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: (27 commits)
  lguest: use __PAGE_KERNEL instead of _PAGE_KERNEL
  lguest: Use explicit includes rateher than indirect
  lguest: get rid of lg variable assignments
  lguest: change gpte_addr header
  lguest: move changed bitmap to lg_cpu
  lguest: move last_pages to lg_cpu
  lguest: change last_guest to last_cpu
  lguest: change spte_addr header
  lguest: per-vcpu lguest pgdir management
  lguest: make pending notifications per-vcpu
  lguest: makes special fields be per-vcpu
  lguest: per-vcpu lguest task management
  lguest: replace lguest_arch with lg_cpu_arch.
  lguest: make registers per-vcpu
  lguest: make emulate_insn receive a vcpu struct.
  lguest: map_switcher_in_guest() per-vcpu
  lguest: per-vcpu interrupt processing.
  lguest: per-vcpu lguest timers
  lguest: make hypercalls use the vcpu struct
  lguest: make write() operation smp aware
  ...

Manual conflict resolved (maybe even correctly, who knows) in
drivers/lguest/x86/core.c

Documentation/lguest/lguest.c

@@ -79,6 +79,9 @@ static void *guest_base;
 /* The maximum guest physical address allowed, and maximum possible. */
 static unsigned long guest_limit, guest_max;
 
+/* a per-cpu variable indicating whose vcpu is currently running */
+static unsigned int __thread cpu_id;
+
 /* This is our list of devices. */
 struct device_list
 {
@@ -153,6 +156,9 @@ struct virtqueue
 	void (*handle_output)(int fd, struct virtqueue *me);
 };
 
+/* Remember the arguments to the program so we can "reboot" */
+static char **main_args;
+
 /* Since guest is UP and we don't run at the same time, we don't need barriers.
  * But I include them in the code in case others copy it. */
 #define wmb()
@@ -554,7 +560,7 @@ static void wake_parent(int pipefd, int lguest_fd)
 			else
 				FD_CLR(-fd - 1, &devices.infds);
 		} else /* Send LHREQ_BREAK command. */
-			write(lguest_fd, args, sizeof(args));
+			pwrite(lguest_fd, args, sizeof(args), cpu_id);
 	}
 }
 
@@ -1489,7 +1495,9 @@ static void setup_block_file(const char *filename)
 
 	/* Create stack for thread and run it */
 	stack = malloc(32768);
-	if (clone(io_thread, stack + 32768, CLONE_VM, dev) == -1)
+	/* SIGCHLD - We dont "wait" for our cloned thread, so prevent it from
+	 * becoming a zombie. */
+	if (clone(io_thread, stack + 32768,  CLONE_VM | SIGCHLD, dev) == -1)
 		err(1, "Creating clone");
 
 	/* We don't need to keep the I/O thread's end of the pipes open. */
@@ -1499,7 +1507,21 @@ static void setup_block_file(const char *filename)
 	verbose("device %u: virtblock %llu sectors\n",
 		devices.device_num, cap);
 }
-/* That's the end of device setup. */
+/* That's the end of device setup. :*/
+
+/* Reboot */
+static void __attribute__((noreturn)) restart_guest(void)
+{
+	unsigned int i;
+
+	/* Closing pipes causes the waker thread and io_threads to die, and
+	 * closing /dev/lguest cleans up the Guest.  Since we don't track all
+	 * open fds, we simply close everything beyond stderr. */
+	for (i = 3; i < FD_SETSIZE; i++)
+		close(i);
+	execv(main_args[0], main_args);
+	err(1, "Could not exec %s", main_args[0]);
+}
 
 /*L:220 Finally we reach the core of the Launcher, which runs the Guest, serves
  * its input and output, and finally, lays it to rest. */
@@ -1511,7 +1533,8 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd)
 		int readval;
 
 		/* We read from the /dev/lguest device to run the Guest. */
-		readval = read(lguest_fd, &notify_addr, sizeof(notify_addr));
+		readval = pread(lguest_fd, &notify_addr,
+				sizeof(notify_addr), cpu_id);
 
 		/* One unsigned long means the Guest did HCALL_NOTIFY */
 		if (readval == sizeof(notify_addr)) {
@@ -1521,16 +1544,23 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd)
 		/* ENOENT means the Guest died.  Reading tells us why. */
 		} else if (errno == ENOENT) {
 			char reason[1024] = { 0 };
-			read(lguest_fd, reason, sizeof(reason)-1);
+			pread(lguest_fd, reason, sizeof(reason)-1, cpu_id);
 			errx(1, "%s", reason);
+		/* ERESTART means that we need to reboot the guest */
+		} else if (errno == ERESTART) {
+			restart_guest();
 		/* EAGAIN means the Waker wanted us to look at some input.
 		 * Anything else means a bug or incompatible change. */
 		} else if (errno != EAGAIN)
 			err(1, "Running guest failed");
 
+		/* Only service input on thread for CPU 0. */
+		if (cpu_id != 0)
+			continue;
+
 		/* Service input, then unset the BREAK to release the Waker. */
 		handle_input(lguest_fd);
-		if (write(lguest_fd, args, sizeof(args)) < 0)
+		if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
 			err(1, "Resetting break");
 	}
 }
@@ -1571,6 +1601,12 @@ int main(int argc, char *argv[])
 	/* If they specify an initrd file to load. */
 	const char *initrd_name = NULL;
 
+	/* Save the args: we "reboot" by execing ourselves again. */
+	main_args = argv;
+	/* We don't "wait" for the children, so prevent them from becoming
+	 * zombies. */
+	signal(SIGCHLD, SIG_IGN);
+
 	/* First we initialize the device list.  Since console and network
 	 * device receive input from a file descriptor, we keep an fdset
 	 * (infds) and the maximum fd number (max_infd) with the head of the
@@ -1582,6 +1618,7 @@ int main(int argc, char *argv[])
 	devices.lastdev = &devices.dev;
 	devices.next_irq = 1;
 
+	cpu_id = 0;
 	/* We need to know how much memory so we can set up the device
 	 * descriptor and memory pages for the devices as we parse the command
 	 * line.  So we quickly look through the arguments to find the amount

arch/x86/lguest/boot.c

@@ -67,6 +67,7 @@
 #include <asm/mce.h>
 #include <asm/io.h>
 #include <asm/i387.h>
+#include <asm/reboot.h>		/* for struct machine_ops */
 
 /*G:010 Welcome to the Guest!
  *
@@ -813,7 +814,7 @@ static void lguest_safe_halt(void)
  * rather than virtual addresses, so we use __pa() here. */
 static void lguest_power_off(void)
 {
-	hcall(LHCALL_CRASH, __pa("Power down"), 0, 0);
+	hcall(LHCALL_SHUTDOWN, __pa("Power down"), LGUEST_SHUTDOWN_POWEROFF, 0);
 }
 
 /*
@@ -823,7 +824,7 @@ static void lguest_power_off(void)
  */
 static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p)
 {
-	hcall(LHCALL_CRASH, __pa(p), 0, 0);
+	hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0);
 	/* The hcall won't return, but to keep gcc happy, we're "done". */
 	return NOTIFY_DONE;
 }
@@ -927,6 +928,11 @@ static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf,
 	return insn_len;
 }
 
+static void lguest_restart(char *reason)
+{
+	hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0);
+}
+
 /*G:030 Once we get to lguest_init(), we know we're a Guest.  The pv_ops
  * structures in the kernel provide points for (almost) every routine we have
  * to override to avoid privileged instructions. */
@@ -1060,6 +1066,7 @@ __init void lguest_init(void)
 	 * the Guest routine to power off. */
 	pm_power_off = lguest_power_off;
 
+	machine_ops.restart = lguest_restart;
 	/* Now we're set up, call start_kernel() in init/main.c and we proceed
 	 * to boot as normal.  It never returns. */
 	start_kernel();

drivers/Makefile

@@ -72,7 +72,7 @@ obj-$(CONFIG_ISDN)		+= isdn/
 obj-$(CONFIG_EDAC)		+= edac/
 obj-$(CONFIG_MCA)		+= mca/
 obj-$(CONFIG_EISA)		+= eisa/
-obj-$(CONFIG_LGUEST_GUEST)	+= lguest/
+obj-y				+= lguest/
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq/
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle/
 obj-$(CONFIG_MMC)		+= mmc/

drivers/lguest/core.c

@@ -151,57 +151,57 @@ int lguest_address_ok(const struct lguest *lg,
 /* This routine copies memory from the Guest.  Here we can see how useful the
  * kill_lguest() routine we met in the Launcher can be: we return a random
  * value (all zeroes) instead of needing to return an error. */
-void __lgread(struct lguest *lg, void *b, unsigned long addr, unsigned bytes)
+void __lgread(struct lg_cpu *cpu, void *b, unsigned long addr, unsigned bytes)
 {
-	if (!lguest_address_ok(lg, addr, bytes)
-	    || copy_from_user(b, lg->mem_base + addr, bytes) != 0) {
+	if (!lguest_address_ok(cpu->lg, addr, bytes)
+	    || copy_from_user(b, cpu->lg->mem_base + addr, bytes) != 0) {
 		/* copy_from_user should do this, but as we rely on it... */
 		memset(b, 0, bytes);
-		kill_guest(lg, "bad read address %#lx len %u", addr, bytes);
+		kill_guest(cpu, "bad read address %#lx len %u", addr, bytes);
 	}
 }
 
 /* This is the write (copy into guest) version. */
-void __lgwrite(struct lguest *lg, unsigned long addr, const void *b,
+void __lgwrite(struct lg_cpu *cpu, unsigned long addr, const void *b,
 	       unsigned bytes)
 {
-	if (!lguest_address_ok(lg, addr, bytes)
-	    || copy_to_user(lg->mem_base + addr, b, bytes) != 0)
-		kill_guest(lg, "bad write address %#lx len %u", addr, bytes);
+	if (!lguest_address_ok(cpu->lg, addr, bytes)
+	    || copy_to_user(cpu->lg->mem_base + addr, b, bytes) != 0)
+		kill_guest(cpu, "bad write address %#lx len %u", addr, bytes);
 }
 /*:*/
 
 /*H:030 Let's jump straight to the the main loop which runs the Guest.
  * Remember, this is called by the Launcher reading /dev/lguest, and we keep
  * going around and around until something interesting happens. */
-int run_guest(struct lguest *lg, unsigned long __user *user)
+int run_guest(struct lg_cpu *cpu, unsigned long __user *user)
 {
 	/* We stop running once the Guest is dead. */
-	while (!lg->dead) {
+	while (!cpu->lg->dead) {
 		/* First we run any hypercalls the Guest wants done. */
-		if (lg->hcall)
-			do_hypercalls(lg);
+		if (cpu->hcall)
+			do_hypercalls(cpu);
 
 		/* It's possible the Guest did a NOTIFY hypercall to the
 		 * Launcher, in which case we return from the read() now. */
-		if (lg->pending_notify) {
-			if (put_user(lg->pending_notify, user))
+		if (cpu->pending_notify) {
+			if (put_user(cpu->pending_notify, user))
 				return -EFAULT;
-			return sizeof(lg->pending_notify);
+			return sizeof(cpu->pending_notify);
 		}
 
 		/* Check for signals */
 		if (signal_pending(current))
 			return -ERESTARTSYS;
 
 		/* If Waker set break_out, return to Launcher. */
-		if (lg->break_out)
+		if (cpu->break_out)
 			return -EAGAIN;
 
 		/* Check if there are any interrupts which can be delivered
 		 * now: if so, this sets up the hander to be executed when we
 		 * next run the Guest. */
-		maybe_do_interrupt(lg);
+		maybe_do_interrupt(cpu);
 
 		/* All long-lived kernel loops need to check with this horrible
 		 * thing called the freezer.  If the Host is trying to suspend,
@@ -210,12 +210,12 @@ int run_guest(struct lguest *lg, unsigned long __user *user)
 
 		/* Just make absolutely sure the Guest is still alive.  One of
 		 * those hypercalls could have been fatal, for example. */
-		if (lg->dead)
+		if (cpu->lg->dead)
 			break;
 
 		/* If the Guest asked to be stopped, we sleep.  The Guest's
 		 * clock timer or LHCALL_BREAK from the Waker will wake us. */
-		if (lg->halted) {
+		if (cpu->halted) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			schedule();
 			continue;
@@ -226,15 +226,17 @@ int run_guest(struct lguest *lg, unsigned long __user *user)
 		local_irq_disable();
 
 		/* Actually run the Guest until something happens. */
-		lguest_arch_run_guest(lg);
+		lguest_arch_run_guest(cpu);
 
 		/* Now we're ready to be interrupted or moved to other CPUs */
 		local_irq_enable();
 
 		/* Now we deal with whatever happened to the Guest. */
-		lguest_arch_handle_trap(lg);
+		lguest_arch_handle_trap(cpu);
 	}
 
+	if (cpu->lg->dead == ERR_PTR(-ERESTART))
+		return -ERESTART;
 	/* The Guest is dead => "No such file or directory" */
 	return -ENOENT;
 }
@@ -253,7 +255,7 @@ static int __init init(void)
 
 	/* Lguest can't run under Xen, VMI or itself.  It does Tricky Stuff. */
 	if (paravirt_enabled()) {
-		printk("lguest is afraid of %s\n", pv_info.name);
+		printk("lguest is afraid of being a guest\n");
 		return -EPERM;
 	}