Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus

* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
  lguest: Fix in/out emulation
  lguest: Fix translation count about wikipedia's cpuid page
  lguest: Fix three simple typos in comments
  lguest: update comments
  lguest: Simplify device initialization.
  lguest: don't rewrite vmcall instructions
  lguest: remove remaining vmcall
  lguest: use a special 1:1 linear pagetable mode until first switch.
  lguest: Do not exit on non-fatal errors

4 files changed, 43 insertions, 30 deletions

diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index b60f2924c413..879fd7d33877 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -61,6 +61,7 @@ hcall(unsigned long call,
 		     : "memory");
 	return call;
 }
+/*:*/
 
 /* Can't use our min() macro here: needs to be a constant */
 #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index c29d631af6fc..395a10e68067 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -63,7 +63,6 @@ void foo(void)
 	BLANK();
 	OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
 	OFFSET(LGUEST_DATA_irq_pending, lguest_data, irq_pending);
-	OFFSET(LGUEST_DATA_pgdir, lguest_data, pgdir);
 
 	BLANK();
 	OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index db832fd65ecb..13ee258442ae 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -71,7 +71,8 @@
 #include <asm/stackprotector.h>
 #include <asm/reboot.h>		/* for struct machine_ops */
 
-/*G:010 Welcome to the Guest!
+/*G:010
+ * Welcome to the Guest!
  *
  * The Guest in our tale is a simple creature: identical to the Host but
  * behaving in simplified but equivalent ways.  In particular, the Guest is the
@@ -190,15 +191,23 @@ static void lazy_hcall4(unsigned long call,
 #endif
 
 /*G:036
- * When lazy mode is turned off reset the per-cpu lazy mode variable and then
- * issue the do-nothing hypercall to flush any stored calls.
-:*/
+ * When lazy mode is turned off, we issue the do-nothing hypercall to
+ * flush any stored calls, and call the generic helper to reset the
+ * per-cpu lazy mode variable.
+ */
 static void lguest_leave_lazy_mmu_mode(void)
 {
 	hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0);
 	paravirt_leave_lazy_mmu();
 }
 
+/*
+ * We also catch the end of context switch; we enter lazy mode for much of
+ * that too, so again we need to flush here.
+ *
+ * (Technically, this is lazy CPU mode, and normally we're in lazy MMU
+ * mode, but unlike Xen, lguest doesn't care about the difference).
+ */
 static void lguest_end_context_switch(struct task_struct *next)
 {
 	hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0);
@@ -391,7 +400,7 @@ static void lguest_load_tr_desc(void)
  * giant ball of hair.  Its entry in the current Intel manual runs to 28 pages.
  *
  * This instruction even it has its own Wikipedia entry.  The Wikipedia entry
- * has been translated into 5 languages.  I am not making this up!
+ * has been translated into 6 languages.  I am not making this up!
  *
  * We could get funky here and identify ourselves as "GenuineLguest", but
  * instead we just use the real "cpuid" instruction.  Then I pretty much turned
@@ -458,7 +467,7 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx,
 	/*
 	 * PAE systems can mark pages as non-executable.  Linux calls this the
 	 * NX bit.  Intel calls it XD (eXecute Disable), AMD EVP (Enhanced
-	 * Virus Protection).  We just switch turn if off here, since we don't
+	 * Virus Protection).  We just switch it off here, since we don't
 	 * support it.
 	 */
 	case 0x80000001:
@@ -520,17 +529,16 @@ static unsigned long lguest_read_cr2(void)
 
 /* See lguest_set_pte() below. */
 static bool cr3_changed = false;
+static unsigned long current_cr3;
 
 /*
  * cr3 is the current toplevel pagetable page: the principle is the same as
- * cr0.  Keep a local copy, and tell the Host when it changes.  The only
- * difference is that our local copy is in lguest_data because the Host needs
- * to set it upon our initial hypercall.
+ * cr0.  Keep a local copy, and tell the Host when it changes.
  */
 static void lguest_write_cr3(unsigned long cr3)
 {
-	lguest_data.pgdir = cr3;
 	lazy_hcall1(LHCALL_NEW_PGTABLE, cr3);
+	current_cr3 = cr3;
 
 	/* These two page tables are simple, linear, and used during boot */
 	if (cr3 != __pa(swapper_pg_dir) && cr3 != __pa(initial_page_table))
@@ -539,7 +547,7 @@ static void lguest_write_cr3(unsigned long cr3)
 
 static unsigned long lguest_read_cr3(void)
 {
-	return lguest_data.pgdir;
+	return current_cr3;
 }
 
 /* cr4 is used to enable and disable PGE, but we don't care. */
@@ -641,7 +649,7 @@ static void lguest_write_cr4(unsigned long val)
 
 /*
  * The Guest calls this after it has set a second-level entry (pte), ie. to map
- * a page into a process' address space.  Wetell the Host the toplevel and
+ * a page into a process' address space.  We tell the Host the toplevel and
  * address this corresponds to.  The Guest uses one pagetable per process, so
  * we need to tell the Host which one we're changing (mm->pgd).
  */
@@ -758,7 +766,7 @@ static void lguest_pmd_clear(pmd_t *pmdp)
 static void lguest_flush_tlb_single(unsigned long addr)
 {
 	/* Simply set it to zero: if it was not, it will fault back in. */
-	lazy_hcall3(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0);
+	lazy_hcall3(LHCALL_SET_PTE, current_cr3, addr, 0);
 }
 
 /*
@@ -1140,7 +1148,7 @@ static struct notifier_block paniced = {
 static __init char *lguest_memory_setup(void)
 {
 	/*
-	 *The Linux bootloader header contains an "e820" memory map: the
+	 * The Linux bootloader header contains an "e820" memory map: the
 	 * Launcher populated the first entry with our memory limit.
 	 */
 	e820_add_region(boot_params.e820_map[0].addr,
diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S
index 4f420c2f2d55..6ddfe4fc23c3 100644
--- a/arch/x86/lguest/i386_head.S
+++ b/arch/x86/lguest/i386_head.S
@@ -6,18 +6,22 @@
 #include <asm/processor-flags.h>
 
 /*G:020
- * Our story starts with the kernel booting into startup_32 in
- * arch/x86/kernel/head_32.S.  It expects a boot header, which is created by
- * the bootloader (the Launcher in our case).
+
+ * Our story starts with the bzImage: booting starts at startup_32 in
+ * arch/x86/boot/compressed/head_32.S.  This merely uncompresses the real
+ * kernel in place and then jumps into it: startup_32 in
+ * arch/x86/kernel/head_32.S.  Both routines expects a boot header in the %esi
+ * register, which is created by the bootloader (the Launcher in our case).
  *
  * The startup_32 function does very little: it clears the uninitialized global
  * C variables which we expect to be zero (ie. BSS) and then copies the boot
- * header and kernel command line somewhere safe.  Finally it checks the
- * 'hardware_subarch' field.  This was introduced in 2.6.24 for lguest and Xen:
- * if it's set to '1' (lguest's assigned number), then it calls us here.
+ * header and kernel command line somewhere safe, and populates some initial
+ * page tables.  Finally it checks the 'hardware_subarch' field.  This was
+ * introduced in 2.6.24 for lguest and Xen: if it's set to '1' (lguest's
+ * assigned number), then it calls us here.
  *
  * WARNING: be very careful here!  We're running at addresses equal to physical
- * addesses (around 0), not above PAGE_OFFSET as most code expectes
+ * addresses (around 0), not above PAGE_OFFSET as most code expects
  * (eg. 0xC0000000).  Jumps are relative, so they're OK, but we can't touch any
  * data without remembering to subtract __PAGE_OFFSET!
  *
@@ -27,13 +31,18 @@
 .section .init.text, "ax", @progbits
 ENTRY(lguest_entry)
 	/*
-	 * We make the "initialization" hypercall now to tell the Host about
-	 * us, and also find out where it put our page tables.
+	 * We make the "initialization" hypercall now to tell the Host where
+	 * our lguest_data struct is.
 	 */
 	movl $LHCALL_LGUEST_INIT, %eax
 	movl $lguest_data - __PAGE_OFFSET, %ebx
 	int $LGUEST_TRAP_ENTRY
 
+	/* Now turn our pagetables on; setup by arch/x86/kernel/head_32.S. */
+	movl $LHCALL_NEW_PGTABLE, %eax
+	movl $(initial_page_table - __PAGE_OFFSET), %ebx
+	int $LGUEST_TRAP_ENTRY
+
 	/* Set up the initial stack so we can run C code. */
 	movl $(init_thread_union+THREAD_SIZE),%esp
 
@@ -96,12 +105,8 @@ send_interrupts:
 	 */
 	pushl %eax
 	movl $LHCALL_SEND_INTERRUPTS, %eax
-	/*
-	 * This is a vmcall instruction (same thing that KVM uses).  Older
-	 * assembler versions might not know the "vmcall" instruction, so we
-	 * create one manually here.
-	 */
-	.byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */
+	/* This is the actual hypercall trap. */
+	int  $LGUEST_TRAP_ENTRY
 	/* Put eax back the way we found it. */
 	popl %eax
 	ret