1 files changed, 115 insertions, 44 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 491f2d9f89ac..84751f3f52d5 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -11,6 +11,40 @@
  *  go into icache. We cache the reference to task_struct upon lookup too.
  *  Eventually it should become a filesystem in its own. We don't use the
  *  rest of procfs anymore.
+ *
+ *
+ *  Changelog:
+ *  17-Jan-2005
+ *  Allan Bezerra
+ *  Bruna Moreira <bruna.moreira@indt.org.br>
+ *  Edjard Mota <edjard.mota@indt.org.br>
+ *  Ilias Biris <ilias.biris@indt.org.br>
+ *  Mauricio Lin <mauricio.lin@indt.org.br>
+ *
+ *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
+ *
+ *  A new process specific entry (smaps) included in /proc. It shows the
+ *  size of rss for each memory area. The maps entry lacks information
+ *  about physical memory size (rss) for each mapped file, i.e.,
+ *  rss information for executables and library files.
+ *  This additional information is useful for any tools that need to know
+ *  about physical memory consumption for a process specific library.
+ *
+ *  Changelog:
+ *  21-Feb-2005
+ *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
+ *  Pud inclusion in the page table walking.
+ *
+ *  ChangeLog:
+ *  10-Mar-2005
+ *  10LE Instituto Nokia de Tecnologia - INdT:
+ *  A better way to walks through the page table as suggested by Hugh Dickins.
+ *
+ *  Simo Piiroinen <simo.piiroinen@nokia.com>:
+ *  Smaps information related to shared, private, clean and dirty pages.
+ *
+ *  Paul Mundt <paul.mundt@nokia.com>:
+ *  Overall revision about smaps.
  */
 
 #include <asm/uaccess.h>
@@ -65,8 +99,10 @@ enum pid_directory_inos {
 	PROC_TGID_STAT,
 	PROC_TGID_STATM,
 	PROC_TGID_MAPS,
+	PROC_TGID_NUMA_MAPS,
 	PROC_TGID_MOUNTS,
 	PROC_TGID_WCHAN,
+	PROC_TGID_SMAPS,
 #ifdef CONFIG_SCHEDSTATS
 	PROC_TGID_SCHEDSTAT,
 #endif
@@ -83,7 +119,6 @@ enum pid_directory_inos {
 #ifdef CONFIG_AUDITSYSCALL
 	PROC_TGID_LOGINUID,
 #endif
-	PROC_TGID_FD_DIR,
 	PROC_TGID_OOM_SCORE,
 	PROC_TGID_OOM_ADJUST,
 	PROC_TID_INO,
@@ -102,8 +137,10 @@ enum pid_directory_inos {
 	PROC_TID_STAT,
 	PROC_TID_STATM,
 	PROC_TID_MAPS,
+	PROC_TID_NUMA_MAPS,
 	PROC_TID_MOUNTS,
 	PROC_TID_WCHAN,
+	PROC_TID_SMAPS,
 #ifdef CONFIG_SCHEDSTATS
 	PROC_TID_SCHEDSTAT,
 #endif
@@ -120,9 +157,11 @@ enum pid_directory_inos {
 #ifdef CONFIG_AUDITSYSCALL
 	PROC_TID_LOGINUID,
 #endif
-	PROC_TID_FD_DIR = 0x8000,	/* 0x8000-0xffff */
 	PROC_TID_OOM_SCORE,
 	PROC_TID_OOM_ADJUST,
+
+	/* Add new entries before this */
+	PROC_TID_FD_DIR = 0x8000,	/* 0x8000-0xffff */
 };
 
 struct pid_entry {
@@ -144,6 +183,9 @@ static struct pid_entry tgid_base_stuff[] = {
 	E(PROC_TGID_STAT,      "stat",    S_IFREG|S_IRUGO),
 	E(PROC_TGID_STATM,     "statm",   S_IFREG|S_IRUGO),
 	E(PROC_TGID_MAPS,      "maps",    S_IFREG|S_IRUGO),
+#ifdef CONFIG_NUMA
+	E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO),
+#endif
 	E(PROC_TGID_MEM,       "mem",     S_IFREG|S_IRUSR|S_IWUSR),
 #ifdef CONFIG_SECCOMP
 	E(PROC_TGID_SECCOMP,   "seccomp", S_IFREG|S_IRUSR|S_IWUSR),
@@ -152,6 +194,7 @@ static struct pid_entry tgid_base_stuff[] = {
 	E(PROC_TGID_ROOT,      "root",    S_IFLNK|S_IRWXUGO),
 	E(PROC_TGID_EXE,       "exe",     S_IFLNK|S_IRWXUGO),
 	E(PROC_TGID_MOUNTS,    "mounts",  S_IFREG|S_IRUGO),
+	E(PROC_TGID_SMAPS,     "smaps",   S_IFREG|S_IRUGO),
 #ifdef CONFIG_SECURITY
 	E(PROC_TGID_ATTR,      "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
 #endif
@@ -180,6 +223,9 @@ static struct pid_entry tid_base_stuff[] = {
 	E(PROC_TID_STAT,       "stat",    S_IFREG|S_IRUGO),
 	E(PROC_TID_STATM,      "statm",   S_IFREG|S_IRUGO),
 	E(PROC_TID_MAPS,       "maps",    S_IFREG|S_IRUGO),
+#ifdef CONFIG_NUMA
+	E(PROC_TID_NUMA_MAPS,  "numa_maps",    S_IFREG|S_IRUGO),
+#endif
 	E(PROC_TID_MEM,        "mem",     S_IFREG|S_IRUSR|S_IWUSR),
 #ifdef CONFIG_SECCOMP
 	E(PROC_TID_SECCOMP,    "seccomp", S_IFREG|S_IRUSR|S_IWUSR),
@@ -188,6 +234,7 @@ static struct pid_entry tid_base_stuff[] = {
 	E(PROC_TID_ROOT,       "root",    S_IFLNK|S_IRWXUGO),
 	E(PROC_TID_EXE,        "exe",     S_IFLNK|S_IRWXUGO),
 	E(PROC_TID_MOUNTS,     "mounts",  S_IFREG|S_IRUGO),
+	E(PROC_TID_SMAPS,      "smaps",   S_IFREG|S_IRUGO),
 #ifdef CONFIG_SECURITY
 	E(PROC_TID_ATTR,       "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
 #endif
@@ -251,15 +298,21 @@ static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsm
 	return -ENOENT;
 }
 
-static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+static struct fs_struct *get_fs_struct(struct task_struct *task)
 {
 	struct fs_struct *fs;
-	int result = -ENOENT;
-	task_lock(proc_task(inode));
-	fs = proc_task(inode)->fs;
+	task_lock(task);
+	fs = task->fs;
 	if(fs)
 		atomic_inc(&fs->count);
-	task_unlock(proc_task(inode));
+	task_unlock(task);
+	return fs;
+}
+
+static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+{
+	struct fs_struct *fs = get_fs_struct(proc_task(inode));
+	int result = -ENOENT;
 	if (fs) {
 		read_lock(&fs->lock);
 		*mnt = mntget(fs->pwdmnt);
@@ -273,13 +326,8 @@ static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfs
 
 static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
 {
-	struct fs_struct *fs;
+	struct fs_struct *fs = get_fs_struct(proc_task(inode));
 	int result = -ENOENT;
-	task_lock(proc_task(inode));
-	fs = proc_task(inode)->fs;
-	if(fs)
-		atomic_inc(&fs->count);
-	task_unlock(proc_task(inode));
 	if (fs) {
 		read_lock(&fs->lock);
 		*mnt = mntget(fs->rootmnt);
@@ -298,33 +346,6 @@ static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vf
 	 (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \
 	 security_ptrace(current,task) == 0))
 
-static int may_ptrace_attach(struct task_struct *task)
-{
-	int retval = 0;
-
-	task_lock(task);
-
-	if (!task->mm)
-		goto out;
-	if (((current->uid != task->euid) ||
-	     (current->uid != task->suid) ||
-	     (current->uid != task->uid) ||
-	     (current->gid != task->egid) ||
-	     (current->gid != task->sgid) ||
-	     (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE))
-		goto out;
-	rmb();
-	if (task->mm->dumpable != 1 && !capable(CAP_SYS_PTRACE))
-		goto out;
-	if (security_ptrace(current, task))
-		goto out;
-
-	retval = 1;
-out:
-	task_unlock(task);
-	return retval;
-}
-
 static int proc_pid_environ(struct task_struct *task, char * buffer)
 {
 	int res = 0;
@@ -334,7 +355,7 @@ static int proc_pid_environ(struct task_struct *task, char * buffer)
 		if (len > PAGE_SIZE)
 			len = PAGE_SIZE;
 		res = access_process_vm(task, mm->env_start, buffer, len, 0);
-		if (!may_ptrace_attach(task))
+		if (!ptrace_may_attach(task))
 			res = -ESRCH;
 		mmput(mm);
 	}
@@ -515,6 +536,46 @@ static struct file_operations proc_maps_operations = {
 	.release	= seq_release,
 };
 
+#ifdef CONFIG_NUMA
+extern struct seq_operations proc_pid_numa_maps_op;
+static int numa_maps_open(struct inode *inode, struct file *file)
+{
+	struct task_struct *task = proc_task(inode);
+	int ret = seq_open(file, &proc_pid_numa_maps_op);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = task;
+	}
+	return ret;
+}
+
+static struct file_operations proc_numa_maps_operations = {
+	.open		= numa_maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+#endif
+
+extern struct seq_operations proc_pid_smaps_op;
+static int smaps_open(struct inode *inode, struct file *file)
+{
+	struct task_struct *task = proc_task(inode);
+	int ret = seq_open(file, &proc_pid_smaps_op);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = task;
+	}
+	return ret;
+}
+
+static struct file_operations proc_smaps_operations = {
+	.open		= smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 extern struct seq_operations mounts_op;
 static int mounts_open(struct inode *inode, struct file *file)
 {
@@ -597,7 +658,7 @@ static ssize_t mem_read(struct file * file, char __user * buf,
 	int ret = -ESRCH;
 	struct mm_struct *mm;
 
-	if (!MAY_PTRACE(task) || !may_ptrace_attach(task))
+	if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
 		goto out;
 
 	ret = -ENOMEM;
@@ -623,7 +684,7 @@ static ssize_t mem_read(struct file * file, char __user * buf,
 
 		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
 		retval = access_process_vm(task, src, page, this_len, 0);
-		if (!retval || !MAY_PTRACE(task) || !may_ptrace_attach(task)) {
+		if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) {
 			if (!ret)
 				ret = -EIO;
 			break;
@@ -661,7 +722,7 @@ static ssize_t mem_write(struct file * file, const char * buf,
 	struct task_struct *task = proc_task(file->f_dentry->d_inode);
 	unsigned long dst = *ppos;
 
-	if (!MAY_PTRACE(task) || !may_ptrace_attach(task))
+	if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
 		return -ESRCH;
 
 	page = (char *)__get_free_page(GFP_USER);
@@ -1524,6 +1585,12 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 		case PROC_TGID_MAPS:
 			inode->i_fop = &proc_maps_operations;
 			break;
+#ifdef CONFIG_NUMA
+		case PROC_TID_NUMA_MAPS:
+		case PROC_TGID_NUMA_MAPS:
+			inode->i_fop = &proc_numa_maps_operations;
+			break;
+#endif
 		case PROC_TID_MEM:
 		case PROC_TGID_MEM:
 			inode->i_op = &proc_mem_inode_operations;
@@ -1539,6 +1606,10 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 		case PROC_TGID_MOUNTS:
 			inode->i_fop = &proc_mounts_operations;
 			break;
+		case PROC_TID_SMAPS:
+		case PROC_TGID_SMAPS:
+			inode->i_fop = &proc_smaps_operations;
+			break;
 #ifdef CONFIG_SECURITY
 		case PROC_TID_ATTR:
 			inode->i_nlink = 2;