[PATCH 1/4] coredump: add an interface to control the core dump routine

From: Kawai, Hidehiro
Date: Thu Mar 01 2007 - 23:48:15 EST

This patch adds an interface to set/reset a flag which determines
anonymous shared memory segments should be dumped or not when a core
file is generated.

/proc/<pid>/coredump_omit_anonymous_shared file is provided to access
the flag. 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.

The flag is stored into coredump_omit_anon_shared member of mm_struct,
which shares bytes with dumpable member because these two are adjacent
bit fields. In order to avoid write-write race between the two, we use
a global spin lock.

smp_wmb() at updating dumpable is removed because set_dumpable()
includes a pair of spin lock and unlock which has the effect of
memory barrier.

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@xxxxxxxxxxx>
---
fs/exec.c | 12 ++--
fs/proc/base.c | 103 ++++++++++++++++++++++++++++++++++++++
include/linux/binfmts.h | 4 +
include/linux/sched.h | 33 ++++++++++++
kernel/fork.c | 3 +
kernel/sys.c | 62 +++++++---------------
security/commoncap.c | 2
security/dummy.c | 2
8 files changed, 174 insertions(+), 47 deletions(-)

Index: linux-2.6.20-mm2/fs/proc/base.c
===================================================================
--- linux-2.6.20-mm2.orig/fs/proc/base.c
+++ linux-2.6.20-mm2/fs/proc/base.c
@@ -74,6 +74,7 @@
#include <linux/poll.h>
#include <linux/nsproxy.h>
#include <linux/oom.h>
+#include <linux/elf.h>
#include "internal.h"

/* NOTE:
@@ -1753,6 +1754,104 @@ static const struct inode_operations pro

#endif

+#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+static ssize_t proc_coredump_omit_anon_shared_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;
+ loff_t __ppos = *ppos;
+ int ret;
+
+ ret = -ESRCH;
+ if (!task)
+ goto out_no_task;
+
+ ret = 0;
+ mm = get_task_mm(task);
+ if (!mm)
+ goto out_no_mm;
+
+ len = snprintf(buffer, sizeof(buffer), "%u\n",
+ mm->coredump_omit_anon_shared);
+ if (__ppos >= len)
+ goto out;
+ if (count > len - __ppos)
+ count = len - __ppos;
+
+ ret = -EFAULT;
+ if (copy_to_user(buf, buffer + __ppos, count))
+ goto out;
+
+ ret = count;
+ *ppos = __ppos + count;
+
+ out:
+ mmput(mm);
+ out_no_mm:
+ put_task_struct(task);
+ out_no_task:
+ return ret;
+}
+
+static ssize_t proc_coredump_omit_anon_shared_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;
+
+ 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;
+
+ if (down_write_trylock(&coredump_settings_sem)) {
+ set_coredump_omit_anon_shared(mm, (val != 0));
+ up_write(&coredump_settings_sem);
+ } else
+ ret = -EBUSY;
+
+ mmput(mm);
+ out_no_mm:
+ put_task_struct(task);
+ out_no_task:
+ return ret;
+}
+
+static struct file_operations proc_coredump_omit_anon_shared_operations = {
+ .read = proc_coredump_omit_anon_shared_read,
+ .write = proc_coredump_omit_anon_shared_write,
+};
+#endif
+
/*
* /proc/self:
*/
@@ -1972,6 +2071,10 @@ static 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_omit_anonymous_shared", S_IRUGO|S_IWUSR,
+ coredump_omit_anon_shared),
+#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
INF("io", S_IRUGO, pid_io_accounting),
#endif
Index: linux-2.6.20-mm2/include/linux/sched.h
===================================================================
--- linux-2.6.20-mm2.orig/include/linux/sched.h
+++ linux-2.6.20-mm2/include/linux/sched.h
@@ -366,7 +366,13 @@ struct mm_struct {
unsigned int token_priority;
unsigned int last_interval;

+ /*
+ * Writing to these bit fields can cause race condition. To avoid
+ * the race, use dump_bits_lock. You may also use set_dumpable() or
+ * set_coredump_*() macros to set a value.
+ */
unsigned char dumpable:2;
+ unsigned char coredump_omit_anon_shared:1; /* don't dump anon shm */

/* coredumping support */
int core_waiters;
@@ -1727,6 +1733,33 @@ static inline void inc_syscw(struct task
}
#endif

+#include <linux/elf.h>
+/*
+ * These macros are used to protect dumpable and coredump_omit_anon_shared bit
+ * fields in mm_struct from write race between the two.
+ */
+extern spinlock_t dump_bits_lock;
+#define __set_dump_bits(dest, val) \
+ do { \
+ spin_lock(&dump_bits_lock); \
+ (dest) = (val); \
+ spin_unlock(&dump_bits_lock); \
+ } while (0)
+
+#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+# define set_dumpable(mm, val) \
+ __set_dump_bits((mm)->dumpable, val)
+# define set_coredump_omit_anon_shared(mm, val) \
+ __set_dump_bits((mm)->coredump_omit_anon_shared, val)
+#else
+# define set_dumpable(mm, val) \
+ do { \
+ (mm)->dumpable = (val); \
+ smp_wmb(); \
+ } while (0)
+# define set_coredump_omit_anon_shared(mm, val)
+#endif
+
#endif /* __KERNEL__ */

#endif
Index: linux-2.6.20-mm2/fs/exec.c
===================================================================
--- linux-2.6.20-mm2.orig/fs/exec.c
+++ linux-2.6.20-mm2/fs/exec.c
@@ -61,6 +61,8 @@
int core_uses_pid;
char core_pattern[128] = "core";
int suid_dumpable = 0;
+DEFINE_SPINLOCK(dump_bits_lock);
+DECLARE_RWSEM(coredump_settings_sem);

EXPORT_SYMBOL(suid_dumpable);
/* The maximal length of core_pattern is also specified in sysctl.c */
@@ -853,9 +855,9 @@ int flush_old_exec(struct linux_binprm *
current->sas_ss_sp = current->sas_ss_size = 0;

if (current->euid == current->uid && current->egid == current->gid)
- current->mm->dumpable = 1;
+ set_dumpable(current->mm, 1);
else
- current->mm->dumpable = suid_dumpable;
+ set_dumpable(current->mm, suid_dumpable);

name = bprm->filename;

@@ -883,7 +885,7 @@ int flush_old_exec(struct linux_binprm *
file_permission(bprm->file, MAY_READ) ||
(bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) {
suid_keys(current);
- current->mm->dumpable = suid_dumpable;
+ set_dumpable(current->mm, suid_dumpable);
}

/* An exec changes our domain. We are no longer part of the thread
@@ -1477,7 +1479,7 @@ int do_coredump(long signr, int exit_cod
flag = O_EXCL; /* Stop rewrite attacks */
current->fsuid = 0; /* Dump root private */
}
- mm->dumpable = 0;
+ set_dumpable(mm, 0);

retval = coredump_wait(exit_code);
if (retval < 0)
@@ -1530,7 +1532,9 @@ int do_coredump(long signr, int exit_cod
if (!ispipe && do_truncate(file->f_path.dentry, 0, 0, file) != 0)
goto close_fail;

+ down_read(&coredump_settings_sem);
retval = binfmt->core_dump(signr, regs, file);
+ up_read(&coredump_settings_sem);

if (retval)
current->signal->group_exit_code |= 0x80;
Index: linux-2.6.20-mm2/kernel/fork.c
===================================================================
--- linux-2.6.20-mm2.orig/kernel/fork.c
+++ linux-2.6.20-mm2/kernel/fork.c
@@ -334,6 +334,9 @@ static struct mm_struct * mm_init(struct
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
+ /* don't need to use set_coredump_omit_anon_shared() */
+ mm->coredump_omit_anon_shared =
+ (current->mm) ? current->mm->coredump_omit_anon_shared : 0;
mm->core_waiters = 0;
mm->nr_ptes = 0;
set_mm_counter(mm, file_rss, 0);
Index: linux-2.6.20-mm2/kernel/sys.c
===================================================================
--- linux-2.6.20-mm2.orig/kernel/sys.c
+++ linux-2.6.20-mm2/kernel/sys.c
@@ -1022,10 +1022,8 @@ asmlinkage long sys_setregid(gid_t rgid,
else
return -EPERM;
}
- if (new_egid != old_egid) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (new_egid != old_egid)
+ set_dumpable(current->mm, suid_dumpable);
if (rgid != (gid_t) -1 ||
(egid != (gid_t) -1 && egid != old_rgid))
current->sgid = new_egid;
@@ -1052,16 +1050,12 @@ asmlinkage long sys_setgid(gid_t gid)
return retval;

if (capable(CAP_SETGID)) {
- if (old_egid != gid) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (old_egid != gid)
+ set_dumpable(current->mm, suid_dumpable);
current->gid = current->egid = current->sgid = current->fsgid = gid;
} else if ((gid == current->gid) || (gid == current->sgid)) {
- if (old_egid != gid) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (old_egid != gid)
+ set_dumpable(current->mm, suid_dumpable);
current->egid = current->fsgid = gid;
}
else
@@ -1089,10 +1083,8 @@ static int set_user(uid_t new_ruid, int

switch_uid(new_user);

- if (dumpclear) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (dumpclear)
+ set_dumpable(current->mm, suid_dumpable);
current->uid = new_ruid;
return 0;
}
@@ -1145,10 +1137,8 @@ asmlinkage long sys_setreuid(uid_t ruid,
if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0)
return -EAGAIN;

- if (new_euid != old_euid) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (new_euid != old_euid)
+ set_dumpable(current->mm, suid_dumpable);
current->fsuid = current->euid = new_euid;
if (ruid != (uid_t) -1 ||
(euid != (uid_t) -1 && euid != old_ruid))
@@ -1195,10 +1185,8 @@ asmlinkage long sys_setuid(uid_t uid)
} else if ((uid != current->uid) && (uid != new_suid))
return -EPERM;

- if (old_euid != uid) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (old_euid != uid)
+ set_dumpable(current->mm, suid_dumpable);
current->fsuid = current->euid = uid;
current->suid = new_suid;

@@ -1240,10 +1228,8 @@ asmlinkage long sys_setresuid(uid_t ruid
return -EAGAIN;
}
if (euid != (uid_t) -1) {
- if (euid != current->euid) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (euid != current->euid)
+ set_dumpable(current->mm, suid_dumpable);
current->euid = euid;
}
current->fsuid = current->euid;
@@ -1290,10 +1276,8 @@ asmlinkage long sys_setresgid(gid_t rgid
return -EPERM;
}
if (egid != (gid_t) -1) {
- if (egid != current->egid) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (egid != current->egid)
+ set_dumpable(current->mm, suid_dumpable);
current->egid = egid;
}
current->fsgid = current->egid;
@@ -1336,10 +1320,8 @@ asmlinkage long sys_setfsuid(uid_t uid)
if (uid == current->uid || uid == current->euid ||
uid == current->suid || uid == current->fsuid ||
capable(CAP_SETUID)) {
- if (uid != old_fsuid) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (uid != old_fsuid)
+ set_dumpable(current->mm, suid_dumpable);
current->fsuid = uid;
}

@@ -1365,10 +1347,8 @@ asmlinkage long sys_setfsgid(gid_t gid)
if (gid == current->gid || gid == current->egid ||
gid == current->sgid || gid == current->fsgid ||
capable(CAP_SETGID)) {
- if (gid != old_fsgid) {
- current->mm->dumpable = suid_dumpable;
- smp_wmb();
- }
+ if (gid != old_fsgid)
+ set_dumpable(current->mm, suid_dumpable);
current->fsgid = gid;
key_fsgid_changed(current);
proc_id_connector(current, PROC_EVENT_GID);
@@ -2163,7 +2143,7 @@ asmlinkage long sys_prctl(int option, un
error = -EINVAL;
break;
}
- current->mm->dumpable = arg2;
+ set_dumpable(current->mm, arg2);
break;

case PR_SET_UNALIGN:
Index: linux-2.6.20-mm2/security/commoncap.c
===================================================================
--- linux-2.6.20-mm2.orig/security/commoncap.c
+++ linux-2.6.20-mm2/security/commoncap.c
@@ -244,7 +244,7 @@ void cap_bprm_apply_creds (struct linux_

if (bprm->e_uid != current->uid || bprm->e_gid != current->gid ||
!cap_issubset (new_permitted, current->cap_permitted)) {
- current->mm->dumpable = suid_dumpable;
+ set_dumpable(current->mm, suid_dumpable);

if (unsafe & ~LSM_UNSAFE_PTRACE_CAP) {
if (!capable(CAP_SETUID)) {
Index: linux-2.6.20-mm2/security/dummy.c
===================================================================
--- linux-2.6.20-mm2.orig/security/dummy.c
+++ linux-2.6.20-mm2/security/dummy.c
@@ -130,7 +130,7 @@ static void dummy_bprm_free_security (st
static void dummy_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
{
if (bprm->e_uid != current->uid || bprm->e_gid != current->gid) {
- current->mm->dumpable = suid_dumpable;
+ set_dumpable(current->mm, suid_dumpable);

if ((unsafe & ~LSM_UNSAFE_PTRACE_CAP) && !capable(CAP_SETUID)) {
bprm->e_uid = current->uid;
Index: linux-2.6.20-mm2/include/linux/binfmts.h
===================================================================
--- linux-2.6.20-mm2.orig/include/linux/binfmts.h
+++ linux-2.6.20-mm2/include/linux/binfmts.h
@@ -17,6 +17,8 @@ struct pt_regs;

#ifdef __KERNEL__

+#include <linux/rwsem.h>
+
/*
* This structure is used to hold the arguments that are used when loading binaries.
*/
@@ -75,6 +77,8 @@ extern int suid_dumpable;
#define SUID_DUMP_USER 1 /* Dump as user of process */
#define SUID_DUMP_ROOT 2 /* Dump as root */

+extern struct rw_semaphore coredump_settings_sem;
+
/* Stack area protections */
#define EXSTACK_DEFAULT 0 /* Whatever the arch defaults to */
#define EXSTACK_DISABLE_X 1 /* Disable executable stacks */


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/