Merge branch 'upstream'

14 files changed, 240 insertions, 95 deletions

diff --git a/arch/um/drivers/cow.h b/arch/um/drivers/cow.h
index 04e3958266e..dc36b222100 100644
--- a/arch/um/drivers/cow.h
+++ b/arch/um/drivers/cow.h
@@ -46,7 +46,7 @@ extern int file_reader(__u64 offset, char *buf, int len, void *arg);
 extern int read_cow_header(int (*reader)(__u64, char *, int, void *),
 			   void *arg, __u32 *version_out,
 			   char **backing_file_out, time_t *mtime_out,
-			   __u64 *size_out, int *sectorsize_out,
+			   unsigned long long *size_out, int *sectorsize_out,
 			   __u32 *align_out, int *bitmap_offset_out);
 
 extern int write_cow_header(char *cow_file, int fd, char *backing_file,
diff --git a/arch/um/drivers/cow_sys.h b/arch/um/drivers/cow_sys.h
index 94de4ead4f7..7a5b4afde69 100644
--- a/arch/um/drivers/cow_sys.h
+++ b/arch/um/drivers/cow_sys.h
@@ -28,7 +28,7 @@ static inline int cow_seek_file(int fd, __u64 offset)
 	return(os_seek_file(fd, offset));
 }
 
-static inline int cow_file_size(char *file, __u64 *size_out)
+static inline int cow_file_size(char *file, unsigned long long *size_out)
 {
 	return(os_file_size(file, size_out));
 }
diff --git a/arch/um/drivers/cow_user.c b/arch/um/drivers/cow_user.c
index 61951b72126..0ec4052db9c 100644
--- a/arch/um/drivers/cow_user.c
+++ b/arch/um/drivers/cow_user.c
@@ -17,30 +17,34 @@
 
 #define PATH_LEN_V1 256
 
+typedef __u32 time32_t;
+
 struct cow_header_v1 {
-	int magic;
-	int version;
+	__s32 magic;
+	__s32 version;
 	char backing_file[PATH_LEN_V1];
-	time_t mtime;
+	time32_t mtime;
 	__u64 size;
-	int sectorsize;
-};
+	__s32 sectorsize;
+} __attribute__((packed));
 
-#define PATH_LEN_V2 MAXPATHLEN
+/* Define PATH_LEN_V3 as the usual value of MAXPATHLEN, just hard-code it in
+ * case other systems have different values for MAXPATHLEN.
+ *
+ * The same must hold for V2 - we want file format compatibility, not anything
+ * else.
+ */
+#define PATH_LEN_V3 4096
+#define PATH_LEN_V2 PATH_LEN_V3
 
 struct cow_header_v2 {
 	__u32 magic;
 	__u32 version;
 	char backing_file[PATH_LEN_V2];
-	time_t mtime;
+	time32_t mtime;
 	__u64 size;
-	int sectorsize;
-};
-
-/* Define PATH_LEN_V3 as the usual value of MAXPATHLEN, just hard-code it in
- * case other systems have different values for MAXPATHLEN
- */
-#define PATH_LEN_V3 4096
+	__s32 sectorsize;
+} __attribute__((packed));
 
 /* Changes from V2 -
  *	PATH_LEN_V3 as described above
@@ -66,6 +70,15 @@ struct cow_header_v2 {
  *	Fixed (finally!) the rounding bug
  */
 
+/* Until Dec2005, __attribute__((packed)) was left out from the below
+ * definition, leading on 64-bit systems to 4 bytes of padding after mtime, to
+ * align size to 8-byte alignment.  This shifted all fields above (no padding
+ * was present on 32-bit, no other padding was added).
+ *
+ * However, this _can be detected_: it means that cow_format (always 0 until
+ * now) is shifted onto the first 4 bytes of backing_file, where it is otherwise
+ * impossible to find 4 zeros. -bb */
+
 struct cow_header_v3 {
 	__u32 magic;
 	__u32 version;
@@ -75,6 +88,18 @@ struct cow_header_v3 {
 	__u32 alignment;
 	__u32 cow_format;
 	char backing_file[PATH_LEN_V3];
+} __attribute__((packed));
+
+/* This is the broken layout used by some 64-bit binaries. */
+struct cow_header_v3_broken {
+	__u32 magic;
+	__u32 version;
+	__s64 mtime;
+	__u64 size;
+	__u32 sectorsize;
+	__u32 alignment;
+	__u32 cow_format;
+	char backing_file[PATH_LEN_V3];
 };
 
 /* COW format definitions - for now, we have only the usual COW bitmap */
@@ -84,6 +109,7 @@ union cow_header {
 	struct cow_header_v1 v1;
 	struct cow_header_v2 v2;
 	struct cow_header_v3 v3;
+	struct cow_header_v3_broken v3_b;
 };
 
 #define COW_MAGIC 0x4f4f4f4d  /* MOOO */
@@ -184,8 +210,9 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
 
 	err = -EINVAL;
 	if(strlen(backing_file) > sizeof(header->backing_file) - 1){
+		/* Below, %zd is for a size_t value */
 		cow_printf("Backing file name \"%s\" is too long - names are "
-			   "limited to %d characters\n", backing_file,
+			   "limited to %zd characters\n", backing_file,
 			   sizeof(header->backing_file) - 1);
 		goto out_free;
 	}
@@ -300,7 +327,8 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 		*align_out = *sectorsize_out;
 		file = header->v2.backing_file;
 	}
-	else if(version == 3){
+	/* This is very subtle - see above at union cow_header definition */
+	else if(version == 3 && (*((int*)header->v3.backing_file) != 0)){
 		if(n < sizeof(header->v3)){
 			cow_printf("read_cow_header - failed to read V3 "
 				   "header\n");
@@ -310,9 +338,43 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 		*size_out = ntohll(header->v3.size);
 		*sectorsize_out = ntohl(header->v3.sectorsize);
 		*align_out = ntohl(header->v3.alignment);
+		if (*align_out == 0) {
+			cow_printf("read_cow_header - invalid COW header, "
+				   "align == 0\n");
+		}
 		*bitmap_offset_out = ROUND_UP(sizeof(header->v3), *align_out);
 		file = header->v3.backing_file;
 	}
+	else if(version == 3){
+		cow_printf("read_cow_header - broken V3 file with"
+			   " 64-bit layout - recovering content.\n");
+
+		if(n < sizeof(header->v3_b)){
+			cow_printf("read_cow_header - failed to read V3 "
+				   "header\n");
+			goto out;
+		}
+
+		/* this was used until Dec2005 - 64bits are needed to represent
+		 * 2038+. I.e. we can safely do this truncating cast.
+		 *
+		 * Additionally, we must use ntohl() instead of ntohll(), since
+		 * the program used to use the former (tested - I got mtime
+		 * mismatch "0 vs whatever").
+		 *
+		 * Ever heard about bug-to-bug-compatibility ? ;-) */
+		*mtime_out = (time32_t) ntohl(header->v3_b.mtime);
+
+		*size_out = ntohll(header->v3_b.size);
+		*sectorsize_out = ntohl(header->v3_b.sectorsize);
+		*align_out = ntohl(header->v3_b.alignment);
+		if (*align_out == 0) {
+			cow_printf("read_cow_header - invalid COW header, "
+				   "align == 0\n");
+		}
+		*bitmap_offset_out = ROUND_UP(sizeof(header->v3_b), *align_out);
+		file = header->v3_b.backing_file;
+	}
 	else {
 		cow_printf("read_cow_header - invalid COW version\n");
 		goto out;
diff --git a/arch/um/drivers/daemon_kern.c b/arch/um/drivers/daemon_kern.c
index a61b7b46bc0..53d09ed78b4 100644
--- a/arch/um/drivers/daemon_kern.c
+++ b/arch/um/drivers/daemon_kern.c
@@ -95,18 +95,7 @@ static struct transport daemon_transport = {
 static int register_daemon(void)
 {
 	register_transport(&daemon_transport);
-	return(1);
+	return 0;
 }
 
 __initcall(register_daemon);
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c
index 49acb2badf3..d18a974735e 100644
--- a/arch/um/drivers/harddog_kern.c
+++ b/arch/um/drivers/harddog_kern.c
@@ -104,7 +104,7 @@ static int harddog_release(struct inode *inode, struct file *file)
 
 extern int ping_watchdog(int fd);
 
-static ssize_t harddog_write(struct file *file, const char *data, size_t len,
+static ssize_t harddog_write(struct file *file, const char __user *data, size_t len,
 			     loff_t *ppos)
 {
 	/*
@@ -118,6 +118,7 @@ static ssize_t harddog_write(struct file *file, const char *data, size_t len,
 static int harddog_ioctl(struct inode *inode, struct file *file,
 			 unsigned int cmd, unsigned long arg)
 {
+	void __user *argp= (void __user *)arg;
 	static struct watchdog_info ident = {
 		WDIOC_SETTIMEOUT,
 		0,
@@ -127,13 +128,12 @@ static int harddog_ioctl(struct inode *inode, struct file *file,
 		default:
 			return -ENOTTY;
 		case WDIOC_GETSUPPORT:
-			if(copy_to_user((struct harddog_info *)arg, &ident,
-					sizeof(ident)))
+			if(copy_to_user(argp, &ident, sizeof(ident)))
 				return -EFAULT;
 			return 0;
 		case WDIOC_GETSTATUS:
 		case WDIOC_GETBOOTSTATUS:
-			return put_user(0,(int *)arg);
+			return put_user(0,(int __user *)argp);
 		case WDIOC_KEEPALIVE:
 			return(ping_watchdog(harddog_out_fd));
 	}
diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c
index 59602b81b24..37232f908cd 100644
--- a/arch/um/drivers/hostaudio_kern.c
+++ b/arch/um/drivers/hostaudio_kern.c
@@ -67,8 +67,8 @@ MODULE_PARM_DESC(mixer, MIXER_HELP);
 
 /* /dev/dsp file operations */
 
-static ssize_t hostaudio_read(struct file *file, char *buffer, size_t count, 
-			      loff_t *ppos)
+static ssize_t hostaudio_read(struct file *file, char __user *buffer,
+			      size_t count, loff_t *ppos)
 {
         struct hostaudio_state *state = file->private_data;
 	void *kbuf;
@@ -94,7 +94,7 @@ static ssize_t hostaudio_read(struct file *file, char *buffer, size_t count,
 	return(err);
 }
 
-static ssize_t hostaudio_write(struct file *file, const char *buffer, 
+static ssize_t hostaudio_write(struct file *file, const char __user *buffer,
 			       size_t count, loff_t *ppos)
 {
         struct hostaudio_state *state = file->private_data;
@@ -152,7 +152,7 @@ static int hostaudio_ioctl(struct inode *inode, struct file *file,
 	case SNDCTL_DSP_CHANNELS:
 	case SNDCTL_DSP_SUBDIVIDE:
 	case SNDCTL_DSP_SETFRAGMENT:
-		if(get_user(data, (int *) arg))
+		if(get_user(data, (int __user *) arg))
 			return(-EFAULT);
 		break;
 	default:
@@ -168,7 +168,7 @@ static int hostaudio_ioctl(struct inode *inode, struct file *file,
 	case SNDCTL_DSP_CHANNELS:
 	case SNDCTL_DSP_SUBDIVIDE:
 	case SNDCTL_DSP_SETFRAGMENT:
-		if(put_user(data, (int *) arg))
+		if(put_user(data, (int __user *) arg))
 			return(-EFAULT);
 		break;
 	default:
diff --git a/arch/um/drivers/mcast_kern.c b/arch/um/drivers/mcast_kern.c
index c9b078fba03..3a7af18cf94 100644
--- a/arch/um/drivers/mcast_kern.c
+++ b/arch/um/drivers/mcast_kern.c
@@ -124,18 +124,7 @@ static struct transport mcast_transport = {
 static int register_mcast(void)
 {
 	register_transport(&mcast_transport);
-	return(1);
+	return 0;
 }
 
 __initcall(register_mcast);
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 1488816588e..6d7173fc55a 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -20,6 +20,8 @@
 #include "linux/namei.h"
 #include "linux/proc_fs.h"
 #include "linux/syscalls.h"
+#include "linux/list.h"
+#include "linux/mm.h"
 #include "linux/console.h"
 #include "asm/irq.h"
 #include "asm/uaccess.h"
@@ -60,7 +62,7 @@ static void mc_work_proc(void *unused)
 	unsigned long flags;
 
 	while(!list_empty(&mc_requests)){
-		local_save_flags(flags);
+		local_irq_save(flags);
 		req = list_entry(mc_requests.next, struct mconsole_entry,
 				 list);
 		list_del(&req->list);
@@ -85,7 +87,7 @@ static irqreturn_t mconsole_interrupt(int irq, void *dev_id,
 		if(req.cmd->context == MCONSOLE_INTR)
 			(*req.cmd->handler)(&req);
 		else {
-			new = kmalloc(sizeof(*new), GFP_ATOMIC);
+			new = kmalloc(sizeof(*new), GFP_NOWAIT);
 			if(new == NULL)
 				mconsole_reply(&req, "Out of memory", 1, 0);
 			else {
@@ -347,6 +349,141 @@ static struct mc_device *mconsole_find_dev(char *name)
 	return(NULL);
 }
 
+#define UNPLUGGED_PER_PAGE \
+	((PAGE_SIZE - sizeof(struct list_head)) / sizeof(unsigned long))
+
+struct unplugged_pages {
+	struct list_head list;
+	void *pages[UNPLUGGED_PER_PAGE];
+};
+
+static unsigned long long unplugged_pages_count = 0;
+static struct list_head unplugged_pages = LIST_HEAD_INIT(unplugged_pages);
+static int unplug_index = UNPLUGGED_PER_PAGE;
+
+static int mem_config(char *str)
+{
+	unsigned long long diff;
+	int err = -EINVAL, i, add;
+	char *ret;
+
+	if(str[0] != '=')
+		goto out;
+
+	str++;
+	if(str[0] == '-')
+		add = 0;
+	else if(str[0] == '+'){
+		add = 1;
+	}
+	else goto out;
+
+	str++;
+	diff = memparse(str, &ret);
+	if(*ret != '\0')
+		goto out;
+
+	diff /= PAGE_SIZE;
+
+	for(i = 0; i < diff; i++){
+		struct unplugged_pages *unplugged;
+		void *addr;
+
+		if(add){
+			if(list_empty(&unplugged_pages))
+				break;
+
+			unplugged = list_entry(unplugged_pages.next,
+					       struct unplugged_pages, list);
+			if(unplug_index > 0)
+				addr = unplugged->pages[--unplug_index];
+			else {
+				list_del(&unplugged->list);
+				addr = unplugged;
+				unplug_index = UNPLUGGED_PER_PAGE;
+			}
+
+			free_page((unsigned long) addr);
+			unplugged_pages_count--;
+		}
+		else {
+			struct page *page;
+
+			page = alloc_page(GFP_ATOMIC);
+			if(page == NULL)
+				break;
+
+			unplugged = page_address(page);
+			if(unplug_index == UNPLUGGED_PER_PAGE){
+				list_add(&unplugged->list, &unplugged_pages);
+				unplug_index = 0;
+			}
+			else {
+				struct list_head *entry = unplugged_pages.next;
+				addr = unplugged;
+
+				unplugged = list_entry(entry,
+						       struct unplugged_pages,
+						       list);
+				unplugged->pages[unplug_index++] = addr;
+				err = os_drop_memory(addr, PAGE_SIZE);
+				if(err)
+					printk("Failed to release memory - "
+					       "errno = %d\n", err);
+			}
+
+			unplugged_pages_count++;
+		}
+	}
+
+	err = 0;
+out:
+	return err;
+}
+
+static int mem_get_config(char *name, char *str, int size, char **error_out)
+{
+	char buf[sizeof("18446744073709551615")];
+	int len = 0;
+
+	sprintf(buf, "%ld", uml_physmem);
+	CONFIG_CHUNK(str, size, len, buf, 1);
+
+	return len;
+}
+
+static int mem_id(char **str, int *start_out, int *end_out)
+{
+	*start_out = 0;
+	*end_out = 0;
+
+	return 0;
+}
+
+static int mem_remove(int n)
+{
+	return -EBUSY;
+}
+
+static struct mc_device mem_mc = {
+	.name		= "mem",
+	.config		= mem_config,
+	.get_config	= mem_get_config,
+	.id		= mem_id,
+	.remove		= mem_remove,
+};
+
+static int mem_mc_init(void)
+{
+	if(can_drop_memory())
+		mconsole_register_dev(&mem_mc);
+	else printk("Can't release memory to the host - memory hotplug won't "
+		    "be supported\n");
+	return 0;
+}
+
+__initcall(mem_mc_init);
+
 #define CONFIG_BUF_SIZE 64
 
 static void mconsole_get_config(int (*get_config)(char *, char *, int,
@@ -478,7 +615,7 @@ static void console_write(struct console *console, const char *string,
 		return;
 
 	while(1){
-		n = min(len, ARRAY_SIZE(console_buf) - console_index);
+		n = min((size_t) len, ARRAY_SIZE(console_buf) - console_index);
 		strncpy(&console_buf[console_index], string, n);
 		console_index += n;
 		string += n;
@@ -517,7 +654,6 @@ static void with_console(struct mc_request *req, void (*proc)(void *),
 	struct mconsole_entry entry;
 	unsigned long flags;
 
-	INIT_LIST_HEAD(&entry.list);
 	entry.request = *req;
 	list_add(&entry.list, &clients);
 	spin_lock_irqsave(&console_lock, flags);
diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c
index 0e2f06187ea..0a7786e00cf 100644
--- a/arch/um/drivers/net_user.c
+++ b/arch/um/drivers/net_user.c
@@ -182,7 +182,9 @@ static int change_tramp(char **argv, char *output, int output_len)
 	pe_data.stdout = fds[1];
 	pid = run_helper(change_pre_exec, &pe_data, argv, NULL);
 
-	read_output(fds[0], output, output_len);
+	if (pid > 0)	/* Avoid hang as we won't get data in failure case. */
+		read_output(fds[0], output, output_len);
+
 	os_close_file(fds[0]);
 	os_close_file(fds[1]);
 
diff --git a/arch/um/drivers/pcap_kern.c b/arch/um/drivers/pcap_kern.c
index 07c80f2156e..466ff2c2f91 100644
--- a/arch/um/drivers/pcap_kern.c
+++ b/arch/um/drivers/pcap_kern.c
@@ -106,18 +106,7 @@ static struct transport pcap_transport = {
 static int register_pcap(void)
 {
 	register_transport(&pcap_transport);
-	return(1);
+	return 0;
 }
 
 __initcall(register_pcap);
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/arch/um/drivers/slip_kern.c b/arch/um/drivers/slip_kern.c
index a62f5ef445c..163ee0d5f75 100644
--- a/arch/um/drivers/slip_kern.c
+++ b/arch/um/drivers/slip_kern.c
@@ -93,18 +93,7 @@ static struct transport slip_transport = {
 static int register_slip(void)
 {
 	register_transport(&slip_transport);
-	return(1);
+	return 0;
 }
 
 __initcall(register_slip);
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/arch/um/drivers/slirp_kern.c b/arch/um/drivers/slirp_kern.c
index 33d7982be5d..95e50c943e1 100644
--- a/arch/um/drivers/slirp_kern.c
+++ b/arch/um/drivers/slirp_kern.c
@@ -77,7 +77,7 @@ static int slirp_setup(char *str, char **mac_out, void *data)
 	int i=0;
 
 	*init = ((struct slirp_init)
-		{ argw :		{ { "slirp", NULL  } } });
+		{ .argw = { { "slirp", NULL  } } });
 
 	str = split_if_spec(str, mac_out, NULL);
 
@@ -116,18 +116,7 @@ static struct transport slirp_transport = {
 static int register_slirp(void)
 {
 	register_transport(&slirp_transport);
-	return(1);
+	return 0;
 }
 
 __initcall(register_slirp);
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/arch/um/drivers/slirp_user.c b/arch/um/drivers/slirp_user.c
index b94c66114bc..33c5f6e625e 100644
--- a/arch/um/drivers/slirp_user.c
+++ b/arch/um/drivers/slirp_user.c
@@ -104,7 +104,7 @@ static void slirp_close(int fd, void *data)
 	}
 
 	if(err == 0) {
-		printk("slirp_close: process %d has not exited\n");
+		printk("slirp_close: process %d has not exited\n", pri->pid);
 		return;
 	}
 
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 0336575d244..0897852b09a 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -891,7 +891,7 @@ int ubd_driver_init(void){
 			     SA_INTERRUPT, "ubd", ubd_dev);
 	if(err != 0)
 		printk(KERN_ERR "um_request_irq failed - errno = %d\n", -err);
-	return(err);
+	return 0;
 }
 
 device_initcall(ubd_driver_init);