start };
+				 guest_limit / getpagesize(), start };
 	int fd;
 
 	verbose("Guest: %p - %p (%#lx)\n",
@@ -1030,7 +985,7 @@ static void update_device_status(struct device *dev)
 		/* Zero out the virtqueues. */
 		for (vq = dev->vq; vq; vq = vq->next) {
 			memset(vq->vring.desc, 0,
-			       vring_size(vq->config.num, getpagesize()));
+			       vring_size(vq->config.num, LGUEST_VRING_ALIGN));
 			lg_last_avail(vq) = 0;
 		}
 	} else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
@@ -1211,7 +1166,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	void *p;
 
 	/* First we need some memory for this virtqueue. */
-	pages = (vring_size(num_descs, getpagesize()) + getpagesize() - 1)
+	pages = (vring_size(num_descs, LGUEST_VRING_ALIGN) + getpagesize() - 1)
 		/ getpagesize();
 	p = get_pages(pages);
 
@@ -1228,7 +1183,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	vq->config.pfn = to_guest_phys(p) / getpagesize();
 
 	/* Initialize the vring. */
-	vring_init(&vq->vring, num_descs, p, getpagesize());
+	vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN);
 
 	/* Append virtqueue to this device's descriptor.  We use
 	 * device_config() to get the end of the device's current virtqueues;
@@ -1941,7 +1896,7 @@ int main(int argc, char *argv[])
 {
 	/* Memory, top-level pagetable, code startpoint and size of the
 	 * (optional) initrd. */
-	unsigned long mem = 0, pgdir, start, initrd_size = 0;
+	unsigned long mem = 0, start, initrd_size = 0;
 	/* Two temporaries and the /dev/lguest file descriptor. */
 	int i, c, lguest_fd;
 	/* The boot information for the Guest. */
@@ -2040,9 +1995,6 @@ int main(int argc, char *argv[])
 		boot->hdr.type_of_loader = 0xFF;
 	}
 
-	/* Set up the initial linear pagetables, starting below the initrd. */
-	pgdir = setup_pagetables(mem, initrd_size);
-
 	/* The Linux boot header contains an "E820" memory map: ours is a
 	 * simple, single region. */
 	boot->e820_entries = 1;
@@ -2064,7 +2016,7 @@ int main(int argc, char *argv[])
 
 	/* We tell the kernel to initialize the Guest: this returns the open
 	 * /dev/lguest file descriptor. */
-	lguest_fd = tell_kernel(pgdir, start);
+	lguest_fd = tell_kernel(start);
 
 	/* We clone off a thread, which wakes the Launcher whenever one of the
 	 * input file descriptors needs attention.  We call this the Waker, and

arch/s390/include/asm/kvm_virtio.h

@@ -50,6 +50,10 @@ struct kvm_vqconfig {
 #define KVM_S390_VIRTIO_RESET		1
 #define KVM_S390_VIRTIO_SET_STATUS	2
 
+/* The alignment to use between consumer and producer parts of vring.
+ * This is pagesize for historical reasons. */
+#define KVM_S390_VIRTIO_RING_ALIGN	4096
+
 #ifdef __KERNEL__
 /* early virtio console setup */
 #ifdef CONFIG_S390_GUEST

arch/x86/lguest/i386_head.S

@@ -30,21 +30,6 @@ ENTRY(lguest_entry)
 	movl $lguest_data - __PAGE_OFFSET, %edx
 	int $LGUEST_TRAP_ENTRY
 
-	/* The Host put the toplevel pagetable in lguest_data.pgdir.  The movsl
-	 * instruction uses %esi implicitly as the source for the copy we're
-	 * about to do. */
-	movl lguest_data - __PAGE_OFFSET + LGUEST_DATA_pgdir, %esi
-
-	/* Copy first 32 entries of page directory to __PAGE_OFFSET entries.
-	 * This means the first 128M of kernel memory will be mapped at
-	 * PAGE_OFFSET where the kernel expects to run.  This will get it far
-	 * enough through boot to switch to its own pagetables. */
-	movl $32, %ecx
-	movl %esi, %edi
-	addl $((__PAGE_OFFSET >> 22) * 4), %edi
-	rep
-	movsl
-
 	/* Set up the initial stack so we can run C code. */
 	movl $(init_thread_union+THREAD_SIZE),%esp
 

drivers/block/virtio_blk.c

@@ -6,7 +6,6 @@
 #include <linux/virtio_blk.h>
 #include <linux/scatterlist.h>
 
-#define VIRTIO_MAX_SG	(3+MAX_PHYS_SEGMENTS)
 #define PART_BITS 4
 
 static int major, index;
@@ -26,8 +25,11 @@ struct virtio_blk
 
 	mempool_t *pool;
 
+	/* What host tells us, plus 2 for header & tailer. */
+	unsigned int sg_elems;
+
 	/* Scatterlist: can be too big for stack. */
-	struct scatterlist sg[VIRTIO_MAX_SG];
+	struct scatterlist sg[/*sg_elems*/];
 };
 
 struct virtblk_req
@@ -97,8 +99,6 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	if (blk_barrier_rq(vbr->req))
 		vbr->out_hdr.type |= VIRTIO_BLK_T_BARRIER;
 
-	/* This init could be done at vblk creation time */
-	sg_init_table(vblk->sg, VIRTIO_MAX_SG);
 	sg_set_buf(&vblk->sg[0], &vbr->out_hdr, sizeof(vbr->out_hdr));
 	num = blk_rq_map_sg(q, vbr->req, vblk->sg+1);
 	sg_set_buf(&vblk->sg[num+1], &vbr->status, sizeof(vbr->status));
@@ -130,7 +130,7 @@ static void do_virtblk_request(struct request_queue *q)
 
 	while ((req = elv_next_request(q)) != NULL) {
 		vblk = req->rq_disk->private_data;
-		BUG_ON(req->nr_phys_segments > ARRAY_SIZE(vblk->sg));
+		BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
 		/* If this request fails, stop queue and wait for something to
 		   finish to restart it. */
@@ -196,12 +196,22 @@ static int virtblk_probe(struct virtio_device *vdev)
 	int err;
 	u64 cap;
 	u32 v;
-	u32 blk_size;
+	u32 blk_size, sg_elems;
 
 	if (index_to_minor(index) >= 1 << MINORBITS)
 		return -ENOSPC;
 
-	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
+	/* We need to know how many segments before we allocate. */
+	err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX,
+				offsetof(struct virtio_blk_config, seg_max),
+				&sg_elems);
+	if (err)
+		sg_elems = 1;
+
+	/* We need an extra sg elements at head and tail. */
+	sg_elems += 2;
+	vdev->priv = vblk = kmalloc(sizeof(*vblk) +
+				    sizeof(vblk->sg[0]) * sg_elems, GFP_KERNEL);
 	if (!vblk) {
 		err = -ENOMEM;
 		goto out;
@@ -210,6 +220,8 @@ static int virtblk_probe(struct virtio_device *vdev)
 	INIT_LIST_HEAD(&vblk->reqs);
 	spin_lock_init(&vblk->lock);
 	vblk->vdev = vdev;
+	vblk->sg_elems = sg_elems;
+	sg_init_table(vblk->sg, vblk->sg_elems);
 
 	/* We expect one virtqueue, for output. */
 	vblk->vq = vdev->config->find_vq(vdev, 0, blk_done);
@@ -279,19 +291,22 @@ static int virtblk_probe(struct virtio_device *vdev)
 	}
 	set_capacity(vblk->disk, cap);
 
+	/* We can handle whatever the host told us to handle. */
+	blk_queue_max_phys_segments(vblk->disk->queue, vblk->sg_elems-2);
+	blk_queue_max_hw_segments(vblk->disk->queue, vblk->sg_elems-2);
+
+	/* No real sector limit. */
+	blk_queue_max_sectors(vblk->disk->queue, -1U);
+
 	/* Host can optionally specify maximum segment size and number of
 	 * segments. */
 	err = virtio_config_val(vdev, VIRTIO_BLK_F_SIZE_MAX,
 				offsetof(struct virtio_blk_config, size_max),
 				&v);
 	if (!err)
 		blk_queue_max_segment_size(vblk->disk->queue, v);
-
-	err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX,
-				offsetof(struct virtio_blk_config, seg_max),
-				&v);
-	if (!err)
-		blk_queue_max_hw_segments(vblk->disk->queue, v);
+	else
+		blk_queue_max_segment_size(vblk->disk->queue, -1U);
 
 	/* Host can optionally specify the block size of the device */
 	err = virtio_config_val(vdev, VIRTIO_BLK_F_BLK_SIZE,

drivers/char/hvc_console.c

@@ -695,6 +695,7 @@ void hvc_resize(struct hvc_struct *hp, struct winsize ws)
 	hp->ws = ws;
 	schedule_work(&hp->tty_resize);
 }
+EXPORT_SYMBOL_GPL(hvc_resize);
 
 /*
  * This kthread is either polling or interrupt driven.  This is determined by

drivers/char/virtio_console.c

@@ -137,13 +137,34 @@ int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int))
 	return hvc_instantiate(0, 0, &virtio_cons);
 }
 
+/*
+ * virtio console configuration. This supports:
+ * - console resize
+ */
+static void virtcons_apply_config(struct virtio_device *dev)
+{
+	struct winsize ws;
+
+	if (virtio_has_feature(dev, VIRTIO_CONSOLE_F_SIZE)) {
+		dev->config->get(dev,
+				 offsetof(struct virtio_console_config, cols),
+				 &ws.ws_col, sizeof(u16));
+		dev->config->get(dev,
+				 offsetof(struct virtio_console_config, rows),
+				 &ws.ws_row, sizeof(u16));
+		hvc_resize(hvc, ws);
+	}
+}
+
 /*
  * we support only one console, the hvc struct is a global var
- * There is no need to do anything
+ * We set the configuration at this point, since we now have a tty
  */
 static int notifier_add_vio(struct hvc_struct *hp, int data)
 {
 	hp->irq_requested = 1;
+	virtcons_apply_config(vdev);
+
 	return 0;
 }
 
@@ -234,11 +255,18 @@ static struct virtio_device_id id_table[] = {
 	{ 0 },
 };
 
+static unsigned int features[] = {
+	VIRTIO_CONSOLE_F_SIZE,
+};
+
 static struct virtio_driver virtio_console = {
+	.feature_table = features,
+	.feature_table_size = ARRAY_SIZE(features),
 	.driver.name =	KBUILD_MODNAME,
 	.driver.owner =	THIS_MODULE,
 	.id_table =	id_table,
 	.probe =	virtcons_probe,
+	.config_changed = virtcons_apply_config,
 };
 
 static int __init init(void)

drivers/lguest/lg.h

@@ -164,7 +164,7 @@ void copy_gdt(const struct lg_cpu *cpu, struct desc_struct *gdt);
 void copy_gdt_tls(const struct lg_cpu *cpu, struct desc_struct *gdt);
 
 /* page_tables.c: */
-int init_guest_pagetable(struct lguest *lg, unsigned long pgtable);
+int init_guest_pagetable(struct lguest *lg);
 void free_guest_pagetable(struct lguest *lg);
 void guest_new_pagetable(struct lg_cpu *cpu, unsigned long pgtable);
 void guest_set_pmd(struct lguest *lg, unsigned long gpgdir, u32 i);

drivers/lguest/lguest_device.c

@@ -250,7 +250,7 @@ static struct virtqueue *lg_find_vq(struct virtio_device *vdev,
 	/* Figure out how many pages the ring will take, and map that memory */
 	lvq->pages = lguest_map((unsigned long)lvq->config.pfn << PAGE_SHIFT,
 				DIV_ROUND_UP(vring_size(lvq->config.num,
-							PAGE_SIZE),
+							LGUEST_VRING_ALIGN),
 					     PAGE_SIZE));
 	if (!lvq->pages) {
 		err = -ENOMEM;
@@ -259,8 +259,8 @@ static struct virtqueue *lg_find_vq(struct virtio_device *vdev,
 
 	/* OK, tell virtio_ring.c to set up a virtqueue now we know its size
 	 * and we've got a pointer to its pages. */
-	vq = vring_new_virtqueue(lvq->config.num, vdev, lvq->pages,
-				 lg_notify, callback);
+	vq = vring_new_virtqueue(lvq->config.num, LGUEST_VRING_ALIGN,
+				 vdev, lvq->pages, lg_notify, callback);
 	if (!vq) {
 		err = -ENOMEM;
 		goto unmap;
@@ -272,7 +272,7 @@ static struct virtqueue *lg_find_vq(struct virtio_device *vdev,
 	 * the interrupt as a source of randomness: it'd be nice to have that
 	 * back.. */
 	err = request_irq(lvq->config.irq, vring_interrupt, IRQF_SHARED,
-			  vdev->dev.bus_id, vq);
+			  dev_name(&vdev->dev), vq);
 	if (err)
 		goto destroy_vring;