The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 07fd5b6cdf3cc30bfde8fe0f644771688be04447 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj(a)kernel.org>
Date: Mon, 13 Jun 2022 12:19:50 -1000
Subject: [PATCH] cgroup: Use separate src/dst nodes when preloading css_sets
for migration
Each cset (css_set) is pinned by its tasks. When we're moving tasks around
across csets for a migration, we need to hold the source and destination
csets to ensure that they don't go away while we're moving tasks about. This
is done by linking cset->mg_preload_node on either the
mgctx->preloaded_src_csets or mgctx->preloaded_dst_csets list. Using the
same cset->mg_preload_node for both the src and dst lists was deemed okay as
a cset can't be both the source and destination at the same time.
Unfortunately, this overloading becomes problematic when multiple tasks are
involved in a migration and some of them are identity noop migrations while
others are actually moving across cgroups. For example, this can happen with
the following sequence on cgroup1:
#1> mkdir -p /sys/fs/cgroup/misc/a/b
#2> echo $$ > /sys/fs/cgroup/misc/a/cgroup.procs
#3> RUN_A_COMMAND_WHICH_CREATES_MULTIPLE_THREADS &
#4> PID=$!
#5> echo $PID > /sys/fs/cgroup/misc/a/b/tasks
#6> echo $PID > /sys/fs/cgroup/misc/a/cgroup.procs
the process including the group leader back into a. In this final migration,
non-leader threads would be doing identity migration while the group leader
is doing an actual one.
After #3, let's say the whole process was in cset A, and that after #4, the
leader moves to cset B. Then, during #6, the following happens:
1. cgroup_migrate_add_src() is called on B for the leader.
2. cgroup_migrate_add_src() is called on A for the other threads.
3. cgroup_migrate_prepare_dst() is called. It scans the src list.
4. It notices that B wants to migrate to A, so it tries to A to the dst
list but realizes that its ->mg_preload_node is already busy.
5. and then it notices A wants to migrate to A as it's an identity
migration, it culls it by list_del_init()'ing its ->mg_preload_node and
putting references accordingly.
6. The rest of migration takes place with B on the src list but nothing on
the dst list.
This means that A isn't held while migration is in progress. If all tasks
leave A before the migration finishes and the incoming task pins it, the
cset will be destroyed leading to use-after-free.
This is caused by overloading cset->mg_preload_node for both src and dst
preload lists. We wanted to exclude the cset from the src list but ended up
inadvertently excluding it from the dst list too.
This patch fixes the issue by separating out cset->mg_preload_node into
->mg_src_preload_node and ->mg_dst_preload_node, so that the src and dst
preloadings don't interfere with each other.
Signed-off-by: Tejun Heo <tj(a)kernel.org>
Reported-by: Mukesh Ojha <quic_mojha(a)quicinc.com>
Reported-by: shisiyuan <shisiyuan19870131(a)gmail.com>
Link: http://lkml.kernel.org/r/1654187688-27411-1-git-send-email-shisiyuan@xiaomi…
Link: https://www.spinics.net/lists/cgroups/msg33313.html
Fixes: f817de98513d ("cgroup: prepare migration path for unified hierarchy")
Cc: stable(a)vger.kernel.org # v3.16+
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 1bfcfb1af352..d4427d0a0e18 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -264,7 +264,8 @@ struct css_set {
* List of csets participating in the on-going migration either as
* source or destination. Protected by cgroup_mutex.
*/
- struct list_head mg_preload_node;
+ struct list_head mg_src_preload_node;
+ struct list_head mg_dst_preload_node;
struct list_head mg_node;
/*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1779ccddb734..13c8e91d7862 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -765,7 +765,8 @@ struct css_set init_css_set = {
.task_iters = LIST_HEAD_INIT(init_css_set.task_iters),
.threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets),
.cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
- .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node),
+ .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node),
+ .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node),
.mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
/*
@@ -1240,7 +1241,8 @@ static struct css_set *find_css_set(struct css_set *old_cset,
INIT_LIST_HEAD(&cset->threaded_csets);
INIT_HLIST_NODE(&cset->hlist);
INIT_LIST_HEAD(&cset->cgrp_links);
- INIT_LIST_HEAD(&cset->mg_preload_node);
+ INIT_LIST_HEAD(&cset->mg_src_preload_node);
+ INIT_LIST_HEAD(&cset->mg_dst_preload_node);
INIT_LIST_HEAD(&cset->mg_node);
/* Copy the set of subsystem state objects generated in
@@ -2597,21 +2599,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp)
*/
void cgroup_migrate_finish(struct cgroup_mgctx *mgctx)
{
- LIST_HEAD(preloaded);
struct css_set *cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
- list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded);
- list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded);
+ list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets,
+ mg_src_preload_node) {
+ cset->mg_src_cgrp = NULL;
+ cset->mg_dst_cgrp = NULL;
+ cset->mg_dst_cset = NULL;
+ list_del_init(&cset->mg_src_preload_node);
+ put_css_set_locked(cset);
+ }
- list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) {
+ list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets,
+ mg_dst_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cgrp = NULL;
cset->mg_dst_cset = NULL;
- list_del_init(&cset->mg_preload_node);
+ list_del_init(&cset->mg_dst_preload_node);
put_css_set_locked(cset);
}
@@ -2651,7 +2659,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
if (src_cset->dead)
return;
- if (!list_empty(&src_cset->mg_preload_node))
+ if (!list_empty(&src_cset->mg_src_preload_node))
return;
src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
@@ -2664,7 +2672,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
src_cset->mg_src_cgrp = src_cgrp;
src_cset->mg_dst_cgrp = dst_cgrp;
get_css_set(src_cset);
- list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets);
+ list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets);
}
/**
@@ -2689,7 +2697,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
/* look up the dst cset for each src cset and link it to src */
list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
- mg_preload_node) {
+ mg_src_preload_node) {
struct css_set *dst_cset;
struct cgroup_subsys *ss;
int ssid;
@@ -2708,7 +2716,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
if (src_cset == dst_cset) {
src_cset->mg_src_cgrp = NULL;
src_cset->mg_dst_cgrp = NULL;
- list_del_init(&src_cset->mg_preload_node);
+ list_del_init(&src_cset->mg_src_preload_node);
put_css_set(src_cset);
put_css_set(dst_cset);
continue;
@@ -2716,8 +2724,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
src_cset->mg_dst_cset = dst_cset;
- if (list_empty(&dst_cset->mg_preload_node))
- list_add_tail(&dst_cset->mg_preload_node,
+ if (list_empty(&dst_cset->mg_dst_preload_node))
+ list_add_tail(&dst_cset->mg_dst_preload_node,
&mgctx->preloaded_dst_csets);
else
put_css_set(dst_cset);
@@ -2963,7 +2971,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
goto out_finish;
spin_lock_irq(&css_set_lock);
- list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) {
+ list_for_each_entry(src_cset, &mgctx.preloaded_src_csets,
+ mg_src_preload_node) {
struct task_struct *task, *ntask;
/* all tasks in src_csets need to be migrated */
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From e5c46fde75e43c15a29b40e5fc5641727f97ae47 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb(a)kernel.org>
Date: Thu, 30 Jun 2022 16:46:54 +0100
Subject: [PATCH] ARM: 9214/1: alignment: advance IT state after emulating
Thumb instruction
After emulating a misaligned load or store issued in Thumb mode, we have
to advance the IT state by hand, or it will get out of sync with the
actual instruction stream, which means we'll end up applying the wrong
condition code to subsequent instructions. This might corrupt the
program state rather catastrophically.
So borrow the it_advance() helper from the probing code, and use it on
CPSR if the emulated instruction is Thumb.
Cc: <stable(a)vger.kernel.org>
Reviewed-by: Linus Walleij <linus.walleij(a)linaro.org>
Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org>
Signed-off-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk>
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 93051e2f402c..1408a6a15d0e 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -163,5 +163,31 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs)
((current_stack_pointer | (THREAD_SIZE - 1)) - 7) - 1; \
})
+
+/*
+ * Update ITSTATE after normal execution of an IT block instruction.
+ *
+ * The 8 IT state bits are split into two parts in CPSR:
+ * ITSTATE<1:0> are in CPSR<26:25>
+ * ITSTATE<7:2> are in CPSR<15:10>
+ */
+static inline unsigned long it_advance(unsigned long cpsr)
+{
+ if ((cpsr & 0x06000400) == 0) {
+ /* ITSTATE<2:0> == 0 means end of IT block, so clear IT state */
+ cpsr &= ~PSR_IT_MASK;
+ } else {
+ /* We need to shift left ITSTATE<4:0> */
+ const unsigned long mask = 0x06001c00; /* Mask ITSTATE<4:0> */
+ unsigned long it = cpsr & mask;
+ it <<= 1;
+ it |= it >> (27 - 10); /* Carry ITSTATE<2> to correct place */
+ it &= mask;
+ cpsr &= ~mask;
+ cpsr |= it;
+ }
+ return cpsr;
+}
+
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 6f499559d193..f8dd0b3cc8e0 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -935,6 +935,9 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (type == TYPE_LDST)
do_alignment_finish_ldst(addr, instr, regs, offset);
+ if (thumb_mode(regs))
+ regs->ARM_cpsr = it_advance(regs->ARM_cpsr);
+
return 0;
bad_or_fault:
diff --git a/arch/arm/probes/decode.h b/arch/arm/probes/decode.h
index 973173598992..facc889d05ee 100644
--- a/arch/arm/probes/decode.h
+++ b/arch/arm/probes/decode.h
@@ -14,6 +14,7 @@
#include <linux/types.h>
#include <linux/stddef.h>
#include <asm/probes.h>
+#include <asm/ptrace.h>
#include <asm/kprobes.h>
void __init arm_probes_decode_init(void);
@@ -35,31 +36,6 @@ void __init find_str_pc_offset(void);
#endif
-/*
- * Update ITSTATE after normal execution of an IT block instruction.
- *
- * The 8 IT state bits are split into two parts in CPSR:
- * ITSTATE<1:0> are in CPSR<26:25>
- * ITSTATE<7:2> are in CPSR<15:10>
- */
-static inline unsigned long it_advance(unsigned long cpsr)
- {
- if ((cpsr & 0x06000400) == 0) {
- /* ITSTATE<2:0> == 0 means end of IT block, so clear IT state */
- cpsr &= ~PSR_IT_MASK;
- } else {
- /* We need to shift left ITSTATE<4:0> */
- const unsigned long mask = 0x06001c00; /* Mask ITSTATE<4:0> */
- unsigned long it = cpsr & mask;
- it <<= 1;
- it |= it >> (27 - 10); /* Carry ITSTATE<2> to correct place */
- it &= mask;
- cpsr &= ~mask;
- cpsr |= it;
- }
- return cpsr;
-}
-
static inline void __kprobes bx_write_pc(long pcv, struct pt_regs *regs)
{
long cpsr = regs->ARM_cpsr;
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From d5b36a4dbd06c5e8e36ca8ccc552f679069e2946 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg(a)redhat.com>
Date: Mon, 11 Jul 2022 18:16:25 +0200
Subject: [PATCH] fix race between exit_itimers() and /proc/pid/timers
As Chris explains, the comment above exit_itimers() is not correct,
we can race with proc_timers_seq_ops. Change exit_itimers() to clear
signal->posix_timers with ->siglock held.
Cc: <stable(a)vger.kernel.org>
Reported-by: chris(a)accessvector.net
Signed-off-by: Oleg Nesterov <oleg(a)redhat.com>
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/fs/exec.c b/fs/exec.c
index 0989fb8472a1..778123259e42 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1301,7 +1301,7 @@ int begin_new_exec(struct linux_binprm * bprm)
bprm->mm = NULL;
#ifdef CONFIG_POSIX_TIMERS
- exit_itimers(me->signal);
+ exit_itimers(me);
flush_itimer_signals();
#endif
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 505aaf9fe477..81cab4b01edc 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -85,7 +85,7 @@ static inline void exit_thread(struct task_struct *tsk)
extern __noreturn void do_group_exit(int);
extern void exit_files(struct task_struct *);
-extern void exit_itimers(struct signal_struct *);
+extern void exit_itimers(struct task_struct *);
extern pid_t kernel_clone(struct kernel_clone_args *kargs);
struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
diff --git a/kernel/exit.c b/kernel/exit.c
index f072959fcab7..64c938ce36fe 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -766,7 +766,7 @@ void __noreturn do_exit(long code)
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
- exit_itimers(tsk->signal);
+ exit_itimers(tsk);
#endif
if (tsk->mm)
setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1cd10b102c51..5dead89308b7 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1051,15 +1051,24 @@ static void itimer_delete(struct k_itimer *timer)
}
/*
- * This is called by do_exit or de_thread, only when there are no more
- * references to the shared signal_struct.
+ * This is called by do_exit or de_thread, only when nobody else can
+ * modify the signal->posix_timers list. Yet we need sighand->siglock
+ * to prevent the race with /proc/pid/timers.
*/
-void exit_itimers(struct signal_struct *sig)
+void exit_itimers(struct task_struct *tsk)
{
+ struct list_head timers;
struct k_itimer *tmr;
- while (!list_empty(&sig->posix_timers)) {
- tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
+ if (list_empty(&tsk->signal->posix_timers))
+ return;
+
+ spin_lock_irq(&tsk->sighand->siglock);
+ list_replace_init(&tsk->signal->posix_timers, &timers);
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ while (!list_empty(&timers)) {
+ tmr = list_first_entry(&timers, struct k_itimer, list);
itimer_delete(tmr);
}
}
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From d5b36a4dbd06c5e8e36ca8ccc552f679069e2946 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg(a)redhat.com>
Date: Mon, 11 Jul 2022 18:16:25 +0200
Subject: [PATCH] fix race between exit_itimers() and /proc/pid/timers
As Chris explains, the comment above exit_itimers() is not correct,
we can race with proc_timers_seq_ops. Change exit_itimers() to clear
signal->posix_timers with ->siglock held.
Cc: <stable(a)vger.kernel.org>
Reported-by: chris(a)accessvector.net
Signed-off-by: Oleg Nesterov <oleg(a)redhat.com>
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/fs/exec.c b/fs/exec.c
index 0989fb8472a1..778123259e42 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1301,7 +1301,7 @@ int begin_new_exec(struct linux_binprm * bprm)
bprm->mm = NULL;
#ifdef CONFIG_POSIX_TIMERS
- exit_itimers(me->signal);
+ exit_itimers(me);
flush_itimer_signals();
#endif
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 505aaf9fe477..81cab4b01edc 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -85,7 +85,7 @@ static inline void exit_thread(struct task_struct *tsk)
extern __noreturn void do_group_exit(int);
extern void exit_files(struct task_struct *);
-extern void exit_itimers(struct signal_struct *);
+extern void exit_itimers(struct task_struct *);
extern pid_t kernel_clone(struct kernel_clone_args *kargs);
struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
diff --git a/kernel/exit.c b/kernel/exit.c
index f072959fcab7..64c938ce36fe 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -766,7 +766,7 @@ void __noreturn do_exit(long code)
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
- exit_itimers(tsk->signal);
+ exit_itimers(tsk);
#endif
if (tsk->mm)
setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1cd10b102c51..5dead89308b7 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1051,15 +1051,24 @@ static void itimer_delete(struct k_itimer *timer)
}
/*
- * This is called by do_exit or de_thread, only when there are no more
- * references to the shared signal_struct.
+ * This is called by do_exit or de_thread, only when nobody else can
+ * modify the signal->posix_timers list. Yet we need sighand->siglock
+ * to prevent the race with /proc/pid/timers.
*/
-void exit_itimers(struct signal_struct *sig)
+void exit_itimers(struct task_struct *tsk)
{
+ struct list_head timers;
struct k_itimer *tmr;
- while (!list_empty(&sig->posix_timers)) {
- tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
+ if (list_empty(&tsk->signal->posix_timers))
+ return;
+
+ spin_lock_irq(&tsk->sighand->siglock);
+ list_replace_init(&tsk->signal->posix_timers, &timers);
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ while (!list_empty(&timers)) {
+ tmr = list_first_entry(&timers, struct k_itimer, list);
itimer_delete(tmr);
}
}
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From d5b36a4dbd06c5e8e36ca8ccc552f679069e2946 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg(a)redhat.com>
Date: Mon, 11 Jul 2022 18:16:25 +0200
Subject: [PATCH] fix race between exit_itimers() and /proc/pid/timers
As Chris explains, the comment above exit_itimers() is not correct,
we can race with proc_timers_seq_ops. Change exit_itimers() to clear
signal->posix_timers with ->siglock held.
Cc: <stable(a)vger.kernel.org>
Reported-by: chris(a)accessvector.net
Signed-off-by: Oleg Nesterov <oleg(a)redhat.com>
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/fs/exec.c b/fs/exec.c
index 0989fb8472a1..778123259e42 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1301,7 +1301,7 @@ int begin_new_exec(struct linux_binprm * bprm)
bprm->mm = NULL;
#ifdef CONFIG_POSIX_TIMERS
- exit_itimers(me->signal);
+ exit_itimers(me);
flush_itimer_signals();
#endif
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 505aaf9fe477..81cab4b01edc 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -85,7 +85,7 @@ static inline void exit_thread(struct task_struct *tsk)
extern __noreturn void do_group_exit(int);
extern void exit_files(struct task_struct *);
-extern void exit_itimers(struct signal_struct *);
+extern void exit_itimers(struct task_struct *);
extern pid_t kernel_clone(struct kernel_clone_args *kargs);
struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
diff --git a/kernel/exit.c b/kernel/exit.c
index f072959fcab7..64c938ce36fe 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -766,7 +766,7 @@ void __noreturn do_exit(long code)
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
- exit_itimers(tsk->signal);
+ exit_itimers(tsk);
#endif
if (tsk->mm)
setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1cd10b102c51..5dead89308b7 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1051,15 +1051,24 @@ static void itimer_delete(struct k_itimer *timer)
}
/*
- * This is called by do_exit or de_thread, only when there are no more
- * references to the shared signal_struct.
+ * This is called by do_exit or de_thread, only when nobody else can
+ * modify the signal->posix_timers list. Yet we need sighand->siglock
+ * to prevent the race with /proc/pid/timers.
*/
-void exit_itimers(struct signal_struct *sig)
+void exit_itimers(struct task_struct *tsk)
{
+ struct list_head timers;
struct k_itimer *tmr;
- while (!list_empty(&sig->posix_timers)) {
- tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
+ if (list_empty(&tsk->signal->posix_timers))
+ return;
+
+ spin_lock_irq(&tsk->sighand->siglock);
+ list_replace_init(&tsk->signal->posix_timers, &timers);
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ while (!list_empty(&timers)) {
+ tmr = list_first_entry(&timers, struct k_itimer, list);
itimer_delete(tmr);
}
}
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From d5b36a4dbd06c5e8e36ca8ccc552f679069e2946 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg(a)redhat.com>
Date: Mon, 11 Jul 2022 18:16:25 +0200
Subject: [PATCH] fix race between exit_itimers() and /proc/pid/timers
As Chris explains, the comment above exit_itimers() is not correct,
we can race with proc_timers_seq_ops. Change exit_itimers() to clear
signal->posix_timers with ->siglock held.
Cc: <stable(a)vger.kernel.org>
Reported-by: chris(a)accessvector.net
Signed-off-by: Oleg Nesterov <oleg(a)redhat.com>
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/fs/exec.c b/fs/exec.c
index 0989fb8472a1..778123259e42 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1301,7 +1301,7 @@ int begin_new_exec(struct linux_binprm * bprm)
bprm->mm = NULL;
#ifdef CONFIG_POSIX_TIMERS
- exit_itimers(me->signal);
+ exit_itimers(me);
flush_itimer_signals();
#endif
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 505aaf9fe477..81cab4b01edc 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -85,7 +85,7 @@ static inline void exit_thread(struct task_struct *tsk)
extern __noreturn void do_group_exit(int);
extern void exit_files(struct task_struct *);
-extern void exit_itimers(struct signal_struct *);
+extern void exit_itimers(struct task_struct *);
extern pid_t kernel_clone(struct kernel_clone_args *kargs);
struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
diff --git a/kernel/exit.c b/kernel/exit.c
index f072959fcab7..64c938ce36fe 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -766,7 +766,7 @@ void __noreturn do_exit(long code)
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
- exit_itimers(tsk->signal);
+ exit_itimers(tsk);
#endif
if (tsk->mm)
setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1cd10b102c51..5dead89308b7 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1051,15 +1051,24 @@ static void itimer_delete(struct k_itimer *timer)
}
/*
- * This is called by do_exit or de_thread, only when there are no more
- * references to the shared signal_struct.
+ * This is called by do_exit or de_thread, only when nobody else can
+ * modify the signal->posix_timers list. Yet we need sighand->siglock
+ * to prevent the race with /proc/pid/timers.
*/
-void exit_itimers(struct signal_struct *sig)
+void exit_itimers(struct task_struct *tsk)
{
+ struct list_head timers;
struct k_itimer *tmr;
- while (!list_empty(&sig->posix_timers)) {
- tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
+ if (list_empty(&tsk->signal->posix_timers))
+ return;
+
+ spin_lock_irq(&tsk->sighand->siglock);
+ list_replace_init(&tsk->signal->posix_timers, &timers);
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ while (!list_empty(&timers)) {
+ tmr = list_first_entry(&timers, struct k_itimer, list);
itimer_delete(tmr);
}
}