Merge branch 'linus' into x86/urgent

Required to queue a dependent fix.

2 files changed, 187 insertions, 12 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ca3f3eae8980..87bf02d93a27 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -27,6 +27,7 @@
 #include <linux/signal_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
+#include <linux/rseq.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
@@ -741,7 +742,7 @@ struct task_struct {
 	pid_t				pid;
 	pid_t				tgid;
 
-#ifdef CONFIG_CC_STACKPROTECTOR
+#ifdef CONFIG_STACKPROTECTOR
 	/* Canary value for the -fstack-protector GCC feature: */
 	unsigned long			stack_canary;
 #endif
@@ -1047,6 +1048,17 @@ struct task_struct {
 	unsigned long			numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
 
+#ifdef CONFIG_RSEQ
+	struct rseq __user *rseq;
+	u32 rseq_len;
+	u32 rseq_sig;
+	/*
+	 * RmW on rseq_event_mask must be performed atomically
+	 * with respect to preemption.
+	 */
+	unsigned long rseq_event_mask;
+#endif
+
 	struct tlbflush_unmap_batch	tlb_ubc;
 
 	struct rcu_head			rcu;
@@ -1118,7 +1130,7 @@ struct task_struct {
 
 #ifdef CONFIG_KCOV
 	/* Coverage collection mode enabled for this task (0 if disabled): */
-	enum kcov_mode			kcov_mode;
+	unsigned int			kcov_mode;
 
 	/* Size of the kcov_area: */
 	unsigned int			kcov_size;
@@ -1512,6 +1524,7 @@ static inline int task_nice(const struct task_struct *p)
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
+extern int available_idle_cpu(int cpu);
 extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
 extern int sched_setattr(struct task_struct *, const struct sched_attr *);
@@ -1626,6 +1639,12 @@ static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
 	clear_ti_thread_flag(task_thread_info(tsk), flag);
 }
 
+static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag,
+					  bool value)
+{
+	update_ti_thread_flag(task_thread_info(tsk), flag, value);
+}
+
 static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
 	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
@@ -1661,7 +1680,6 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
  * explicit rescheduling in places that are safe. The return
  * value indicates whether a reschedule was done in fact.
  * cond_resched_lock() will drop the spinlock before scheduling,
- * cond_resched_softirq() will enable bhs before scheduling.
  */
 #ifndef CONFIG_PREEMPT
 extern int _cond_resched(void);
@@ -1681,13 +1699,6 @@ extern int __cond_resched_lock(spinlock_t *lock);
 	__cond_resched_lock(lock);				\
 })
 
-extern int __cond_resched_softirq(void);
-
-#define cond_resched_softirq() ({					\
-	___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
-	__cond_resched_softirq();					\
-})
-
 static inline void cond_resched_rcu(void)
 {
 #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
@@ -1764,4 +1775,126 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
+#ifdef CONFIG_RSEQ
+
+/*
+ * Map the event mask on the user-space ABI enum rseq_cs_flags
+ * for direct mask checks.
+ */
+enum rseq_event_mask_bits {
+	RSEQ_EVENT_PREEMPT_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT,
+	RSEQ_EVENT_SIGNAL_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT,
+	RSEQ_EVENT_MIGRATE_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT,
+};
+
+enum rseq_event_mask {
+	RSEQ_EVENT_PREEMPT	= (1U << RSEQ_EVENT_PREEMPT_BIT),
+	RSEQ_EVENT_SIGNAL	= (1U << RSEQ_EVENT_SIGNAL_BIT),
+	RSEQ_EVENT_MIGRATE	= (1U << RSEQ_EVENT_MIGRATE_BIT),
+};
+
+static inline void rseq_set_notify_resume(struct task_struct *t)
+{
+	if (t->rseq)
+		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+}
+
+void __rseq_handle_notify_resume(struct pt_regs *regs);
+
+static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+{
+	if (current->rseq)
+		__rseq_handle_notify_resume(regs);
+}
+
+static inline void rseq_signal_deliver(struct pt_regs *regs)
+{
+	preempt_disable();
+	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
+	preempt_enable();
+	rseq_handle_notify_resume(regs);
+}
+
+/* rseq_preempt() requires preemption to be disabled. */
+static inline void rseq_preempt(struct task_struct *t)
+{
+	__set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask);
+	rseq_set_notify_resume(t);
+}
+
+/* rseq_migrate() requires preemption to be disabled. */
+static inline void rseq_migrate(struct task_struct *t)
+{
+	__set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask);
+	rseq_set_notify_resume(t);
+}
+
+/*
+ * If parent process has a registered restartable sequences area, the
+ * child inherits. Only applies when forking a process, not a thread. In
+ * case a parent fork() in the middle of a restartable sequence, set the
+ * resume notifier to force the child to retry.
+ */
+static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
+{
+	if (clone_flags & CLONE_THREAD) {
+		t->rseq = NULL;
+		t->rseq_len = 0;
+		t->rseq_sig = 0;
+		t->rseq_event_mask = 0;
+	} else {
+		t->rseq = current->rseq;
+		t->rseq_len = current->rseq_len;
+		t->rseq_sig = current->rseq_sig;
+		t->rseq_event_mask = current->rseq_event_mask;
+		rseq_preempt(t);
+	}
+}
+
+static inline void rseq_execve(struct task_struct *t)
+{
+	t->rseq = NULL;
+	t->rseq_len = 0;
+	t->rseq_sig = 0;
+	t->rseq_event_mask = 0;
+}
+
+#else
+
+static inline void rseq_set_notify_resume(struct task_struct *t)
+{
+}
+static inline void rseq_handle_notify_resume(struct pt_regs *regs)
+{
+}
+static inline void rseq_signal_deliver(struct pt_regs *regs)
+{
+}
+static inline void rseq_preempt(struct task_struct *t)
+{
+}
+static inline void rseq_migrate(struct task_struct *t)
+{
+}
+static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
+{
+}
+static inline void rseq_execve(struct task_struct *t)
+{
+}
+
+#endif
+
+#ifdef CONFIG_DEBUG_RSEQ
+
+void rseq_syscall(struct pt_regs *regs);
+
+#else
+
+static inline void rseq_syscall(struct pt_regs *regs)
+{
+}
+
+#endif
+
 #endif
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 2c570cd934af..44d356f5e47c 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -28,7 +28,7 @@ extern struct mm_struct *mm_alloc(void);
  *
  * Use mmdrop() to release the reference acquired by mmgrab().
  *
- * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
  * of &mm_struct.mm_count vs &mm_struct.mm_users.
  */
 static inline void mmgrab(struct mm_struct *mm)
@@ -62,7 +62,7 @@ static inline void mmdrop(struct mm_struct *mm)
  *
  * Use mmput() to release the reference acquired by mmget().
  *
- * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
  * of &mm_struct.mm_count vs &mm_struct.mm_users.
  */
 static inline void mmget(struct mm_struct *mm)
@@ -163,13 +163,28 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 }
 
 #ifdef CONFIG_LOCKDEP
+extern void __fs_reclaim_acquire(void);
+extern void __fs_reclaim_release(void);
 extern void fs_reclaim_acquire(gfp_t gfp_mask);
 extern void fs_reclaim_release(gfp_t gfp_mask);
 #else
+static inline void __fs_reclaim_acquire(void) { }
+static inline void __fs_reclaim_release(void) { }
 static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
 static inline void fs_reclaim_release(gfp_t gfp_mask) { }
 #endif
 
+/**
+ * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
+ *
+ * This functions marks the beginning of the GFP_NOIO allocation scope.
+ * All further allocations will implicitly drop __GFP_IO flag and so
+ * they are safe for the IO critical section from the allocation recursion
+ * point of view. Use memalloc_noio_restore to end the scope with flags
+ * returned by this function.
+ *
+ * This function is safe to be used from any context.
+ */
 static inline unsigned int memalloc_noio_save(void)
 {
 	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
@@ -177,11 +192,30 @@ static inline unsigned int memalloc_noio_save(void)
 	return flags;
 }
 
+/**
+ * memalloc_noio_restore - Ends the implicit GFP_NOIO scope.
+ * @flags: Flags to restore.
+ *
+ * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
+ * Always make sure that that the given flags is the return value from the
+ * pairing memalloc_noio_save call.
+ */
 static inline void memalloc_noio_restore(unsigned int flags)
 {
 	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
 }
 
+/**
+ * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope.
+ *
+ * This functions marks the beginning of the GFP_NOFS allocation scope.
+ * All further allocations will implicitly drop __GFP_FS flag and so
+ * they are safe for the FS critical section from the allocation recursion
+ * point of view. Use memalloc_nofs_restore to end the scope with flags
+ * returned by this function.
+ *
+ * This function is safe to be used from any context.
+ */
 static inline unsigned int memalloc_nofs_save(void)
 {
 	unsigned int flags = current->flags & PF_MEMALLOC_NOFS;
@@ -189,6 +223,14 @@ static inline unsigned int memalloc_nofs_save(void)
 	return flags;
 }
 
+/**
+ * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope.
+ * @flags: Flags to restore.
+ *
+ * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
+ * Always make sure that that the given flags is the return value from the
+ * pairing memalloc_nofs_save call.
+ */
 static inline void memalloc_nofs_restore(unsigned int flags)
 {
 	current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags;