lguest: the guest code

lguest is a simple hypervisor for Linux on Linux.  Unlike kvm it doesn't need
VT/SVM hardware.  Unlike Xen it's simply "modprobe and go".  Unlike both, it's
5000 lines and self-contained.

Performance is ok, but not great (-30% on kernel compile).  But given its
hackability, I expect this to improve, along with the paravirt_ops code which
it supplies a complete example for.  There's also a 64-bit version being
worked on and other craziness.

But most of all, lguest is awesome fun!  Too much of the kernel is a big ball
of hair.  lguest is simple enough to dive into and hack, plus has some warts
which scream "fork me!".

This patch:

This is the code and headers required to make an i386 kernel an lguest guest.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andi Kleen <ak@suse.de>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 133 insertions, 0 deletions

diff --git a/include/linux/lguest.h b/include/linux/lguest.h
new file mode 100644
index 0000000..f30c04f
--- /dev/null
+++ b/include/linux/lguest.h
@@ -0,0 +1,85 @@
+/* Things the lguest guest needs to know.  Note: like all lguest interfaces,
+ * this is subject to wild and random change between versions. */
+#ifndef _ASM_LGUEST_H
+#define _ASM_LGUEST_H
+
+/* These are randomly chosen numbers which indicate we're an lguest at boot */
+#define LGUEST_MAGIC_EBP 0x4C687970
+#define LGUEST_MAGIC_EDI 0x652D4D65
+#define LGUEST_MAGIC_ESI 0xFFFFFFFF
+
+#ifndef __ASSEMBLY__
+#include <asm/irq.h>
+
+#define LHCALL_FLUSH_ASYNC	0
+#define LHCALL_LGUEST_INIT	1
+#define LHCALL_CRASH		2
+#define LHCALL_LOAD_GDT		3
+#define LHCALL_NEW_PGTABLE	4
+#define LHCALL_FLUSH_TLB	5
+#define LHCALL_LOAD_IDT_ENTRY	6
+#define LHCALL_SET_STACK	7
+#define LHCALL_TS		8
+#define LHCALL_TIMER_READ	9
+#define LHCALL_HALT		10
+#define LHCALL_GET_WALLCLOCK	11
+#define LHCALL_BIND_DMA		12
+#define LHCALL_SEND_DMA		13
+#define LHCALL_SET_PTE		14
+#define LHCALL_SET_PMD		15
+#define LHCALL_LOAD_TLS		16
+
+#define LGUEST_TRAP_ENTRY 0x1F
+
+static inline unsigned long
+hcall(unsigned long call,
+      unsigned long arg1, unsigned long arg2, unsigned long arg3)
+{
+	asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY)
+		     : "=a"(call)
+		     : "a"(call), "d"(arg1), "b"(arg2), "c"(arg3)
+		     : "memory");
+	return call;
+}
+
+void async_hcall(unsigned long call,
+		 unsigned long arg1, unsigned long arg2, unsigned long arg3);
+
+/* Can't use our min() macro here: needs to be a constant */
+#define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
+
+#define LHCALL_RING_SIZE 64
+struct hcall_ring
+{
+	u32 eax, edx, ebx, ecx;
+};
+
+/* All the good stuff happens here: guest registers it with LGUEST_INIT */
+struct lguest_data
+{
+/* Fields which change during running: */
+	/* 512 == enabled (same as eflags) */
+	unsigned int irq_enabled;
+	/* Interrupts blocked by guest. */
+	DECLARE_BITMAP(blocked_interrupts, LGUEST_IRQS);
+
+	/* Virtual address of page fault. */
+	unsigned long cr2;
+
+	/* Async hypercall ring.  0xFF == done, 0 == pending. */
+	u8 hcall_status[LHCALL_RING_SIZE];
+	struct hcall_ring hcalls[LHCALL_RING_SIZE];
+
+/* Fields initialized by the hypervisor at boot: */
+	/* Memory not to try to access */
+	unsigned long reserve_mem;
+	/* ID of this guest (used by network driver to set ethernet address) */
+	u16 guestid;
+
+/* Fields initialized by the guest at boot: */
+	/* Instruction range to suppress interrupts even if enabled */
+	unsigned long noirq_start, noirq_end;
+};
+extern struct lguest_data lguest_data;
+#endif /* __ASSEMBLY__ */
+#endif	/* _ASM_LGUEST_H */
diff --git a/include/linux/lguest_bus.h b/include/linux/lguest_bus.h
new file mode 100644
index 0000000..c9b4e05f
--- /dev/null
+++ b/include/linux/lguest_bus.h
@@ -0,0 +1,48 @@
+#ifndef _ASM_LGUEST_DEVICE_H
+#define _ASM_LGUEST_DEVICE_H
+/* Everything you need to know about lguest devices. */
+#include <linux/device.h>
+#include <linux/lguest.h>
+#include <linux/lguest_launcher.h>
+
+struct lguest_device {
+	/* Unique busid, and index into lguest_page->devices[] */
+	unsigned int index;
+
+	struct device dev;
+
+	/* Driver can hang data off here. */
+	void *private;
+};
+
+/* By convention, each device can use irq index+1 if it wants to. */
+static inline int lgdev_irq(const struct lguest_device *dev)
+{
+	return dev->index + 1;
+}
+
+/* dma args must not be vmalloced! */
+void lguest_send_dma(unsigned long key, struct lguest_dma *dma);
+int lguest_bind_dma(unsigned long key, struct lguest_dma *dmas,
+		    unsigned int num, u8 irq);
+void lguest_unbind_dma(unsigned long key, struct lguest_dma *dmas);
+
+/* Map the virtual device space */
+void *lguest_map(unsigned long phys_addr, unsigned long pages);
+void lguest_unmap(void *);
+
+struct lguest_driver {
+	const char *name;
+	struct module *owner;
+	u16 device_type;
+	int (*probe)(struct lguest_device *dev);
+	void (*remove)(struct lguest_device *dev);
+
+	struct device_driver drv;
+};
+
+extern int register_lguest_driver(struct lguest_driver *drv);
+extern void unregister_lguest_driver(struct lguest_driver *drv);
+
+extern struct lguest_device_desc *lguest_devices; /* Just past max_pfn */
+#endif /* _ASM_LGUEST_DEVICE_H */