lguest: the host code

This is the code for the "lg.ko" module, which allows lguest guests to
be launched.

[akpm@linux-foundation.org: update for futex-new-private-futexes]
[akpm@linux-foundation.org: build fix]
[jmorris@namei.org: lguest: use hrtimers]
[akpm@linux-foundation.org: x86_64 build fix]
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andi Kleen <ak@suse.de>
Cc: Eric Dumazet <dada1@cosmosbay.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 159 insertions, 0 deletions

diff --git a/drivers/lguest/switcher.S b/drivers/lguest/switcher.S
new file mode 100644
index 000000000000..eadd4cc299d2
--- /dev/null
+++ b/drivers/lguest/switcher.S
@@ -0,0 +1,159 @@
+/* This code sits at 0xFFC00000 to do the low-level guest<->host switch.
+
+   There is are two pages above us for this CPU (struct lguest_pages).
+   The second page (struct lguest_ro_state) becomes read-only after the
+   context switch.  The first page (the stack for traps) remains writable,
+   but while we're in here, the guest cannot be running.
+*/
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include "lg.h"
+
+.text
+ENTRY(start_switcher_text)
+
+/* %eax points to lguest pages for this CPU.  %ebx contains cr3 value.
+   All normal registers can be clobbered! */
+ENTRY(switch_to_guest)
+        /* Save host segments on host stack. */
+        pushl   %es
+        pushl   %ds
+        pushl   %gs
+        pushl   %fs
+        /* With CONFIG_FRAME_POINTER, gcc doesn't let us clobber this! */
+        pushl   %ebp
+        /* Save host stack. */
+        movl    %esp, LGUEST_PAGES_host_sp(%eax)
+        /* Switch to guest stack: if we get NMI we expect to be there. */
+        movl    %eax, %edx
+        addl    $LGUEST_PAGES_regs, %edx
+        movl    %edx, %esp
+        /* Switch to guest's GDT, IDT. */
+        lgdt    LGUEST_PAGES_guest_gdt_desc(%eax)
+        lidt    LGUEST_PAGES_guest_idt_desc(%eax)
+        /* Switch to guest's TSS while GDT still writable. */
+        movl    $(GDT_ENTRY_TSS*8), %edx
+        ltr     %dx
+        /* Set host's TSS GDT entry to available (clear byte 5 bit 2). */
+        movl    (LGUEST_PAGES_host_gdt_desc+2)(%eax), %edx
+        andb    $0xFD, (GDT_ENTRY_TSS*8 + 5)(%edx)
+        /* Switch to guest page tables: lguest_pages->state now read-only. */
+        movl    %ebx, %cr3
+        /* Restore guest regs */
+        popl    %ebx
+        popl    %ecx
+        popl    %edx
+        popl    %esi
+        popl    %edi
+        popl    %ebp
+        popl    %gs
+        popl    %eax
+        popl    %fs
+        popl    %ds
+        popl    %es
+        /* Skip error code and trap number */
+        addl    $8, %esp
+        iret
+
+#define SWITCH_TO_HOST                                                  \
+        /* Save guest state */                                          \
+        pushl   %es;                                                    \
+        pushl   %ds;                                                    \
+        pushl   %fs;                                                    \
+        pushl   %eax;                                                   \
+        pushl   %gs;                                                    \
+        pushl   %ebp;                                                   \
+        pushl   %edi;                                                   \
+        pushl   %esi;                                                   \
+        pushl   %edx;                                                   \
+        pushl   %ecx;                                                   \
+        pushl   %ebx;                                                   \
+        /* Load lguest ds segment for convenience. */                   \
+        movl    $(LGUEST_DS), %eax;                                     \
+        movl    %eax, %ds;                                              \
+        /* Figure out where we are, based on stack (at top of regs). */ \
+        movl    %esp, %eax;                                             \
+        subl    $LGUEST_PAGES_regs, %eax;                               \
+        /* Put trap number in %ebx before we switch cr3 and lose it. */ \
+        movl    LGUEST_PAGES_regs_trapnum(%eax), %ebx;                  \
+        /* Switch to host page tables (host GDT, IDT and stack are in host   \
+           mem, so need this first) */                                  \
+        movl    LGUEST_PAGES_host_cr3(%eax), %edx;                      \
+        movl    %edx, %cr3;                                             \
+        /* Set guest's TSS to available (clear byte 5 bit 2). */        \
+        andb    $0xFD, (LGUEST_PAGES_guest_gdt+GDT_ENTRY_TSS*8+5)(%eax); \
+        /* Switch to host's GDT & IDT. */                               \
+        lgdt    LGUEST_PAGES_host_gdt_desc(%eax);                       \
+        lidt    LGUEST_PAGES_host_idt_desc(%eax);                       \
+        /* Switch to host's stack. */                                   \
+        movl    LGUEST_PAGES_host_sp(%eax), %esp;                       \
+        /* Switch to host's TSS */                                      \
+        movl    $(GDT_ENTRY_TSS*8), %edx;                               \
+        ltr     %dx;                                                    \
+        popl    %ebp;                                                   \
+        popl    %fs;                                                    \
+        popl    %gs;                                                    \
+        popl    %ds;                                                    \
+        popl    %es
+
+/* Return to run_guest_once. */
+return_to_host:
+        SWITCH_TO_HOST
+        iret
+
+deliver_to_host:
+        SWITCH_TO_HOST
+        /* Decode IDT and jump to hosts' irq handler.  When that does iret, it
+         * will return to run_guest_once.  This is a feature. */
+        movl    (LGUEST_PAGES_host_idt_desc+2)(%eax), %edx
+        leal    (%edx,%ebx,8), %eax
+        movzwl  (%eax),%edx
+        movl    4(%eax), %eax
+        xorw    %ax, %ax
+        orl     %eax, %edx
+        jmp     *%edx
+
+/* Real hardware interrupts are delivered straight to the host.  Others
+   cause us to return to run_guest_once so it can decide what to do.  Note
+   that some of these are overridden by the guest to deliver directly, and
+   never enter here (see load_guest_idt_entry). */
+.macro IRQ_STUB N TARGET
+        .data; .long 1f; .text; 1:
+ /* Make an error number for most traps, which don't have one. */
+ .if (\N <> 8) && (\N < 10 || \N > 14) && (\N <> 17)
+        pushl   $0
+ .endif
+        pushl   $\N
+        jmp     \TARGET
+        ALIGN
+.endm
+
+.macro IRQ_STUBS FIRST LAST TARGET
+ irq=\FIRST
+ .rept \LAST-\FIRST+1
+        IRQ_STUB irq \TARGET
+  irq=irq+1
+ .endr
+.endm
+
+/* We intercept every interrupt, because we may need to switch back to
+ * host.  Unfortunately we can't tell them apart except by entry
+ * point, so we need 256 entry points.
+ */
+.data
+.global default_idt_entries
+default_idt_entries:
+.text
+        IRQ_STUBS 0 1 return_to_host            /* First two traps */
+        IRQ_STUB 2 handle_nmi                   /* NMI */
+        IRQ_STUBS 3 31 return_to_host           /* Rest of traps */
+        IRQ_STUBS 32 127 deliver_to_host        /* Real interrupts */
+        IRQ_STUB 128 return_to_host             /* System call (overridden) */
+        IRQ_STUBS 129 255 deliver_to_host       /* Other real interrupts */
+
+/* We ignore NMI and return. */
+handle_nmi:
+        addl    $8, %esp
+        iret
+
+ENTRY(end_switcher_text)