Merge branch 'linus' into x86/nmitip-x86-nmi-2008-06-16_09.20_Mon

Conflicts:

	arch/x86/kernel/nmi_32.c

11 files changed, 174 insertions, 87 deletions

diff --git a/arch/um/os-Linux/drivers/ethertap_user.c b/arch/um/os-Linux/drivers/ethertap_user.c
index 6fb0b174f538..cc72cb2c1af6 100644
--- a/arch/um/os-Linux/drivers/ethertap_user.c
+++ b/arch/um/os-Linux/drivers/ethertap_user.c
@@ -52,7 +52,7 @@ static void etap_change(int op, unsigned char *addr, unsigned char *netmask,
 		return;
 	}
 
-	output = kmalloc(UM_KERN_PAGE_SIZE, UM_GFP_KERNEL);
+	output = uml_kmalloc(UM_KERN_PAGE_SIZE, UM_GFP_KERNEL);
 	if (output == NULL)
 		printk(UM_KERN_ERR "etap_change : Failed to allocate output "
 		       "buffer\n");
@@ -165,7 +165,7 @@ static int etap_open(void *data)
 	err = etap_tramp(pri->dev_name, pri->gate_addr, control_fds[0],
 			 control_fds[1], data_fds[0], data_fds[1]);
 	output_len = UM_KERN_PAGE_SIZE;
-	output = kmalloc(output_len, UM_GFP_KERNEL);
+	output = uml_kmalloc(output_len, UM_GFP_KERNEL);
 	read_output(control_fds[0], output, output_len);
 
 	if (output == NULL)
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index f25c29a12d00..30860b89ec58 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -7,6 +7,7 @@
 #include <unistd.h>
 #include <errno.h>
 #include <sched.h>
+#include <linux/limits.h>
 #include <sys/socket.h>
 #include <sys/wait.h>
 #include "kern_constants.h"
@@ -71,8 +72,8 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv)
 	data.pre_data = pre_data;
 	data.argv = argv;
 	data.fd = fds[1];
-	data.buf = __cant_sleep() ? kmalloc(PATH_MAX, UM_GFP_ATOMIC) :
-					kmalloc(PATH_MAX, UM_GFP_KERNEL);
+	data.buf = __cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) :
+					uml_kmalloc(PATH_MAX, UM_GFP_KERNEL);
 	pid = clone(helper_child, (void *) sp, CLONE_VM, &data);
 	if (pid < 0) {
 		ret = -errno;
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index abb9b0ffd960..eee69b9f52c9 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -199,7 +199,7 @@ void *__wrap_malloc(int size)
 		return __real_malloc(size);
 	else if (size <= UM_KERN_PAGE_SIZE)
 		/* finding contiguous pages can be hard*/
-		ret = kmalloc(size, UM_GFP_KERNEL);
+		ret = uml_kmalloc(size, UM_GFP_KERNEL);
 	else ret = vmalloc(size);
 
 	/*
diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c
index abf47a7c4abd..eb8f2e4be192 100644
--- a/arch/um/os-Linux/sigio.c
+++ b/arch/um/os-Linux/sigio.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright (C) 2002 - 2008 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  * Licensed under the GPL
  */
 
@@ -15,6 +15,7 @@
 #include "kern_util.h"
 #include "init.h"
 #include "os.h"
+#include "process.h"
 #include "sigio.h"
 #include "um_malloc.h"
 #include "user.h"
@@ -109,7 +110,7 @@ static int need_poll(struct pollfds *polls, int n)
 	if (n <= polls->size)
 		return 0;
 
-	new = kmalloc(n * sizeof(struct pollfd), UM_GFP_ATOMIC);
+	new = uml_kmalloc(n * sizeof(struct pollfd), UM_GFP_ATOMIC);
 	if (new == NULL) {
 		printk(UM_KERN_ERR "need_poll : failed to allocate new "
 		       "pollfds\n");
@@ -243,7 +244,7 @@ static struct pollfd *setup_initial_poll(int fd)
 {
 	struct pollfd *p;
 
-	p = kmalloc(sizeof(struct pollfd), UM_GFP_KERNEL);
+	p = uml_kmalloc(sizeof(struct pollfd), UM_GFP_KERNEL);
 	if (p == NULL) {
 		printk(UM_KERN_ERR "setup_initial_poll : failed to allocate "
 		       "poll\n");
@@ -338,20 +339,10 @@ out_close1:
 	close(l_write_sigio_fds[1]);
 }
 
-/* Changed during early boot */
-static int pty_output_sigio = 0;
-static int pty_close_sigio = 0;
-
-void maybe_sigio_broken(int fd, int read)
+void sigio_broken(int fd, int read)
 {
 	int err;
 
-	if (!isatty(fd))
-		return;
-
-	if ((read || pty_output_sigio) && (!read || pty_close_sigio))
-		return;
-
 	write_sigio_workaround();
 
 	sigio_lock();
@@ -370,6 +361,21 @@ out:
 	sigio_unlock();
 }
 
+/* Changed during early boot */
+static int pty_output_sigio;
+static int pty_close_sigio;
+
+void maybe_sigio_broken(int fd, int read)
+{
+	if (!isatty(fd))
+		return;
+
+	if ((read || pty_output_sigio) && (!read || pty_close_sigio))
+		return;
+
+	sigio_broken(fd, read);
+}
+
 static void sigio_cleanup(void)
 {
 	if (write_sigio_pid == -1)
@@ -383,7 +389,7 @@ static void sigio_cleanup(void)
 __uml_exitcall(sigio_cleanup);
 
 /* Used as a flag during SIGIO testing early in boot */
-static volatile int got_sigio = 0;
+static int got_sigio;
 
 static void __init handler(int sig)
 {
@@ -498,7 +504,8 @@ static void tty_output(int master, int slave)
 	if (errno != EAGAIN)
 		printk(UM_KERN_ERR "tty_output : write failed, errno = %d\n",
 		       errno);
-	while (((n = read(slave, buf, sizeof(buf))) > 0) && !got_sigio)
+	while (((n = read(slave, buf, sizeof(buf))) > 0) &&
+	       !({ barrier(); got_sigio; }))
 		;
 
 	if (got_sigio) {
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 3f1694b134cb..5aade6027e40 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -12,6 +12,7 @@
 #include "as-layout.h"
 #include "kern_util.h"
 #include "os.h"
+#include "process.h"
 #include "sysdep/barrier.h"
 #include "sysdep/sigcontext.h"
 #include "user.h"
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 1e8cba6550a9..172ad8f72e12 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -55,7 +55,7 @@ static int ptrace_dump_regs(int pid)
  * Signals that are OK to receive in the stub - we'll just continue it.
  * SIGWINCH will happen when UML is inside a detached screen.
  */
-#define STUB_SIG_MASK (1 << SIGVTALRM)
+#define STUB_SIG_MASK ((1 << SIGVTALRM) | (1 << SIGWINCH))
 
 /* Signals that the stub will finish with - anything else is an error */
 #define STUB_DONE_MASK (1 << SIGTRAP)
@@ -442,7 +442,7 @@ void userspace(struct uml_pt_regs *regs)
 				unblock_signals();
 				break;
 			default:
-			        printk(UM_KERN_ERR "userspace - child stopped "
+				printk(UM_KERN_ERR "userspace - child stopped "
 				       "with signal %d\n", sig);
 				fatal_sigsegv();
 			}
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index 997d01944f91..183db26d01bf 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -23,6 +23,7 @@
 #include "mem_user.h"
 #include "ptrace_user.h"
 #include "registers.h"
+#include "skas.h"
 #include "skas_ptrace.h"
 
 static void ptrace_child(void)
@@ -120,8 +121,10 @@ static int stop_ptraced_child(int pid, int exitcode, int mustexit)
 {
 	int status, n, ret = 0;
 
-	if (ptrace(PTRACE_CONT, pid, 0, 0) < 0)
-		fatal_perror("stop_ptraced_child : ptrace failed");
+	if (ptrace(PTRACE_CONT, pid, 0, 0) < 0) {
+		perror("stop_ptraced_child : ptrace failed");
+		return -1;
+	}
 	CATCH_EINTR(n = waitpid(pid, &status, 0));
 	if (!WIFEXITED(status) || (WEXITSTATUS(status) != exitcode)) {
 		int exit_with = WEXITSTATUS(status);
@@ -140,14 +143,27 @@ static int stop_ptraced_child(int pid, int exitcode, int mustexit)
 }
 
 /* Changed only during early boot */
-int ptrace_faultinfo = 1;
-int ptrace_ldt = 1;
-int proc_mm = 1;
-int skas_needs_stub = 0;
+int ptrace_faultinfo;
+static int disable_ptrace_faultinfo;
+
+int ptrace_ldt;
+static int disable_ptrace_ldt;
+
+int proc_mm;
+static int disable_proc_mm;
+
+int have_switch_mm;
+static int disable_switch_mm;
+
+int skas_needs_stub;
 
 static int __init skas0_cmd_param(char *str, int* add)
 {
-	ptrace_faultinfo = proc_mm = 0;
+	disable_ptrace_faultinfo = 1;
+	disable_ptrace_ldt = 1;
+	disable_proc_mm = 1;
+	disable_switch_mm = 1;
+
 	return 0;
 }
 
@@ -157,15 +173,12 @@ static int __init mode_skas0_cmd_param(char *str, int* add)
 	__attribute__((alias("skas0_cmd_param")));
 
 __uml_setup("skas0", skas0_cmd_param,
-		"skas0\n"
-		"    Disables SKAS3 usage, so that SKAS0 is used, unless \n"
-	        "    you specify mode=tt.\n\n");
+"skas0\n"
+"    Disables SKAS3 and SKAS4 usage, so that SKAS0 is used\n\n");
 
 __uml_setup("mode=skas0", mode_skas0_cmd_param,
-		"mode=skas0\n"
-		"    Disables SKAS3 usage, so that SKAS0 is used, unless you \n"
-		"    specify mode=tt. Note that this was recently added - on \n"
-		"    older kernels you must use simply \"skas0\".\n\n");
+"mode=skas0\n"
+"    Disables SKAS3 and SKAS4 usage, so that SKAS0 is used.\n\n");
 
 /* Changed only during early boot */
 static int force_sysemu_disabled = 0;
@@ -201,7 +214,7 @@ static void __init check_sysemu(void)
 	if (n < 0)
 		fatal_perror("check_sysemu : wait failed");
 	if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGTRAP))
-		fatal("check_sysemu : expected SIGTRAP, got status = %d",
+		fatal("check_sysemu : expected SIGTRAP, got status = %d\n",
 		      status);
 
 	if (ptrace(PTRACE_GETREGS, pid, 0, regs) < 0)
@@ -243,9 +256,11 @@ static void __init check_sysemu(void)
 
 		if (WIFSTOPPED(status) &&
 		    (WSTOPSIG(status) == (SIGTRAP|0x80))) {
-			if (!count)
-				fatal("check_ptrace : SYSEMU_SINGLESTEP "
-				      "doesn't singlestep");
+			if (!count) {
+				non_fatal("check_ptrace : SYSEMU_SINGLESTEP "
+					  "doesn't singlestep");
+				goto fail;
+			}
 			n = ptrace(PTRACE_POKEUSR, pid, PT_SYSCALL_RET_OFFSET,
 				   os_getpid());
 			if (n < 0)
@@ -255,9 +270,12 @@ static void __init check_sysemu(void)
 		}
 		else if (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGTRAP))
 			count++;
-		else
-			fatal("check_ptrace : expected SIGTRAP or "
-			      "(SIGTRAP | 0x80), got status = %d", status);
+		else {
+			non_fatal("check_ptrace : expected SIGTRAP or "
+				  "(SIGTRAP | 0x80), got status = %d\n",
+				  status);
+			goto fail;
+		}
 	}
 	if (stop_ptraced_child(pid, 0, 0) < 0)
 		goto fail_stopped;
@@ -360,7 +378,7 @@ void __init os_early_checks(void)
 
 static int __init noprocmm_cmd_param(char *str, int* add)
 {
-	proc_mm = 0;
+	disable_proc_mm = 1;
 	return 0;
 }
 
@@ -372,7 +390,7 @@ __uml_setup("noprocmm", noprocmm_cmd_param,
 
 static int __init noptracefaultinfo_cmd_param(char *str, int* add)
 {
-	ptrace_faultinfo = 0;
+	disable_ptrace_faultinfo = 1;
 	return 0;
 }
 
@@ -384,7 +402,7 @@ __uml_setup("noptracefaultinfo", noptracefaultinfo_cmd_param,
 
 static int __init noptraceldt_cmd_param(char *str, int* add)
 {
-	ptrace_ldt = 0;
+	disable_ptrace_ldt = 1;
 	return 0;
 }
 
@@ -404,17 +422,15 @@ static inline void check_skas3_ptrace_faultinfo(void)
 
 	n = ptrace(PTRACE_FAULTINFO, pid, 0, &fi);
 	if (n < 0) {
-		ptrace_faultinfo = 0;
 		if (errno == EIO)
 			non_fatal("not found\n");
 		else
 			perror("not found");
-	}
+	} else if (disable_ptrace_faultinfo)
+		non_fatal("found but disabled on command line\n");
 	else {
-		if (!ptrace_faultinfo)
-			non_fatal("found but disabled on command line\n");
-		else
-			non_fatal("found\n");
+		ptrace_faultinfo = 1;
+		non_fatal("found\n");
 	}
 
 	stop_ptraced_child(pid, 1, 1);
@@ -437,38 +453,30 @@ static inline void check_skas3_ptrace_ldt(void)
 	if (n < 0) {
 		if (errno == EIO)
 			non_fatal("not found\n");
-		else {
+		else
 			perror("not found");
-		}
-		ptrace_ldt = 0;
-	}
+	} else if (disable_ptrace_ldt)
+		non_fatal("found, but use is disabled\n");
 	else {
-		if (ptrace_ldt)
-			non_fatal("found\n");
-		else
-			non_fatal("found, but use is disabled\n");
+		ptrace_ldt = 1;
+		non_fatal("found\n");
 	}
 
 	stop_ptraced_child(pid, 1, 1);
-#else
-	/* PTRACE_LDT might be disabled via cmdline option.
-	 * We want to override this, else we might use the stub
-	 * without real need
-	 */
-	ptrace_ldt = 1;
 #endif
 }
 
 static inline void check_skas3_proc_mm(void)
 {
 	non_fatal("  - /proc/mm...");
-	if (access("/proc/mm", W_OK) < 0) {
-		proc_mm = 0;
+	if (access("/proc/mm", W_OK) < 0)
 		perror("not found");
-	}
-	else if (!proc_mm)
+	else if (disable_proc_mm)
 		non_fatal("found but disabled on command line\n");
-	else non_fatal("found\n");
+	else {
+		proc_mm = 1;
+		non_fatal("found\n");
+	}
 }
 
 void can_do_skas(void)
diff --git a/arch/um/os-Linux/sys-i386/registers.c b/arch/um/os-Linux/sys-i386/registers.c
index b613473b3ec1..229f7a53d8da 100644
--- a/arch/um/os-Linux/sys-i386/registers.c
+++ b/arch/um/os-Linux/sys-i386/registers.c
@@ -5,6 +5,8 @@
  */
 
 #include <errno.h>
+#include <sys/ptrace.h>
+#include <sys/user.h>
 #include "kern_constants.h"
 #include "longjmp.h"
 #include "user.h"
@@ -74,10 +76,10 @@ int put_fp_registers(int pid, unsigned long *regs)
 
 void arch_init_registers(int pid)
 {
-	unsigned long fpx_regs[HOST_XFP_SIZE];
+	struct user_fpxregs_struct fpx_regs;
 	int err;
 
-	err = ptrace(PTRACE_GETFPXREGS, pid, 0, fpx_regs);
+	err = ptrace(PTRACE_GETFPXREGS, pid, 0, &fpx_regs);
 	if (!err)
 		return;
 
diff --git a/arch/um/os-Linux/sys-i386/task_size.c b/arch/um/os-Linux/sys-i386/task_size.c
index ccb49b0aff59..be04c1e183bf 100644
--- a/arch/um/os-Linux/sys-i386/task_size.c
+++ b/arch/um/os-Linux/sys-i386/task_size.c
@@ -63,7 +63,7 @@ static int page_ok(unsigned long page)
 	return ok;
 }
 
-unsigned long os_get_task_size(void)
+unsigned long os_get_top_address(void)
 {
 	struct sigaction sa, old;
 	unsigned long bottom = 0;
@@ -76,9 +76,9 @@ unsigned long os_get_task_size(void)
 	 * hosts, but shouldn't hurt otherwise.
 	 */
 	unsigned long top = 0xffffd000 >> UM_KERN_PAGE_SHIFT;
-	unsigned long test;
+	unsigned long test, original;
 
-	printf("Locating the top of the address space ... ");
+	printf("Locating the bottom of the address space ... ");
 	fflush(stdout);
 
 	/*
@@ -89,16 +89,31 @@ unsigned long os_get_task_size(void)
 	sigemptyset(&sa.sa_mask);
 	sa.sa_flags = SA_NODEFER;
 	if (sigaction(SIGSEGV, &sa, &old)) {
-		perror("os_get_task_size");
+		perror("os_get_top_address");
 		exit(1);
 	}
 
-	if (!page_ok(bottom)) {
-		fprintf(stderr, "Address 0x%x no good?\n",
-			bottom << UM_KERN_PAGE_SHIFT);
+	/* Manually scan the address space, bottom-up, until we find
+	 * the first valid page (or run out of them).
+	 */
+	for (bottom = 0; bottom < top; bottom++) {
+		if (page_ok(bottom))
+			break;
+	}
+
+	/* If we've got this far, we ran out of pages. */
+	if (bottom == top) {
+		fprintf(stderr, "Unable to determine bottom of address "
+			"space.\n");
 		exit(1);
 	}
 
+	printf("0x%x\n", bottom << UM_KERN_PAGE_SHIFT);
+	printf("Locating the top of the address space ... ");
+	fflush(stdout);
+
+	original = bottom;
+
 	/* This could happen with a 4G/4G split */
 	if (page_ok(top))
 		goto out;
@@ -114,7 +129,7 @@ unsigned long os_get_task_size(void)
 out:
 	/* Restore the old SIGSEGV handling */
 	if (sigaction(SIGSEGV, &old, NULL)) {
-		perror("os_get_task_size");
+		perror("os_get_top_address");
 		exit(1);
 	}
 	top <<= UM_KERN_PAGE_SHIFT;
diff --git a/arch/um/os-Linux/sys-x86_64/task_size.c b/arch/um/os-Linux/sys-x86_64/task_size.c
index fad6f57f8ee3..26a0dd1f349c 100644
--- a/arch/um/os-Linux/sys-x86_64/task_size.c
+++ b/arch/um/os-Linux/sys-x86_64/task_size.c
@@ -1,4 +1,4 @@
-unsigned long os_get_task_size(unsigned long shift)
+unsigned long os_get_top_address(unsigned long shift)
 {
 	/* The old value of CONFIG_TOP_ADDR */
 	return 0x7fc0000000;
diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c
index e49280599465..dec5678fc17f 100644
--- a/arch/um/os-Linux/time.c
+++ b/arch/um/os-Linux/time.c
@@ -9,7 +9,9 @@
 #include <time.h>
 #include <sys/time.h>
 #include "kern_constants.h"
+#include "kern_util.h"
 #include "os.h"
+#include "process.h"
 #include "user.h"
 
 int set_interval(void)
@@ -58,12 +60,17 @@ static inline long long timeval_to_ns(const struct timeval *tv)
 long long disable_timer(void)
 {
 	struct itimerval time = ((struct itimerval) { { 0, 0 }, { 0, 0 } });
+	int remain, max = UM_NSEC_PER_SEC / UM_HZ;
 
 	if (setitimer(ITIMER_VIRTUAL, &time, &time) < 0)
 		printk(UM_KERN_ERR "disable_timer - setitimer failed, "
 		       "errno = %d\n", errno);
 
-	return timeval_to_ns(&time.it_value);
+	remain = timeval_to_ns(&time.it_value);
+	if (remain > max)
+		remain = max;
+
+	return remain;
 }
 
 long long os_nsecs(void)
@@ -79,7 +86,48 @@ static int after_sleep_interval(struct timespec *ts)
 {
 	return 0;
 }
+
+static void deliver_alarm(void)
+{
+	alarm_handler(SIGVTALRM, NULL);
+}
+
+static unsigned long long sleep_time(unsigned long long nsecs)
+{
+	return nsecs;
+}
+
 #else
+unsigned long long last_tick;
+unsigned long long skew;
+
+static void deliver_alarm(void)
+{
+	unsigned long long this_tick = os_nsecs();
+	int one_tick = UM_NSEC_PER_SEC / UM_HZ;
+
+	/* Protection against the host's time going backwards */
+	if ((last_tick != 0) && (this_tick < last_tick))
+		this_tick = last_tick;
+
+	if (last_tick == 0)
+		last_tick = this_tick - one_tick;
+
+	skew += this_tick - last_tick;
+
+	while (skew >= one_tick) {
+		alarm_handler(SIGVTALRM, NULL);
+		skew -= one_tick;
+	}
+
+	last_tick = this_tick;
+}
+
+static unsigned long long sleep_time(unsigned long long nsecs)
+{
+	return nsecs > skew ? nsecs - skew : 0;
+}
+
 static inline long long timespec_to_us(const struct timespec *ts)
 {
 	return ((long long) ts->tv_sec * UM_USEC_PER_SEC) +
@@ -102,6 +150,11 @@ static int after_sleep_interval(struct timespec *ts)
 	 */
 	if (start_usecs > usec)
 		start_usecs = usec;
+
+	start_usecs -= skew / UM_NSEC_PER_USEC;
+	if (start_usecs < 0)
+		start_usecs = 0;
+
 	tv = ((struct timeval) { .tv_sec  = start_usecs / UM_USEC_PER_SEC,
 				 .tv_usec = start_usecs % UM_USEC_PER_SEC });
 	interval = ((struct itimerval) { { 0, usec }, tv });
@@ -113,8 +166,6 @@ static int after_sleep_interval(struct timespec *ts)
 }
 #endif
 
-extern void alarm_handler(int sig, struct sigcontext *sc);
-
 void idle_sleep(unsigned long long nsecs)
 {
 	struct timespec ts;
@@ -126,10 +177,12 @@ void idle_sleep(unsigned long long nsecs)
 	 */
 	if (nsecs == 0)
 		nsecs = UM_NSEC_PER_SEC / UM_HZ;
+
+	nsecs = sleep_time(nsecs);
 	ts = ((struct timespec) { .tv_sec	= nsecs / UM_NSEC_PER_SEC,
 				  .tv_nsec	= nsecs % UM_NSEC_PER_SEC });
 
 	if (nanosleep(&ts, &ts) == 0)
-		alarm_handler(SIGVTALRM, NULL);
+		deliver_alarm();
 	after_sleep_interval(&ts);
 }