Merge branch 'linus' into release

5 files changed, 93 insertions, 25 deletions

diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c
index a1039068f95c..415fab0125ac 100644
--- a/drivers/lguest/interrupts_and_traps.c
+++ b/drivers/lguest/interrupts_and_traps.c
@@ -222,11 +222,16 @@ bool check_syscall_vector(struct lguest *lg)
 int init_interrupts(void)
 {
         /* If they want some strange system call vector, reserve it now */
-        if (syscall_vector != SYSCALL_VECTOR
-            && test_and_set_bit(syscall_vector, used_vectors)) {
-                printk("lg: couldn't reserve syscall %u\n", syscall_vector);
-                return -EBUSY;
+        if (syscall_vector != SYSCALL_VECTOR) {
+                if (test_bit(syscall_vector, used_vectors) ||
+                    vector_used_by_percpu_irq(syscall_vector)) {
+                        printk(KERN_ERR "lg: couldn't reserve syscall %u\n",
+                                 syscall_vector);
+                        return -EBUSY;
+                }
+                set_bit(syscall_vector, used_vectors);
         }
+
         return 0;
 }
 
diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h
index 5faefeaf6790..f2c641e0bdde 100644
--- a/drivers/lguest/lg.h
+++ b/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);
diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index a661bbdae3d6..b4d44e571d76 100644
--- a/drivers/lguest/lguest_device.c
+++ b/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;
 
@@ -321,10 +321,7 @@ static struct virtio_config_ops lguest_config_ops = {
 
 /* The root device for the lguest virtio devices.  This makes them appear as
  * /sys/devices/lguest/0,1,2 not /sys/devices/0,1,2. */
-static struct device lguest_root = {
-        .parent = NULL,
-        .bus_id = "lguest",
-};
+static struct device *lguest_root;
 
 /*D:120 This is the core of the lguest bus: actually adding a new device.
  * It's a separate function because it's neater that way, and because an
@@ -351,7 +348,7 @@ static void add_lguest_device(struct lguest_device_desc *d,
         }
 
         /* This devices' parent is the lguest/ dir. */
-        ldev->vdev.dev.parent = &lguest_root;
+        ldev->vdev.dev.parent = lguest_root;
         /* We have a unique device index thanks to the dev_index counter. */
         ldev->vdev.id.device = d->type;
         /* We have a simple set of routines for querying the device's
@@ -407,7 +404,8 @@ static int __init lguest_devices_init(void)
         if (strcmp(pv_info.name, "lguest") != 0)
                 return 0;
 
-        if (device_register(&lguest_root) != 0)
+        lguest_root = root_device_register("lguest");
+        if (IS_ERR(lguest_root))
                 panic("Could not register lguest root");
 
         /* Devices are in a single page above top of "normal" mem */
diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c
index e73a000473cc..34bc017b8b3c 100644
--- a/drivers/lguest/lguest_user.c
+++ b/drivers/lguest/lguest_user.c
@@ -146,7 +146,7 @@ static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip)
         return 0;
 }
 
-/*L:020 The initialization write supplies 4 pointer sized (32 or 64 bit)
+/*L:020 The initialization write supplies 3 pointer sized (32 or 64 bit)
  * values (in addition to the LHREQ_INITIALIZE value).  These are:
  *
  * base: The start of the Guest-physical memory inside the Launcher memory.
@@ -155,9 +155,6 @@ static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip)
  * allowed to access.  The Guest memory lives inside the Launcher, so it sets
  * this to ensure the Guest can only reach its own memory.
  *
- * pgdir: The (Guest-physical) address of the top of the initial Guest
- * pagetables (which are set up by the Launcher).
- *
  * start: The first instruction to execute ("eip" in x86-speak).
  */
 static int initialize(struct file *file, const unsigned long __user *input)
@@ -166,7 +163,7 @@ static int initialize(struct file *file, const unsigned long __user *input)
          * Guest. */
         struct lguest *lg;
         int err;
-        unsigned long args[4];
+        unsigned long args[3];
 
         /* We grab the Big Lguest lock, which protects against multiple
          * simultaneous initializations. */
@@ -192,14 +189,14 @@ static int initialize(struct file *file, const unsigned long __user *input)
         lg->mem_base = (void __user *)args[0];
         lg->pfn_limit = args[1];
 
-        /* This is the first cpu (cpu 0) and it will start booting at args[3] */
-        err = lg_cpu_start(&lg->cpus[0], 0, args[3]);
+        /* This is the first cpu (cpu 0) and it will start booting at args[2] */
+        err = lg_cpu_start(&lg->cpus[0], 0, args[2]);
         if (err)
                 goto release_guest;
 
         /* Initialize the Guest's shadow page tables, using the toplevel
          * address the Launcher gave us.  This allocates memory, so can fail. */
-        err = init_guest_pagetable(lg, args[2]);
+        err = init_guest_pagetable(lg);
         if (err)
                 goto free_regs;
 
diff --git a/drivers/lguest/page_tables.c b/drivers/lguest/page_tables.c
index 81d0c6053447..576a8318221c 100644
--- a/drivers/lguest/page_tables.c
+++ b/drivers/lguest/page_tables.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
+#include <asm/bootparam.h>
 #include "lg.h"
 
 /*M:008 We hold reference to pages, which prevents them from being swapped.
@@ -581,15 +582,82 @@ void guest_set_pmd(struct lguest *lg, unsigned long gpgdir, u32 idx)
                 release_pgd(lg, lg->pgdirs[pgdir].pgdir + idx);
 }
 
+/* Once we know how much memory we have we can construct simple identity
+ * (which set virtual == physical) and linear mappings
+ * 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(struct lguest *lg,
+                                      unsigned long mem,
+                                      unsigned long initrd_size)
+{
+        pgd_t __user *pgdir;
+        pte_t __user *linear;
+        unsigned int mapped_pages, i, linear_pages, phys_linear;
+        unsigned long mem_base = (unsigned long)lg->mem_base;
+
+        /* We have mapped_pages frames to map, so we need
+         * linear_pages page tables to map them. */
+        mapped_pages = mem / PAGE_SIZE;
+        linear_pages = (mapped_pages + PTRS_PER_PTE - 1) / PTRS_PER_PTE;
+
+        /* We put the toplevel page directory page at the top of memory. */
+        pgdir = (pgd_t *)(mem + mem_base - initrd_size - PAGE_SIZE);
+
+        /* Now we use the next linear_pages pages as pte pages */
+        linear = (void *)pgdir - linear_pages * PAGE_SIZE;
+
+        /* Linear mapping is easy: put every page's address into the
+         * mapping in order. */
+        for (i = 0; i < mapped_pages; i++) {
+                pte_t pte;
+                pte = pfn_pte(i, __pgprot(_PAGE_PRESENT|_PAGE_RW|_PAGE_USER));
+                if (copy_to_user(&linear[i], &pte, sizeof(pte)) != 0)
+                        return -EFAULT;
+        }
+
+        /* The top level points to the linear page table pages above.
+         * We setup the identity and linear mappings here. */
+        phys_linear = (unsigned long)linear - mem_base;
+        for (i = 0; i < mapped_pages; i += PTRS_PER_PTE) {
+                pgd_t pgd;
+                pgd = __pgd((phys_linear + i * sizeof(pte_t)) |
+                            (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER));
+
+                if (copy_to_user(&pgdir[i / PTRS_PER_PTE], &pgd, sizeof(pgd))
+                    || copy_to_user(&pgdir[pgd_index(PAGE_OFFSET)
+                                           + i / PTRS_PER_PTE],
+                                    &pgd, sizeof(pgd)))
+                        return -EFAULT;
+        }
+
+        /* We return the top level (guest-physical) address: remember where
+         * this is. */
+        return (unsigned long)pgdir - mem_base;
+}
+
 /*H:500 (vii) Setting up the page tables initially.
  *
  * When a Guest is first created, the Launcher tells us where the toplevel of
  * its first page table is.  We set some things up here: */
-int init_guest_pagetable(struct lguest *lg, unsigned long pgtable)
+int init_guest_pagetable(struct lguest *lg)
 {
+        u64 mem;
+        u32 initrd_size;
+        struct boot_params __user *boot = (struct boot_params *)lg->mem_base;
+
+        /* Get the Guest memory size and the ramdisk size from the boot header
+         * located at lg->mem_base (Guest address 0). */
+        if (copy_from_user(&mem, &boot->e820_map[0].size, sizeof(mem))
+            || get_user(initrd_size, &boot->hdr.ramdisk_size))
+                return -EFAULT;
+
         /* We start on the first shadow page table, and give it a blank PGD
          * page. */
-        lg->pgdirs[0].gpgdir = pgtable;
+        lg->pgdirs[0].gpgdir = setup_pagetables(lg, mem, initrd_size);
+        if (IS_ERR_VALUE(lg->pgdirs[0].gpgdir))
+                return lg->pgdirs[0].gpgdir;
         lg->pgdirs[0].pgdir = (pgd_t *)get_zeroed_page(GFP_KERNEL);
         if (!lg->pgdirs[0].pgdir)
                 return -ENOMEM;