proc: seqfile convert proc_pid_status to properly handle pid namespaces

Currently we possibly lookup the pid in the wrong pid namespace.  So
seq_file convert proc_pid_status which ensures the proper pid namespaces is
passed in.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: another build fix]
[akpm@linux-foundation.org: s390 build fix]
[akpm@linux-foundation.org: fix task_name() output]
[akpm@linux-foundation.org: fix nommu build]
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Andrew Morgan <morgan@kernel.org>
Cc: Serge Hallyn <serue@us.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

10 files changed, 103 insertions, 101 deletions

diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 1a2fdb6991d..a4d29025ddb 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -24,6 +24,7 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/seq_file.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/kdebug.h>
@@ -218,41 +219,40 @@ void show_registers(struct pt_regs *regs)
 }	
 
 /* This is called from fs/proc/array.c */
-char *task_show_regs(struct task_struct *task, char *buffer)
+void task_show_regs(struct seq_file *m, struct task_struct *task)
 {
 	struct pt_regs *regs;
 
 	regs = task_pt_regs(task);
-	buffer += sprintf(buffer, "task: %p, ksp: %p\n",
+	seq_printf(m, "task: %p, ksp: %p\n",
 		       task, (void *)task->thread.ksp);
-	buffer += sprintf(buffer, "User PSW : %p %p\n",
+	seq_printf(m, "User PSW : %p %p\n",
 		       (void *) regs->psw.mask, (void *)regs->psw.addr);
 
-	buffer += sprintf(buffer, "User GPRS: " FOURLONG,
+	seq_printf(m, "User GPRS: " FOURLONG,
 			  regs->gprs[0], regs->gprs[1],
 			  regs->gprs[2], regs->gprs[3]);
-	buffer += sprintf(buffer, "           " FOURLONG,
+	seq_printf(m, "           " FOURLONG,
 			  regs->gprs[4], regs->gprs[5],
 			  regs->gprs[6], regs->gprs[7]);
-	buffer += sprintf(buffer, "           " FOURLONG,
+	seq_printf(m, "           " FOURLONG,
 			  regs->gprs[8], regs->gprs[9],
 			  regs->gprs[10], regs->gprs[11]);
-	buffer += sprintf(buffer, "           " FOURLONG,
+	seq_printf(m, "           " FOURLONG,
 			  regs->gprs[12], regs->gprs[13],
 			  regs->gprs[14], regs->gprs[15]);
-	buffer += sprintf(buffer, "User ACRS: %08x %08x %08x %08x\n",
+	seq_printf(m, "User ACRS: %08x %08x %08x %08x\n",
 			  task->thread.acrs[0], task->thread.acrs[1],
 			  task->thread.acrs[2], task->thread.acrs[3]);
-	buffer += sprintf(buffer, "           %08x %08x %08x %08x\n",
+	seq_printf(m, "           %08x %08x %08x %08x\n",
 			  task->thread.acrs[4], task->thread.acrs[5],
 			  task->thread.acrs[6], task->thread.acrs[7]);
-	buffer += sprintf(buffer, "           %08x %08x %08x %08x\n",
+	seq_printf(m, "           %08x %08x %08x %08x\n",
 			  task->thread.acrs[8], task->thread.acrs[9],
 			  task->thread.acrs[10], task->thread.acrs[11]);
-	buffer += sprintf(buffer, "           %08x %08x %08x %08x\n",
+	seq_printf(m, "           %08x %08x %08x %08x\n",
 			  task->thread.acrs[12], task->thread.acrs[13],
 			  task->thread.acrs[14], task->thread.acrs[15]);
-	return buffer;
 }
 
 static DEFINE_SPINLOCK(die_lock);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 5540e9575c6..07d6c4853fe 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -89,18 +89,21 @@
 do { memcpy(buffer, string, strlen(string)); \
      buffer += strlen(string); } while (0)
 
-static inline char *task_name(struct task_struct *p, char *buf)
+static inline void task_name(struct seq_file *m, struct task_struct *p)
 {
 	int i;
+	char *buf, *end;
 	char *name;
 	char tcomm[sizeof(p->comm)];
 
 	get_task_comm(tcomm, p);
 
-	ADDBUF(buf, "Name:\t");
+	seq_printf(m, "Name:\t");
+	end = m->buf + m->size;
+	buf = m->buf + m->count;
 	name = tcomm;
 	i = sizeof(tcomm);
-	do {
+	while (i && (buf < end)) {
 		unsigned char c = *name;
 		name++;
 		i--;
@@ -108,20 +111,21 @@ static inline char *task_name(struct task_struct *p, char *buf)
 		if (!c)
 			break;
 		if (c == '\\') {
-			buf[1] = c;
-			buf += 2;
+			buf++;
+			if (buf < end)
+				*buf++ = c;
 			continue;
 		}
 		if (c == '\n') {
-			buf[0] = '\\';
-			buf[1] = 'n';
-			buf += 2;
+			*buf++ = '\\';
+			if (buf < end)
+				*buf++ = 'n';
 			continue;
 		}
 		buf++;
-	} while (i);
-	*buf = '\n';
-	return buf+1;
+	}
+	m->count = buf - m->buf;
+	seq_printf(m, "\n");
 }
 
 /*
@@ -152,21 +156,20 @@ static inline const char *get_task_state(struct task_struct *tsk)
 	return *p;
 }
 
-static inline char *task_state(struct task_struct *p, char *buffer)
+static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *p)
 {
 	struct group_info *group_info;
 	int g;
 	struct fdtable *fdt = NULL;
-	struct pid_namespace *ns;
 	pid_t ppid, tpid;
 
-	ns = current->nsproxy->pid_ns;
 	rcu_read_lock();
 	ppid = pid_alive(p) ?
 		task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
 	tpid = pid_alive(p) && p->ptrace ?
 		task_pid_nr_ns(rcu_dereference(p->parent), ns) : 0;
-	buffer += sprintf(buffer,
+	seq_printf(m,
 		"State:\t%s\n"
 		"Tgid:\t%d\n"
 		"Pid:\t%d\n"
@@ -176,7 +179,7 @@ static inline char *task_state(struct task_struct *p, char *buffer)
 		"Gid:\t%d\t%d\t%d\t%d\n",
 		get_task_state(p),
 		task_tgid_nr_ns(p, ns),
-		task_pid_nr_ns(p, ns),
+		pid_nr_ns(pid, ns),
 		ppid, tpid,
 		p->uid, p->euid, p->suid, p->fsuid,
 		p->gid, p->egid, p->sgid, p->fsgid);
@@ -184,7 +187,7 @@ static inline char *task_state(struct task_struct *p, char *buffer)
 	task_lock(p);
 	if (p->files)
 		fdt = files_fdtable(p->files);
-	buffer += sprintf(buffer,
+	seq_printf(m,
 		"FDSize:\t%d\n"
 		"Groups:\t",
 		fdt ? fdt->max_fds : 0);
@@ -195,20 +198,18 @@ static inline char *task_state(struct task_struct *p, char *buffer)
 	task_unlock(p);
 
 	for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++)
-		buffer += sprintf(buffer, "%d ", GROUP_AT(group_info, g));
+		seq_printf(m, "%d ", GROUP_AT(group_info, g));
 	put_group_info(group_info);
 
-	buffer += sprintf(buffer, "\n");
-	return buffer;
+	seq_printf(m, "\n");
 }
 
-static char *render_sigset_t(const char *header, sigset_t *set, char *buffer)
+static void render_sigset_t(struct seq_file *m, const char *header,
+				sigset_t *set)
 {
-	int i, len;
+	int i;
 
-	len = strlen(header);
-	memcpy(buffer, header, len);
-	buffer += len;
+	seq_printf(m, "%s", header);
 
 	i = _NSIG;
 	do {
@@ -219,12 +220,10 @@ static char *render_sigset_t(const char *header, sigset_t *set, char *buffer)
 		if (sigismember(set, i+2)) x |= 2;
 		if (sigismember(set, i+3)) x |= 4;
 		if (sigismember(set, i+4)) x |= 8;
-		*buffer++ = (x < 10 ? '0' : 'a' - 10) + x;
+		seq_printf(m, "%x", x);
 	} while (i >= 4);
 
-	*buffer++ = '\n';
-	*buffer = 0;
-	return buffer;
+	seq_printf(m, "\n");
 }
 
 static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign,
@@ -242,7 +241,7 @@ static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign,
 	}
 }
 
-static inline char *task_sig(struct task_struct *p, char *buffer)
+static inline void task_sig(struct seq_file *m, struct task_struct *p)
 {
 	unsigned long flags;
 	sigset_t pending, shpending, blocked, ignored, caught;
@@ -269,67 +268,66 @@ static inline char *task_sig(struct task_struct *p, char *buffer)
 	}
 	rcu_read_unlock();
 
-	buffer += sprintf(buffer, "Threads:\t%d\n", num_threads);
-	buffer += sprintf(buffer, "SigQ:\t%lu/%lu\n", qsize, qlim);
+	seq_printf(m, "Threads:\t%d\n", num_threads);
+	seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim);
 
 	/* render them all */
-	buffer = render_sigset_t("SigPnd:\t", &pending, buffer);
-	buffer = render_sigset_t("ShdPnd:\t", &shpending, buffer);
-	buffer = render_sigset_t("SigBlk:\t", &blocked, buffer);
-	buffer = render_sigset_t("SigIgn:\t", &ignored, buffer);
-	buffer = render_sigset_t("SigCgt:\t", &caught, buffer);
-
-	return buffer;
+	render_sigset_t(m, "SigPnd:\t", &pending);
+	render_sigset_t(m, "ShdPnd:\t", &shpending);
+	render_sigset_t(m, "SigBlk:\t", &blocked);
+	render_sigset_t(m, "SigIgn:\t", &ignored);
+	render_sigset_t(m, "SigCgt:\t", &caught);
 }
 
-static char *render_cap_t(const char *header, kernel_cap_t *a, char *buffer)
+static void render_cap_t(struct seq_file *m, const char *header,
+			kernel_cap_t *a)
 {
 	unsigned __capi;
 
-	buffer += sprintf(buffer, "%s", header);
+	seq_printf(m, "%s", header);
 	CAP_FOR_EACH_U32(__capi) {
-		buffer += sprintf(buffer, "%08x",
-				  a->cap[(_LINUX_CAPABILITY_U32S-1) - __capi]);
+		seq_printf(m, "%08x",
+			   a->cap[(_LINUX_CAPABILITY_U32S-1) - __capi]);
 	}
-	return buffer + sprintf(buffer, "\n");
+	seq_printf(m, "\n");
 }
 
-static inline char *task_cap(struct task_struct *p, char *buffer)
+static inline void task_cap(struct seq_file *m, struct task_struct *p)
 {
-	buffer = render_cap_t("CapInh:\t", &p->cap_inheritable, buffer);
-	buffer = render_cap_t("CapPrm:\t", &p->cap_permitted, buffer);
-	return render_cap_t("CapEff:\t", &p->cap_effective, buffer);
+	render_cap_t(m, "CapInh:\t", &p->cap_inheritable);
+	render_cap_t(m, "CapPrm:\t", &p->cap_permitted);
+	render_cap_t(m, "CapEff:\t", &p->cap_effective);
 }
 
-static inline char *task_context_switch_counts(struct task_struct *p,
-						char *buffer)
+static inline void task_context_switch_counts(struct seq_file *m,
+						struct task_struct *p)
 {
-	return buffer + sprintf(buffer, "voluntary_ctxt_switches:\t%lu\n"
-			    "nonvoluntary_ctxt_switches:\t%lu\n",
-			    p->nvcsw,
-			    p->nivcsw);
+	seq_printf(m,	"voluntary_ctxt_switches:\t%lu\n"
+			"nonvoluntary_ctxt_switches:\t%lu\n",
+			p->nvcsw,
+			p->nivcsw);
 }
 
-int proc_pid_status(struct task_struct *task, char *buffer)
+int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
 {
-	char *orig = buffer;
 	struct mm_struct *mm = get_task_mm(task);
 
-	buffer = task_name(task, buffer);
-	buffer = task_state(task, buffer);
+	task_name(m, task);
+	task_state(m, ns, pid, task);
 
 	if (mm) {
-		buffer = task_mem(mm, buffer);
+		task_mem(m, mm);
 		mmput(mm);
 	}
-	buffer = task_sig(task, buffer);
-	buffer = task_cap(task, buffer);
-	buffer = cpuset_task_status_allowed(task, buffer);
+	task_sig(m, task);
+	task_cap(m, task);
+	cpuset_task_status_allowed(m, task);
 #if defined(CONFIG_S390)
-	buffer = task_show_regs(task, buffer);
+	task_show_regs(m, task);
 #endif
-	buffer = task_context_switch_counts(task, buffer);
-	return buffer - orig;
+	task_context_switch_counts(m, task);
+	return 0;
 }
 
 /*
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9c3e548a675..8a19a8a1a3e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2274,7 +2274,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	DIR("fdinfo",     S_IRUSR|S_IXUSR, fdinfo),
 	REG("environ",    S_IRUSR, environ),
 	INF("auxv",       S_IRUSR, pid_auxv),
-	INF("status",     S_IRUGO, pid_status),
+	ONE("status",     S_IRUGO, pid_status),
 	INF("limits",	  S_IRUSR, pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",      S_IRUGO|S_IWUSR, pid_sched),
@@ -2605,7 +2605,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	DIR("fdinfo",    S_IRUSR|S_IXUSR, fdinfo),
 	REG("environ",   S_IRUSR, environ),
 	INF("auxv",      S_IRUSR, pid_auxv),
-	INF("status",    S_IRUGO, pid_status),
+	ONE("status",    S_IRUGO, pid_status),
 	INF("limits",	 S_IRUSR, pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",     S_IRUGO|S_IWUSR, pid_sched),
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 45bdbfc704e..ea496ffeabe 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -53,7 +53,8 @@ extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task);
 extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task);
-extern int proc_pid_status(struct task_struct *, char *);
+extern int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task);
 extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task);
 extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 38338ed98cc..a34c440f8d2 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -9,13 +9,14 @@
 #include <linux/mempolicy.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/seq_file.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
 
-char *task_mem(struct mm_struct *mm, char *buffer)
+void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
 	unsigned long data, text, lib;
 	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
@@ -37,7 +38,7 @@ char *task_mem(struct mm_struct *mm, char *buffer)
 	data = mm->total_vm - mm->shared_vm - mm->stack_vm;
 	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
 	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
-	buffer += sprintf(buffer,
+	seq_printf(m,
 		"VmPeak:\t%8lu kB\n"
 		"VmSize:\t%8lu kB\n"
 		"VmLck:\t%8lu kB\n"
@@ -56,7 +57,6 @@ char *task_mem(struct mm_struct *mm, char *buffer)
 		data << (PAGE_SHIFT-10),
 		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
 		(PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
-	return buffer;
 }
 
 unsigned long task_vsize(struct mm_struct *mm)
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 1932c2ca345..cee0231c6ce 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -12,7 +12,7 @@
  * each process that owns it. Non-shared memory is counted
  * accurately.
  */
-char *task_mem(struct mm_struct *mm, char *buffer)
+void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
 	struct vm_list_struct *vml;
 	unsigned long bytes = 0, sbytes = 0, slack = 0;
@@ -58,14 +58,13 @@ char *task_mem(struct mm_struct *mm, char *buffer)
 
 	bytes += kobjsize(current); /* includes kernel stack */
 
-	buffer += sprintf(buffer,
+	seq_printf(m,
 		"Mem:\t%8lu bytes\n"
 		"Slack:\t%8lu bytes\n"
 		"Shared:\t%8lu bytes\n",
 		bytes, slack, sbytes);
 
 	up_read(&mm->mmap_sem);
-	return buffer;
 }
 
 unsigned long task_vsize(struct mm_struct *mm)
diff --git a/include/asm-s390/processor.h b/include/asm-s390/processor.h
index 4f744609cd1..dfec2d011c0 100644
--- a/include/asm-s390/processor.h
+++ b/include/asm-s390/processor.h
@@ -161,6 +161,7 @@ struct stack_frame {
 /* Forward declaration, a strange C thing */
 struct task_struct;
 struct mm_struct;
+struct seq_file;
 
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
@@ -177,7 +178,7 @@ extern unsigned long thread_saved_pc(struct task_struct *t);
 /*
  * Print register of task into buffer. Used in fs/proc/array.c.
  */
-extern char *task_show_regs(struct task_struct *task, char *buffer);
+extern void task_show_regs(struct seq_file *m, struct task_struct *task);
 
 extern void show_registers(struct pt_regs *regs);
 extern void show_code(struct pt_regs *regs);
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index ecae585ec3d..f8c9a2752f0 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -57,7 +57,9 @@ extern int cpuset_memory_pressure_enabled;
 extern void __cpuset_memory_pressure_bump(void);
 
 extern const struct file_operations proc_cpuset_operations;
-extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer);
+struct seq_file;
+extern void cpuset_task_status_allowed(struct seq_file *m,
+					struct task_struct *task);
 
 extern void cpuset_lock(void);
 extern void cpuset_unlock(void);
@@ -126,10 +128,9 @@ static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 
 static inline void cpuset_memory_pressure_bump(void) {}
 
-static inline char *cpuset_task_status_allowed(struct task_struct *task,
-							char *buffer)
+static inline void cpuset_task_status_allowed(struct seq_file *m,
+						struct task_struct *task)
 {
-	return buffer;
 }
 
 static inline void cpuset_lock(void) {}
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index b04ebf09fb9..e4a8f9aef18 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -118,7 +118,8 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct
 int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
 unsigned long task_vsize(struct mm_struct *);
 int task_statm(struct mm_struct *, int *, int *, int *, int *);
-char *task_mem(struct mm_struct *, char *);
+void task_mem(struct seq_file *, struct mm_struct *);
+void clear_refs_smap(struct mm_struct *mm);
 
 struct proc_dir_entry *de_get(struct proc_dir_entry *de);
 void de_put(struct proc_dir_entry *de);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 67b2bfe2781..3e296ed81d4 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2255,13 +2255,14 @@ const struct file_operations proc_cpuset_operations = {
 #endif /* CONFIG_PROC_PID_CPUSET */
 
 /* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
-char *cpuset_task_status_allowed(struct task_struct *task, char *buffer)
-{
-	buffer += sprintf(buffer, "Cpus_allowed:\t");
-	buffer += cpumask_scnprintf(buffer, PAGE_SIZE, task->cpus_allowed);
-	buffer += sprintf(buffer, "\n");
-	buffer += sprintf(buffer, "Mems_allowed:\t");
-	buffer += nodemask_scnprintf(buffer, PAGE_SIZE, task->mems_allowed);
-	buffer += sprintf(buffer, "\n");
-	return buffer;
+void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
+{
+	seq_printf(m, "Cpus_allowed:\t");
+	m->count += cpumask_scnprintf(m->buf + m->count, m->size - m->count,
+					task->cpus_allowed);
+	seq_printf(m, "\n");
+	seq_printf(m, "Mems_allowed:\t");
+	m->count += nodemask_scnprintf(m->buf + m->count, m->size - m->count,
+					task->mems_allowed);
+	seq_printf(m, "\n");
 }