coredump masking: add an interface for core dump filter

This patch adds an interface to set/reset flags which determines each memory
segment should be dumped or not when a core file is generated.

/proc/<pid>/coredump_filter file is provided to access the flags.  You can
change the flag status for a particular process by writing to or reading from
the file.

The flag status is inherited to the child process when it is created.

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: David Howells <dhowells@redhat.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 105 insertions, 0 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 49b3ab0175e0..3c77d5a64e7c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -72,6 +72,7 @@
 #include <linux/poll.h>
 #include <linux/nsproxy.h>
 #include <linux/oom.h>
+#include <linux/elf.h>
 #include "internal.h"
 
 /* NOTE:
@@ -1785,6 +1786,91 @@ static const struct inode_operations proc_attr_dir_inode_operations = {
 
 #endif
 
+#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf,
+                                         size_t count, loff_t *ppos)
+{
+        struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
+        struct mm_struct *mm;
+        char buffer[PROC_NUMBUF];
+        size_t len;
+        int ret;
+
+        if (!task)
+                return -ESRCH;
+
+        ret = 0;
+        mm = get_task_mm(task);
+        if (mm) {
+                len = snprintf(buffer, sizeof(buffer), "%08lx\n",
+                               ((mm->flags & MMF_DUMP_FILTER_MASK) >>
+                                MMF_DUMP_FILTER_SHIFT));
+                mmput(mm);
+                ret = simple_read_from_buffer(buf, count, ppos, buffer, len);
+        }
+
+        put_task_struct(task);
+
+        return ret;
+}
+
+static ssize_t proc_coredump_filter_write(struct file *file,
+                                          const char __user *buf,
+                                          size_t count,
+                                          loff_t *ppos)
+{
+        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 = -ESRCH;
+        task = get_proc_task(file->f_dentry->d_inode);
+        if (!task)
+                goto out_no_task;
+
+        ret = end - buffer;
+        mm = get_task_mm(task);
+        if (!mm)
+                goto out_no_mm;
+
+        for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) {
+                if (val & mask)
+                        set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
+                else
+                        clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags);
+        }
+
+        mmput(mm);
+ out_no_mm:
+        put_task_struct(task);
+ out_no_task:
+        return ret;
+}
+
+static const struct file_operations proc_coredump_filter_operations = {
+        .read           = proc_coredump_filter_read,
+        .write          = proc_coredump_filter_write,
+};
+#endif
+
 /*
  * /proc/self:
  */
@@ -2005,6 +2091,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_FAULT_INJECTION
         REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject),
 #endif
+#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+        REG("coredump_filter", S_IRUGO|S_IWUSR, coredump_filter),
+#endif
 #ifdef CONFIG_TASK_IO_ACCOUNTING
         INF("io",       S_IRUGO, pid_io_accounting),
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8dbd08366400..94f624aef017 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -349,8 +349,22 @@ extern void set_dumpable(struct mm_struct *mm, int value);
 extern int get_dumpable(struct mm_struct *mm);
 
 /* mm flags */
+/* dumpable bits */
 #define MMF_DUMPABLE      0  /* core dump is permitted */
 #define MMF_DUMP_SECURELY 1  /* core file is readable only by root */
+#define MMF_DUMPABLE_BITS 2
+
+/* coredump filter bits */
+#define MMF_DUMP_ANON_PRIVATE   2
+#define MMF_DUMP_ANON_SHARED    3
+#define MMF_DUMP_MAPPED_PRIVATE 4
+#define MMF_DUMP_MAPPED_SHARED  5
+#define MMF_DUMP_FILTER_SHIFT   MMF_DUMPABLE_BITS
+#define MMF_DUMP_FILTER_BITS    4
+#define MMF_DUMP_FILTER_MASK \
+        (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
+#define MMF_DUMP_FILTER_DEFAULT \
+        ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED))
 
 struct mm_struct {
         struct vm_area_struct * mmap;           /* list of VMAs */
diff --git a/kernel/fork.c b/kernel/fork.c
index ba39bdb2a7b8..469838998220 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -334,6 +334,8 @@ static struct mm_struct * mm_init(struct mm_struct * mm)
         atomic_set(&mm->mm_count, 1);
         init_rwsem(&mm->mmap_sem);
         INIT_LIST_HEAD(&mm->mmlist);
+        mm->flags = (current->mm) ? current->mm->flags
+                                  : MMF_DUMP_FILTER_DEFAULT;
         mm->core_waiters = 0;
         mm->nr_ptes = 0;
         set_mm_counter(mm, file_rss, 0);