lkml.org 
[lkml]   [2019]   [Apr]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
Subject[RFC 2/2] signal: extend pidfd_send_signal() to allow expedited process killing
From
Add new SS_EXPEDITE flag to be used when sending SIGKILL via
pidfd_send_signal() syscall to allow expedited memory reclaim of the
victim process. The usage of this flag is currently limited to SIGKILL
signal and only to privileged users.

Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
include/linux/sched/signal.h | 3 ++-
include/linux/signal.h | 11 ++++++++++-
ipc/mqueue.c | 2 +-
kernel/signal.c | 37 ++++++++++++++++++++++++++++--------
kernel/time/itimer.c | 2 +-
5 files changed, 43 insertions(+), 12 deletions(-)

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index e412c092c1e8..8a227633a058 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -327,7 +327,8 @@ extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *);
extern void force_sigsegv(int sig, struct task_struct *p);
extern int force_sig_info(int, struct kernel_siginfo *, struct task_struct *);
extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp);
-extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid);
+extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid,
+ bool expedite);
extern int kill_pid_info_as_cred(int, struct kernel_siginfo *, struct pid *,
const struct cred *);
extern int kill_pgrp(struct pid *pid, int sig, int priv);
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 9702016734b1..34b7852aa4a0 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -446,8 +446,17 @@ int __save_altstack(stack_t __user *, unsigned long);
} while (0);

#ifdef CONFIG_PROC_FS
+
+/*
+ * SS_FLAGS values used in pidfd_send_signal:
+ *
+ * SS_EXPEDITE indicates desire to expedite the operation.
+ */
+#define SS_EXPEDITE 0x00000001
+
struct seq_file;
extern void render_sigset_t(struct seq_file *, const char *, sigset_t *);
-#endif
+
+#endif /* CONFIG_PROC_FS */

#endif /* _LINUX_SIGNAL_H */
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index aea30530c472..27c66296e08e 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -720,7 +720,7 @@ static void __do_notify(struct mqueue_inode_info *info)
rcu_read_unlock();

kill_pid_info(info->notify.sigev_signo,
- &sig_i, info->notify_owner);
+ &sig_i, info->notify_owner, false);
break;
case SIGEV_THREAD:
set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
diff --git a/kernel/signal.c b/kernel/signal.c
index f98448cf2def..02ed4332d17c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -43,6 +43,7 @@
#include <linux/compiler.h>
#include <linux/posix-timers.h>
#include <linux/livepatch.h>
+#include <linux/oom.h>

#define CREATE_TRACE_POINTS
#include <trace/events/signal.h>
@@ -1394,7 +1395,8 @@ int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp)
return success ? 0 : retval;
}

-int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
+int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid,
+ bool expedite)
{
int error = -ESRCH;
struct task_struct *p;
@@ -1402,8 +1404,17 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
for (;;) {
rcu_read_lock();
p = pid_task(pid, PIDTYPE_PID);
- if (p)
+ if (p) {
error = group_send_sig_info(sig, info, p, PIDTYPE_TGID);
+
+ /*
+ * Ignore expedite_reclaim return value, it is best
+ * effort only.
+ */
+ if (!error && expedite)
+ expedite_reclaim(p);
+ }
+
rcu_read_unlock();
if (likely(!p || error != -ESRCH))
return error;
@@ -1420,7 +1431,7 @@ static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid)
{
int error;
rcu_read_lock();
- error = kill_pid_info(sig, info, find_vpid(pid));
+ error = kill_pid_info(sig, info, find_vpid(pid), false);
rcu_read_unlock();
return error;
}
@@ -1487,7 +1498,7 @@ static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid)

if (pid > 0) {
rcu_read_lock();
- ret = kill_pid_info(sig, info, find_vpid(pid));
+ ret = kill_pid_info(sig, info, find_vpid(pid), false);
rcu_read_unlock();
return ret;
}
@@ -1704,7 +1715,7 @@ EXPORT_SYMBOL(kill_pgrp);

int kill_pid(struct pid *pid, int sig, int priv)
{
- return kill_pid_info(sig, __si_special(priv), pid);
+ return kill_pid_info(sig, __si_special(priv), pid, false);
}
EXPORT_SYMBOL(kill_pid);

@@ -3577,10 +3588,20 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
struct pid *pid;
kernel_siginfo_t kinfo;

- /* Enforce flags be set to 0 until we add an extension. */
- if (flags)
+ /* Enforce no unknown flags. */
+ if (flags & ~SS_EXPEDITE)
return -EINVAL;

+ if (flags & SS_EXPEDITE) {
+ /* Enforce SS_EXPEDITE to be used with SIGKILL only. */
+ if (sig != SIGKILL)
+ return -EINVAL;
+
+ /* Limit expedited killing to privileged users only. */
+ if (!capable(CAP_SYS_NICE))
+ return -EPERM;
+ }
+
f = fdget_raw(pidfd);
if (!f.file)
return -EBADF;
@@ -3614,7 +3635,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
prepare_kill_siginfo(sig, &kinfo);
}

- ret = kill_pid_info(sig, &kinfo, pid);
+ ret = kill_pid_info(sig, &kinfo, pid, (flags & SS_EXPEDITE) != 0);

err:
fdput(f);
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 02068b2d5862..c926483cdb53 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -140,7 +140,7 @@ enum hrtimer_restart it_real_fn(struct hrtimer *timer)
struct pid *leader_pid = sig->pids[PIDTYPE_TGID];

trace_itimer_expire(ITIMER_REAL, leader_pid, 0);
- kill_pid_info(SIGALRM, SEND_SIG_PRIV, leader_pid);
+ kill_pid_info(SIGALRM, SEND_SIG_PRIV, leader_pid, false);

return HRTIMER_NORESTART;
}
--
2.21.0.392.gf8f6787159e-goog
\
 
 \ /
  Last update: 2019-04-11 03:44    [W:0.334 / U:1.468 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site