summaryrefslogtreecommitdiff
path: root/include/linux
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2026-10-18 07:03:51 -1000
committerLinus Torvalds <torvalds@linux-foundation.org>2026-10-18 07:03:51 -1000
commitcf20e7f96ae688dd8611dd6dce8cb4a036fecc72 (patch)
tree6a82bded6a6e5af0e548c18b5e61db4f73b7ab5d /include/linux
parent32c52ec87d6245ee2d12ed5dd509e40062939b50 (diff)
parent7cbaa0f4579f48e92639c6abb761fdef8fbade47 (diff)
downloadlinux-cf20e7f96ae688dd8611dd6dce8cb4a036fecc72.tar.gz
linux-cf20e7f96ae688dd8611dd6dce8cb4a036fecc72.zip
Merge tag 'locking-urgent-2026-10-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking fixes from Ingo Molnar: - Fix FUT_OFF_MMSHARED futex hashing bug that can cause missed wakeups or spurious wakeups on futex-waiting tasks (Jann Horn) - Fix lockdep context tracking bug in the deferred hrtimer rearming entry code, which causes a lockdep chain leak that will eventually turn lockdep off (Mikhail Gavrilov) * tag 'locking-urgent-2026-10-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: entry: Account the deferred hrtimer rearm as hardirq context for lockdep futex: Fix mm reuse handling for FUT_OFF_MMSHARED
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/futex.h19
-rw-r--r--include/linux/futex_types.h2
-rw-r--r--include/linux/irq-entry-common.h23
3 files changed, 34 insertions, 10 deletions
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 18ed18d5cbc1..a895d8c69d66 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -23,28 +23,32 @@ struct task_struct;
* 01 : Shared futex (PTHREAD_PROCESS_SHARED)
* mapped on a file (reference on the underlying inode)
* 10 : Shared futex (PTHREAD_PROCESS_SHARED)
- * (but private mapping on an mm, and reference taken on it)
+ * (but private mapping on an mm)
*/
-#define FUT_OFF_INODE 1 /* We set bit 0 if key has a reference on inode */
-#define FUT_OFF_MMSHARED 2 /* We set bit 1 if key has a reference on mm */
+#define FUT_OFF_INODE 1 /* We set bit 0 if shared key identifies an inode */
+#define FUT_OFF_MMSHARED 2 /* We set bit 1 if shared key identifies an mm */
union futex_key {
+ /* For FUT_OFF_INODE */
struct {
u64 i_seq;
unsigned long pgoff;
unsigned int offset;
/* unsigned int node; */
} shared;
+
+ /* For FUT_OFF_MMSHARED or private */
struct {
union {
- struct mm_struct *mm;
- u64 __tmp;
+ struct mm_struct *mm; /* for private */
+ u64 mm_seq; /* for FUT_OFF_MMSHARED */
};
unsigned long address;
unsigned int offset;
/* unsigned int node; */
} private;
+
struct {
u64 ptr;
unsigned long word;
@@ -152,11 +156,10 @@ static inline void futex_set_vdso_cs_range(struct futex_mm_data *fd, unsigned in
static inline void futex_fixup_robust_unlock(struct pt_regs *regs) { }
#endif /* !CONFIG_FUTEX_ROBUST_UNLOCK */
-
-#if defined(CONFIG_FUTEX_PRIVATE_HASH) || defined(CONFIG_FUTEX_ROBUST_UNLOCK)
+#ifdef CONFIG_FUTEX
void futex_mm_init(struct mm_struct *mm);
#else
static inline void futex_mm_init(struct mm_struct *mm) { }
-#endif
+#endif /* !CONFIG_FUTEX */
#endif /* _LINUX_FUTEX_H */
diff --git a/include/linux/futex_types.h b/include/linux/futex_types.h
index d320c0571f0c..34b16f2828e7 100644
--- a/include/linux/futex_types.h
+++ b/include/linux/futex_types.h
@@ -85,10 +85,12 @@ struct futex_unlock_cs_ranges { };
* struct futex_mm_data - Futex related per MM data
* @phash: Futex private hash related data
* @unlock: Futex unlock VDSO critical sections
+ * @unique_id: Unique ID of the MM, for FUT_OFF_MMSHARED futexes
*/
struct futex_mm_data {
struct futex_mm_phash phash;
struct futex_unlock_cs_ranges unlock;
+ atomic64_t unique_id;
};
#else /* CONFIG_FUTEX */
struct futex_sched_data { };
diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h
index 0bb6c03481fa..c74b5c87e10f 100644
--- a/include/linux/irq-entry-common.h
+++ b/include/linux/irq-entry-common.h
@@ -468,6 +468,25 @@ static inline void irqentry_exit_to_kernel_mode_preempt(struct pt_regs *regs,
irqentry_exit_cond_resched();
}
+/*
+ * The deferred hrtimer rearm is the tail of the timer interrupt, moved to the
+ * interrupt return path so that it runs after a possible reschedule. By now
+ * irq_exit_rcu() has left lockdep's hardirq context. Re-enter it for the
+ * rearm, so that the hrtimer base lock and the timekeeping sequence count are
+ * not chained onto the locks held by the interrupted context, which would add
+ * new lock chains for every lock stack an interrupt hits.
+ *
+ * The rearm on return to user mode needs no such annotation: no locks are
+ * held there, so it uses the same lock chains as the rearm in hardirq
+ * context.
+ */
+static __always_inline void irqentry_hrtimer_rearm_deferred(void)
+{
+ lockdep_hardirq_enter();
+ hrtimer_rearm_deferred();
+ lockdep_hardirq_exit();
+}
+
/**
* irqentry_exit_to_kernel_mode_after_preempt - Establish trace, lockdep and RCU state
* @regs: Pointer to current's pt_regs
@@ -491,7 +510,7 @@ irqentry_exit_to_kernel_mode_after_preempt(struct pt_regs *regs, irqentry_state_
*/
if (state.exit_rcu) {
instrumentation_begin();
- hrtimer_rearm_deferred();
+ irqentry_hrtimer_rearm_deferred();
/* Tell the tracer that IRET will enable interrupts */
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare();
@@ -502,7 +521,7 @@ irqentry_exit_to_kernel_mode_after_preempt(struct pt_regs *regs, irqentry_state_
}
instrumentation_begin();
- hrtimer_rearm_deferred();
+ irqentry_hrtimer_rearm_deferred();
/* Covers both tracing and lockdep */
trace_hardirqs_on();
instrumentation_end();