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: 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

Documentation/virtual/lguest/lguest.c

@@ -51,7 +51,7 @@
 #include <asm/bootparam.h>
 #include "../../../include/linux/lguest_launcher.h"
 /*L:110
- * We can ignore the 42 include files we need for this program, but I do want
+ * We can ignore the 43 include files we need for this program, but I do want
  * to draw attention to the use of kernel-style types.
  *
  * As Linus said, "C is a Spartan language, and so should your naming be."  I
@@ -65,7 +65,6 @@ typedef uint16_t u16;
 typedef uint8_t u8;
 /*:*/
 
-#define PAGE_PRESENT 0x7 	/* Present, RW, Execute */
 #define BRIDGE_PFX "bridge:"
 #ifndef SIOCBRADDIF
 #define SIOCBRADDIF	0x89a2		/* add interface to bridge      */
@@ -861,8 +860,10 @@ static void console_output(struct virtqueue *vq)
 	/* writev can return a partial write, so we loop here. */
 	while (!iov_empty(iov, out)) {
 		int len = writev(STDOUT_FILENO, iov, out);
-		if (len <= 0)
-			err(1, "Write to stdout gave %i", len);
+		if (len <= 0) {
+			warn("Write to stdout gave %i (%d)", len, errno);
+			break;
+		}
 		iov_consume(iov, out, len);
 	}
 
@@ -898,7 +899,7 @@ static void net_output(struct virtqueue *vq)
 	 * same format: what a coincidence!
 	 */
 	if (writev(net_info->tunfd, iov, out) < 0)
-		errx(1, "Write to tun failed?");
+		warnx("Write to tun failed (%d)?", errno);
 
 	/*
 	 * Done with that one; wait_for_vq_desc() will send the interrupt if
@@ -955,7 +956,7 @@ static void net_input(struct virtqueue *vq)
 	 */
 	len = readv(net_info->tunfd, iov, in);
 	if (len <= 0)
-		err(1, "Failed to read from tun.");
+		warn("Failed to read from tun (%d).", errno);
 
 	/*
 	 * Mark that packet buffer as used, but don't interrupt here.  We want
@@ -1093,9 +1094,10 @@ static void update_device_status(struct device *dev)
 		warnx("Device %s configuration FAILED", dev->name);
 		if (dev->running)
 			reset_device(dev);
-	} else if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK) {
-		if (!dev->running)
-			start_device(dev);
+	} else {
+		if (dev->running)
+			err(1, "Device %s features finalized twice", dev->name);
+		start_device(dev);
 	}
 }
 
@@ -1120,25 +1122,11 @@ static void handle_output(unsigned long addr)
 			return;
 		}
 
-		/*
-		 * Devices *can* be used before status is set to DRIVER_OK.
-		 * The original plan was that they would never do this: they
-		 * would always finish setting up their status bits before
-		 * actually touching the virtqueues.  In practice, we allowed
-		 * them to, and they do (eg. the disk probes for partition
-		 * tables as part of initialization).
-		 *
-		 * If we see this, we start the device: once it's running, we
-		 * expect the device to catch all the notifications.
-		 */
+		/* Devices should not be used before features are finalized. */
 		for (vq = i->vq; vq; vq = vq->next) {
 			if (addr != vq->config.pfn*getpagesize())
 				continue;
-			if (i->running)
-				errx(1, "Notification on running %s", i->name);
-			/* This just calls create_thread() for each virtqueue */
-			start_device(i);
-			return;
+			errx(1, "Notification on %s before setup!", i->name);
 		}
 	}
 
@@ -1370,7 +1358,7 @@ static void setup_console(void)
  * --sharenet=<name> option which opens or creates a named pipe.  This can be
  * used to send packets to another guest in a 1:1 manner.
  *
- * More sopisticated is to use one of the tools developed for project like UML
+ * More sophisticated is to use one of the tools developed for project like UML
  * to do networking.
  *
  * Faster is to do virtio bonding in kernel.  Doing this 1:1 would be
@@ -1380,7 +1368,7 @@ static void setup_console(void)
  * multiple inter-guest channels behind one interface, although it would
  * require some manner of hotplugging new virtio channels.
  *
- * Finally, we could implement a virtio network switch in the kernel.
+ * Finally, we could use a virtio network switch in the kernel, ie. vhost.
 :*/
 
 static u32 str2ip(const char *ipaddr)
@@ -2017,10 +2005,7 @@ int main(int argc, char *argv[])
 	/* Tell the entry path not to try to reload segment registers. */
 	boot->hdr.loadflags |= KEEP_SEGMENTS;
 
-	/*
-	 * We tell the kernel to initialize the Guest: this returns the open
-	 * /dev/lguest file descriptor.
-	 */
+	/* We tell the kernel to initialize the Guest. */
 	tell_kernel(start);
 
 	/* Ensure that we terminate if a device-servicing child dies. */

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)

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);

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,

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

drivers/lguest/core.c

@@ -117,7 +117,7 @@ static __init int map_switcher(void)
 
 	/*
 	 * Now the Switcher is mapped at the right address, we can't fail!
-	 * Copy in the compiled-in Switcher code (from <arch>_switcher.S).
+	 * Copy in the compiled-in Switcher code (from x86/switcher_32.S).
 	 */
 	memcpy(switcher_vma->addr, start_switcher_text,
 	       end_switcher_text - start_switcher_text);

drivers/lguest/interrupts_and_traps.c

@@ -375,11 +375,9 @@ static bool direct_trap(unsigned int num)
 	/*
 	 * The Host needs to see page faults (for shadow paging and to save the
 	 * fault address), general protection faults (in/out emulation) and
-	 * device not available (TS handling), invalid opcode fault (kvm hcall),
-	 * and of course, the hypercall trap.
+	 * device not available (TS handling) and of course, the hypercall trap.
 	 */
-	return num != 14 && num != 13 && num != 7 &&
-			num != 6 && num != LGUEST_TRAP_ENTRY;
+	return num != 14 && num != 13 && num != 7 && num != LGUEST_TRAP_ENTRY;
 }
 /*:*/
 
@@ -429,8 +427,8 @@ void pin_stack_pages(struct lg_cpu *cpu)
 
 /*
  * Direct traps also mean that we need to know whenever the Guest wants to use
- * a different kernel stack, so we can change the IDT entries to use that
- * stack.  The IDT entries expect a virtual address, so unlike most addresses
+ * a different kernel stack, so we can change the guest TSS to use that
+ * stack.  The TSS entries expect a virtual address, so unlike most addresses
  * the Guest gives us, the "esp" (stack pointer) value here is virtual, not
  * physical.
  *

drivers/lguest/lg.h

@@ -59,6 +59,8 @@ struct lg_cpu {
 
 	struct lguest_pages *last_pages;
 
+	/* Initialization mode: linear map everything. */
+	bool linear_pages;
 	int cpu_pgd; /* Which pgd this cpu is currently using */
 
 	/* If a hypercall was asked for, this points to the arguments. */