X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?p=kvmfornfv.git;a=blobdiff_plain;f=kernel%2Ffs%2Fproc%2Fbase.c;h=b7de324bec1193dbb0d0eed756bcfbbb82e898ba;hp=093ca14f570154f5de1cc6db10c7995e1b7cba02;hb=e09b41010ba33a20a87472ee821fa407a5b8da36;hpb=f93b97fd65072de626c074dbe099a1fff05ce060

diff --git a/kernel/fs/proc/base.c b/kernel/fs/proc/base.c
index 093ca14f5..b7de324be 100644
--- a/kernel/fs/proc/base.c
+++ b/kernel/fs/proc/base.c
@@ -196,22 +196,214 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
 	return result;
 }
 
-static int proc_pid_cmdline(struct seq_file *m, struct pid_namespace *ns,
-			    struct pid *pid, struct task_struct *task)
+static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
+				     size_t _count, loff_t *pos)
 {
+	struct task_struct *tsk;
+	struct mm_struct *mm;
+	char *page;
+	unsigned long count = _count;
+	unsigned long arg_start, arg_end, env_start, env_end;
+	unsigned long len1, len2, len;
+	unsigned long p;
+	char c;
+	ssize_t rv;
+
+	BUG_ON(*pos < 0);
+
+	tsk = get_proc_task(file_inode(file));
+	if (!tsk)
+		return -ESRCH;
+	mm = get_task_mm(tsk);
+	put_task_struct(tsk);
+	if (!mm)
+		return 0;
+	/* Check if process spawned far enough to have cmdline. */
+	if (!mm->env_end) {
+		rv = 0;
+		goto out_mmput;
+	}
+
+	page = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!page) {
+		rv = -ENOMEM;
+		goto out_mmput;
+	}
+
+	down_read(&mm->mmap_sem);
+	arg_start = mm->arg_start;
+	arg_end = mm->arg_end;
+	env_start = mm->env_start;
+	env_end = mm->env_end;
+	up_read(&mm->mmap_sem);
+
+	BUG_ON(arg_start > arg_end);
+	BUG_ON(env_start > env_end);
+
+	len1 = arg_end - arg_start;
+	len2 = env_end - env_start;
+
+	/* Empty ARGV. */
+	if (len1 == 0) {
+		rv = 0;
+		goto out_free_page;
+	}
 	/*
-	 * Rely on struct seq_operations::show() being called once
-	 * per internal buffer allocation. See single_open(), traverse().
+	 * Inherently racy -- command line shares address space
+	 * with code and data.
 	 */
-	BUG_ON(m->size < PAGE_SIZE);
-	m->count += get_cmdline(task, m->buf, PAGE_SIZE);
-	return 0;
+	rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+	if (rv <= 0)
+		goto out_free_page;
+
+	rv = 0;
+
+	if (c == '\0') {
+		/* Command line (set of strings) occupies whole ARGV. */
+		if (len1 <= *pos)
+			goto out_free_page;
+
+		p = arg_start + *pos;
+		len = len1 - *pos;
+		while (count > 0 && len > 0) {
+			unsigned int _count;
+			int nr_read;
+
+			_count = min3(count, len, PAGE_SIZE);
+			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			if (nr_read < 0)
+				rv = nr_read;
+			if (nr_read <= 0)
+				goto out_free_page;
+
+			if (copy_to_user(buf, page, nr_read)) {
+				rv = -EFAULT;
+				goto out_free_page;
+			}
+
+			p	+= nr_read;
+			len	-= nr_read;
+			buf	+= nr_read;
+			count	-= nr_read;
+			rv	+= nr_read;
+		}
+	} else {
+		/*
+		 * Command line (1 string) occupies ARGV and maybe
+		 * extends into ENVP.
+		 */
+		if (len1 + len2 <= *pos)
+			goto skip_argv_envp;
+		if (len1 <= *pos)
+			goto skip_argv;
+
+		p = arg_start + *pos;
+		len = len1 - *pos;
+		while (count > 0 && len > 0) {
+			unsigned int _count, l;
+			int nr_read;
+			bool final;
+
+			_count = min3(count, len, PAGE_SIZE);
+			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			if (nr_read < 0)
+				rv = nr_read;
+			if (nr_read <= 0)
+				goto out_free_page;
+
+			/*
+			 * Command line can be shorter than whole ARGV
+			 * even if last "marker" byte says it is not.
+			 */
+			final = false;
+			l = strnlen(page, nr_read);
+			if (l < nr_read) {
+				nr_read = l;
+				final = true;
+			}
+
+			if (copy_to_user(buf, page, nr_read)) {
+				rv = -EFAULT;
+				goto out_free_page;
+			}
+
+			p	+= nr_read;
+			len	-= nr_read;
+			buf	+= nr_read;
+			count	-= nr_read;
+			rv	+= nr_read;
+
+			if (final)
+				goto out_free_page;
+		}
+skip_argv:
+		/*
+		 * Command line (1 string) occupies ARGV and
+		 * extends into ENVP.
+		 */
+		if (len1 <= *pos) {
+			p = env_start + *pos - len1;
+			len = len1 + len2 - *pos;
+		} else {
+			p = env_start;
+			len = len2;
+		}
+		while (count > 0 && len > 0) {
+			unsigned int _count, l;
+			int nr_read;
+			bool final;
+
+			_count = min3(count, len, PAGE_SIZE);
+			nr_read = access_remote_vm(mm, p, page, _count, 0);
+			if (nr_read < 0)
+				rv = nr_read;
+			if (nr_read <= 0)
+				goto out_free_page;
+
+			/* Find EOS. */
+			final = false;
+			l = strnlen(page, nr_read);
+			if (l < nr_read) {
+				nr_read = l;
+				final = true;
+			}
+
+			if (copy_to_user(buf, page, nr_read)) {
+				rv = -EFAULT;
+				goto out_free_page;
+			}
+
+			p	+= nr_read;
+			len	-= nr_read;
+			buf	+= nr_read;
+			count	-= nr_read;
+			rv	+= nr_read;
+
+			if (final)
+				goto out_free_page;
+		}
+skip_argv_envp:
+		;
+	}
+
+out_free_page:
+	free_page((unsigned long)page);
+out_mmput:
+	mmput(mm);
+	if (rv > 0)
+		*pos += rv;
+	return rv;
 }
 
+static const struct file_operations proc_pid_cmdline_ops = {
+	.read	= proc_pid_cmdline_read,
+	.llseek	= generic_file_llseek,
+};
+
 static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
 			 struct pid *pid, struct task_struct *task)
 {
-	struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
+	struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
 	if (mm && !IS_ERR(mm)) {
 		unsigned int nwords = 0;
 		do {
@@ -238,13 +430,11 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 
 	wchan = get_wchan(task);
 
-	if (lookup_symbol_name(wchan, symname) < 0) {
-		if (!ptrace_may_access(task, PTRACE_MODE_READ))
-			return 0;
-		seq_printf(m, "%lu", wchan);
-	} else {
+	if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)
+			&& !lookup_symbol_name(wchan, symname))
 		seq_printf(m, "%s", symname);
-	}
+	else
+		seq_putc(m, '0');
 
 	return 0;
 }
@@ -255,7 +445,7 @@ static int lock_trace(struct task_struct *task)
 	int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
 	if (err)
 		return err;
-	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
 		mutex_unlock(&task->signal->cred_guard_mutex);
 		return -EPERM;
 	}
@@ -304,14 +494,17 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
 }
 #endif
 
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
 /*
  * Provides /proc/PID/schedstat
  */
 static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
 			      struct pid *pid, struct task_struct *task)
 {
-	seq_printf(m, "%llu %llu %lu\n",
+	if (unlikely(!sched_info_on()))
+		seq_printf(m, "0 0 0\n");
+	else
+		seq_printf(m, "%llu %llu %lu\n",
 		   (unsigned long long)task->se.sum_exec_runtime,
 		   (unsigned long long)task->sched_info.run_delay,
 		   task->sched_info.pcount);
@@ -505,7 +698,7 @@ static int proc_fd_access_allowed(struct inode *inode)
 	 */
 	task = get_proc_task(inode);
 	if (task) {
-		allowed = ptrace_may_access(task, PTRACE_MODE_READ);
+		allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
 		put_task_struct(task);
 	}
 	return allowed;
@@ -540,7 +733,7 @@ static bool has_pid_permissions(struct pid_namespace *pid,
 		return true;
 	if (in_group_p(pid->pid_gid))
 		return true;
-	return ptrace_may_access(task, PTRACE_MODE_READ);
+	return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
 }
 
 
@@ -617,7 +810,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
 	struct mm_struct *mm = ERR_PTR(-ESRCH);
 
 	if (task) {
-		mm = mm_access(task, mode);
+		mm = mm_access(task, mode | PTRACE_MODE_FSCREDS);
 		put_task_struct(task);
 
 		if (!IS_ERR_OR_NULL(mm)) {
@@ -840,6 +1033,16 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
 	return simple_read_from_buffer(buf, count, ppos, buffer, len);
 }
 
+/*
+ * /proc/pid/oom_adj exists solely for backwards compatibility with previous
+ * kernels.  The effective policy is defined by oom_score_adj, which has a
+ * different scale: oom_adj grew exponentially and oom_score_adj grows linearly.
+ * Values written to oom_adj are simply mapped linearly to oom_score_adj.
+ * Processes that become oom disabled via oom_adj will still be oom disabled
+ * with this implementation.
+ *
+ * oom_adj cannot be removed since existing userspace binaries use it.
+ */
 static ssize_t oom_adj_write(struct file *file, const char __user *buf,
 			     size_t count, loff_t *ppos)
 {
@@ -1035,10 +1238,9 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
 				   size_t count, loff_t *ppos)
 {
 	struct inode * inode = file_inode(file);
-	char *page, *tmp;
-	ssize_t length;
 	uid_t loginuid;
 	kuid_t kloginuid;
+	int rv;
 
 	rcu_read_lock();
 	if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
@@ -1047,46 +1249,28 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
 	}
 	rcu_read_unlock();
 
-	if (count >= PAGE_SIZE)
-		count = PAGE_SIZE - 1;
-
 	if (*ppos != 0) {
 		/* No partial writes. */
 		return -EINVAL;
 	}
-	page = (char*)__get_free_page(GFP_TEMPORARY);
-	if (!page)
-		return -ENOMEM;
-	length = -EFAULT;
-	if (copy_from_user(page, buf, count))
-		goto out_free_page;
 
-	page[count] = '\0';
-	loginuid = simple_strtoul(page, &tmp, 10);
-	if (tmp == page) {
-		length = -EINVAL;
-		goto out_free_page;
-
-	}
+	rv = kstrtou32_from_user(buf, count, 10, &loginuid);
+	if (rv < 0)
+		return rv;
 
 	/* is userspace tring to explicitly UNSET the loginuid? */
 	if (loginuid == AUDIT_UID_UNSET) {
 		kloginuid = INVALID_UID;
 	} else {
 		kloginuid = make_kuid(file->f_cred->user_ns, loginuid);
-		if (!uid_valid(kloginuid)) {
-			length = -EINVAL;
-			goto out_free_page;
-		}
+		if (!uid_valid(kloginuid))
+			return -EINVAL;
 	}
 
-	length = audit_set_loginuid(kloginuid);
-	if (likely(length == 0))
-		length = count;
-
-out_free_page:
-	free_page((unsigned long) page);
-	return length;
+	rv = audit_set_loginuid(kloginuid);
+	if (rv < 0)
+		return rv;
+	return count;
 }
 
 static const struct file_operations proc_loginuid_operations = {
@@ -1140,8 +1324,9 @@ static ssize_t proc_fault_inject_write(struct file * file,
 			const char __user * buf, size_t count, loff_t *ppos)
 {
 	struct task_struct *task;
-	char buffer[PROC_NUMBUF], *end;
+	char buffer[PROC_NUMBUF];
 	int make_it_fail;
+	int rv;
 
 	if (!capable(CAP_SYS_RESOURCE))
 		return -EPERM;
@@ -1150,9 +1335,9 @@ static ssize_t proc_fault_inject_write(struct file * file,
 		count = sizeof(buffer) - 1;
 	if (copy_from_user(buffer, buf, count))
 		return -EFAULT;
-	make_it_fail = simple_strtol(strstrip(buffer), &end, 0);
-	if (*end)
-		return -EINVAL;
+	rv = kstrtoint(strstrip(buffer), 0, &make_it_fail);
+	if (rv < 0)
+		return rv;
 	if (make_it_fail < 0 || make_it_fail > 1)
 		return -EINVAL;
 
@@ -1380,7 +1565,7 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
 		return -ENOENT;
 }
 
-static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct inode *inode = d_inode(dentry);
 	struct path path;
@@ -1394,7 +1579,7 @@ static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
 	if (error)
 		goto out;
 
-	nd_jump_link(nd, &path);
+	nd_jump_link(&path);
 	return NULL;
 out:
 	return ERR_PTR(error);
@@ -1641,8 +1826,6 @@ end_instantiate:
 	return dir_emit(ctx, name, len, 1, DT_UNKNOWN);
 }
 
-#ifdef CONFIG_CHECKPOINT_RESTORE
-
 /*
  * dname_to_vma_addr - maps a dentry name into two unsigned longs
  * which represent vma start and end addresses.
@@ -1669,17 +1852,12 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
-	if (!capable(CAP_SYS_ADMIN)) {
-		status = -EPERM;
-		goto out_notask;
-	}
-
 	inode = d_inode(dentry);
 	task = get_proc_task(inode);
 	if (!task)
 		goto out_notask;
 
-	mm = mm_access(task, PTRACE_MODE_READ);
+	mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
 	if (IS_ERR_OR_NULL(mm))
 		goto out;
 
@@ -1762,6 +1940,29 @@ struct map_files_info {
 	unsigned char	name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */
 };
 
+/*
+ * Only allow CAP_SYS_ADMIN to follow the links, due to concerns about how the
+ * symlinks may be used to bypass permissions on ancestor directories in the
+ * path to the file in question.
+ */
+static const char *
+proc_map_files_follow_link(struct dentry *dentry, void **cookie)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	return proc_pid_follow_link(dentry, NULL);
+}
+
+/*
+ * Identical to proc_pid_link_inode_operations except for follow_link()
+ */
+static const struct inode_operations proc_map_files_link_inode_operations = {
+	.readlink	= proc_pid_readlink,
+	.follow_link	= proc_map_files_follow_link,
+	.setattr	= proc_setattr,
+};
+
 static int
 proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 			   struct task_struct *task, const void *ptr)
@@ -1777,7 +1978,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 	ei = PROC_I(inode);
 	ei->op.proc_get_link = proc_map_files_get_link;
 
-	inode->i_op = &proc_pid_link_inode_operations;
+	inode->i_op = &proc_map_files_link_inode_operations;
 	inode->i_size = 64;
 	inode->i_mode = S_IFLNK;
 
@@ -1801,17 +2002,13 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 	int result;
 	struct mm_struct *mm;
 
-	result = -EPERM;
-	if (!capable(CAP_SYS_ADMIN))
-		goto out;
-
 	result = -ENOENT;
 	task = get_proc_task(dir);
 	if (!task)
 		goto out;
 
 	result = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out_put_task;
 
 	result = -ENOENT;
@@ -1858,17 +2055,13 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 	struct map_files_info *p;
 	int ret;
 
-	ret = -EPERM;
-	if (!capable(CAP_SYS_ADMIN))
-		goto out;
-
 	ret = -ENOENT;
 	task = get_proc_task(file_inode(file));
 	if (!task)
 		goto out;
 
 	ret = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out_put_task;
 
 	ret = 0;
@@ -2050,7 +2243,6 @@ static const struct file_operations proc_timers_operations = {
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
 };
-#endif /* CONFIG_CHECKPOINT_RESTORE */
 
 static int proc_pident_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
@@ -2286,35 +2478,24 @@ static ssize_t proc_coredump_filter_write(struct file *file,
 {
 	struct task_struct *task;
 	struct mm_struct *mm;
-	char buffer[PROC_NUMBUF], *end;
 	unsigned int val;
 	int ret;
 	int i;
 	unsigned long mask;
 
-	ret = -EFAULT;
-	memset(buffer, 0, sizeof(buffer));
-	if (count > sizeof(buffer) - 1)
-		count = sizeof(buffer) - 1;
-	if (copy_from_user(buffer, buf, count))
-		goto out_no_task;
-
-	ret = -EINVAL;
-	val = (unsigned int)simple_strtoul(buffer, &end, 0);
-	if (*end == '\n')
-		end++;
-	if (end - buffer == 0)
-		goto out_no_task;
+	ret = kstrtouint_from_user(buf, count, 0, &val);
+	if (ret < 0)
+		return ret;
 
 	ret = -ESRCH;
 	task = get_proc_task(file_inode(file));
 	if (!task)
 		goto out_no_task;
 
-	ret = end - buffer;
 	mm = get_task_mm(task);
 	if (!mm)
 		goto out_no_mm;
+	ret = 0;
 
 	for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) {
 		if (val & mask)
@@ -2327,7 +2508,9 @@ static ssize_t proc_coredump_filter_write(struct file *file,
  out_no_mm:
 	put_task_struct(task);
  out_no_task:
-	return ret;
+	if (ret < 0)
+		return ret;
+	return count;
 }
 
 static const struct file_operations proc_coredump_filter_operations = {
@@ -2348,7 +2531,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	if (result)
 		return result;
 
-	if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
 		result = -EACCES;
 		goto out_unlock;
 	}
@@ -2549,9 +2732,7 @@ static const struct inode_operations proc_task_inode_operations;
 static const struct pid_entry tgid_base_stuff[] = {
 	DIR("task",       S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations),
 	DIR("fd",         S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
-#ifdef CONFIG_CHECKPOINT_RESTORE
 	DIR("map_files",  S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations),
-#endif
 	DIR("fdinfo",     S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
 	DIR("ns",	  S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
 #ifdef CONFIG_NET
@@ -2572,7 +2753,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
 	ONE("syscall",    S_IRUSR, proc_pid_syscall),
 #endif
-	ONE("cmdline",    S_IRUGO, proc_pid_cmdline),
+	REG("cmdline",    S_IRUGO, proc_pid_cmdline_ops),
 	ONE("stat",       S_IRUGO, proc_tgid_stat),
 	ONE("statm",      S_IRUGO, proc_pid_statm),
 	REG("maps",       S_IRUGO, proc_pid_maps_operations),
@@ -2600,7 +2781,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_STACKTRACE
 	ONE("stack",      S_IRUSR, proc_pid_stack),
 #endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
 	ONE("schedstat",  S_IRUGO, proc_pid_schedstat),
 #endif
 #ifdef CONFIG_LATENCYTOP
@@ -2918,11 +3099,11 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
 	ONE("syscall",   S_IRUSR, proc_pid_syscall),
 #endif
-	ONE("cmdline",   S_IRUGO, proc_pid_cmdline),
+	REG("cmdline",   S_IRUGO, proc_pid_cmdline_ops),
 	ONE("stat",      S_IRUGO, proc_tid_stat),
 	ONE("statm",     S_IRUGO, proc_pid_statm),
 	REG("maps",      S_IRUGO, proc_tid_maps_operations),
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#ifdef CONFIG_PROC_CHILDREN
 	REG("children",  S_IRUGO, proc_tid_children_operations),
 #endif
 #ifdef CONFIG_NUMA
@@ -2948,7 +3129,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_STACKTRACE
 	ONE("stack",      S_IRUSR, proc_pid_stack),
 #endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
 	ONE("schedstat", S_IRUGO, proc_pid_schedstat),
 #endif
 #ifdef CONFIG_LATENCYTOP