[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200622081027.GM576888@hirez.programming.kicks-ass.net>
Date: Mon, 22 Jun 2020 10:10:27 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Kees Cook <keescook@...omium.org>,
Guenter Roeck <linux@...ck-us.net>,
Eric Biggers <ebiggers@...nel.org>, x86 <x86@...nel.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Ingo Molnar <mingo@...nel.org>
Subject: Re: [tip: sched/urgent] sched: Fix RANDSTRUCT build fail
On Sat, Jun 20, 2020 at 09:32:26AM -0700, Linus Torvalds wrote:
> Peter/Ingo?
I have the below (and a whole fair number of even more patches), but
I've been struggling with a possibly related NULL pointer deref, which
is why I've been holding off on landing this.
It looks like we finally have a handle on the NULL deref, and it isn't
related to the IPI stuff (as it was initially bisected to), so I'll go
polish that a bit and then push stuff (including the below) into
sched/urgent.
---
Subject: smp, irq_work: Continue smp_call_function*() and irq_work*() integration
From: Peter Zijlstra <peterz@...radead.org>
Date: Mon Jun 15 11:27:58 CEST 2020
Instead of relying on BUG_ON() to ensure the various data structures
line up, use a bunch of horrible unions.
Much of the union magic is to ensure irq_work and smp_call_function do
not (yet) see the members of their respective data structures change
name.
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Reviewed-by: Frederic Weisbecker <frederic@...nel.org>
---
include/linux/irq_work.h | 26 +++++-------------
include/linux/sched.h | 5 ---
include/linux/smp.h | 23 +++++-----------
include/linux/smp_types.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++
kernel/sched/core.c | 6 ++--
kernel/smp.c | 18 ------------
6 files changed, 86 insertions(+), 58 deletions(-)
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -2,7 +2,7 @@
#ifndef _LINUX_IRQ_WORK_H
#define _LINUX_IRQ_WORK_H
-#include <linux/llist.h>
+#include <linux/smp_types.h>
/*
* An entry can be in one of four states:
@@ -13,24 +13,14 @@
* busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed
*/
-/* flags share CSD_FLAG_ space */
-
-#define IRQ_WORK_PENDING BIT(0)
-#define IRQ_WORK_BUSY BIT(1)
-
-/* Doesn't want IPI, wait for tick: */
-#define IRQ_WORK_LAZY BIT(2)
-/* Run hard IRQ context, even on RT */
-#define IRQ_WORK_HARD_IRQ BIT(3)
-
-#define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY)
-
-/*
- * structure shares layout with single_call_data_t.
- */
struct irq_work {
- struct llist_node llnode;
- atomic_t flags;
+ union {
+ struct __call_single_node node;
+ struct {
+ struct llist_node llnode;
+ atomic_t flags;
+ };
+ };
void (*func)(struct irq_work *);
};
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -653,11 +653,8 @@ struct task_struct {
unsigned int ptrace;
#ifdef CONFIG_SMP
- struct {
- struct llist_node wake_entry;
- unsigned int wake_entry_type;
- };
int on_cpu;
+ struct __call_single_node wake_entry;
#ifdef CONFIG_THREAD_INFO_IN_TASK
/* Current CPU: */
unsigned int cpu;
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -12,29 +12,22 @@
#include <linux/list.h>
#include <linux/cpumask.h>
#include <linux/init.h>
-#include <linux/llist.h>
+#include <linux/smp_types.h>
typedef void (*smp_call_func_t)(void *info);
typedef bool (*smp_cond_func_t)(int cpu, void *info);
-enum {
- CSD_FLAG_LOCK = 0x01,
-
- /* IRQ_WORK_flags */
-
- CSD_TYPE_ASYNC = 0x00,
- CSD_TYPE_SYNC = 0x10,
- CSD_TYPE_IRQ_WORK = 0x20,
- CSD_TYPE_TTWU = 0x30,
- CSD_FLAG_TYPE_MASK = 0xF0,
-};
-
/*
* structure shares (partial) layout with struct irq_work
*/
struct __call_single_data {
- struct llist_node llist;
- unsigned int flags;
+ union {
+ struct __call_single_node node;
+ struct {
+ struct llist_node llist;
+ unsigned int flags;
+ };
+ };
smp_call_func_t func;
void *info;
};
--- /dev/null
+++ b/include/linux/smp_types.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_SMP_TYPES_H
+#define __LINUX_SMP_TYPES_H
+
+#include <linux/llist.h>
+
+enum {
+ CSD_FLAG_LOCK = 0x01,
+
+ IRQ_WORK_PENDING = 0x01,
+ IRQ_WORK_BUSY = 0x02,
+ IRQ_WORK_LAZY = 0x04, /* No IPI, wait for tick */
+ IRQ_WORK_HARD_IRQ = 0x08, /* IRQ context on PREEMPT_RT */
+
+ IRQ_WORK_CLAIMED = (IRQ_WORK_PENDING | IRQ_WORK_BUSY),
+
+ CSD_TYPE_ASYNC = 0x00,
+ CSD_TYPE_SYNC = 0x10,
+ CSD_TYPE_IRQ_WORK = 0x20,
+ CSD_TYPE_TTWU = 0x30,
+
+ CSD_FLAG_TYPE_MASK = 0xF0,
+};
+
+/*
+ * struct __call_single_node is the primary type on
+ * smp.c:call_single_queue.
+ *
+ * flush_smp_call_function_queue() only reads the type from
+ * __call_single_node::u_flags as a regular load, the above
+ * (anonymous) enum defines all the bits of this word.
+ *
+ * Other bits are not modified until the type is known.
+ *
+ * CSD_TYPE_SYNC/ASYNC:
+ * struct {
+ * struct llist_node node;
+ * unsigned int flags;
+ * smp_call_func_t func;
+ * void *info;
+ * };
+ *
+ * CSD_TYPE_IRQ_WORK:
+ * struct {
+ * struct llist_node node;
+ * atomic_t flags;
+ * void (*func)(struct irq_work *);
+ * };
+ *
+ * CSD_TYPE_TTWU:
+ * struct {
+ * struct llist_node node;
+ * unsigned int flags;
+ * };
+ *
+ */
+
+struct __call_single_node {
+ struct llist_node llist;
+ union {
+ unsigned int u_flags;
+ atomic_t a_flags;
+ };
+};
+
+#endif /* __LINUX_SMP_TYPES_H */
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2293,7 +2293,7 @@ void sched_ttwu_pending(void *arg)
rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
- llist_for_each_entry_safe(p, t, llist, wake_entry)
+ llist_for_each_entry_safe(p, t, llist, wake_entry.llist)
ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
rq_unlock_irqrestore(rq, &rf);
@@ -2322,7 +2322,7 @@ static void __ttwu_queue_wakelist(struct
p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
WRITE_ONCE(rq->ttwu_pending, 1);
- __smp_call_single_queue(cpu, &p->wake_entry);
+ __smp_call_single_queue(cpu, &p->wake_entry.llist);
}
void wake_up_if_idle(int cpu)
@@ -2774,7 +2774,7 @@ static void __sched_fork(unsigned long c
#endif
init_numa_balancing(clone_flags, p);
#ifdef CONFIG_SMP
- p->wake_entry_type = CSD_TYPE_TTWU;
+ p->wake_entry.u_flags = CSD_TYPE_TTWU;
#endif
}
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -671,24 +671,6 @@ void __init smp_init(void)
{
int num_nodes, num_cpus;
- /*
- * Ensure struct irq_work layout matches so that
- * flush_smp_call_function_queue() can do horrible things.
- */
- BUILD_BUG_ON(offsetof(struct irq_work, llnode) !=
- offsetof(struct __call_single_data, llist));
- BUILD_BUG_ON(offsetof(struct irq_work, func) !=
- offsetof(struct __call_single_data, func));
- BUILD_BUG_ON(offsetof(struct irq_work, flags) !=
- offsetof(struct __call_single_data, flags));
-
- /*
- * Assert the CSD_TYPE_TTWU layout is similar enough
- * for task_struct to be on the @call_single_queue.
- */
- BUILD_BUG_ON(offsetof(struct task_struct, wake_entry_type) - offsetof(struct task_struct, wake_entry) !=
- offsetof(struct __call_single_data, flags) - offsetof(struct __call_single_data, llist));
-
idle_threads_init();
cpuhp_threads_init();
Powered by blists - more mailing lists