aboutsummaryrefslogtreecommitdiff
path: root/include/linux/sched
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2020-11-04 18:14:52 +0100
committerThomas Gleixner <tglx@linutronix.de>2020-11-04 18:14:52 +0100
commit01be83eea08d6d9f9209843e2e084505fba4053f (patch)
tree95b456e1ac40399fd5f55b57ae0936643bea1836 /include/linux/sched
parent45ff510517f3b1354a3d9c273ad5e5e8d08312cb (diff)
parent9d820f68b2bdba5b2e7bf135123c3f57c5051d05 (diff)
downloadlinux-stericsson-01be83eea08d6d9f9209843e2e084505fba4053f.tar.gz
Merge branch 'core/urgent' into core/entry
Pick up the entry fix before further modifications.
Diffstat (limited to 'include/linux/sched')
-rw-r--r--include/linux/sched/coredump.h1
-rw-r--r--include/linux/sched/debug.h2
-rw-r--r--include/linux/sched/mm.h67
-rw-r--r--include/linux/sched/sd_flags.h156
-rw-r--r--include/linux/sched/task.h2
-rw-r--r--include/linux/sched/topology.h37
-rw-r--r--include/linux/sched/user.h3
7 files changed, 207 insertions, 61 deletions
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index ecdc6542070f..dfd82eab2902 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -72,6 +72,7 @@ static inline int get_dumpable(struct mm_struct *mm)
#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */
#define MMF_OOM_VICTIM 25 /* mm is the oom victim */
#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */
+#define MMF_MULTIPROCESS 27 /* mm is shared between processes */
#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP)
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index 00c45a0e6abe..ae51f4529fc9 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -43,7 +43,7 @@ extern void proc_sched_set_task(struct task_struct *p);
#endif
/* Attach to any functions which should be ignored in wchan output. */
-#define __sched __attribute__((__section__(".sched.text")))
+#define __sched __section(".sched.text")
/* Linker adds these: start and end of __sched functions */
extern char __sched_text_start[], __sched_text_end[];
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index f889e332912f..d5ece7a9a403 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,31 +49,6 @@ static inline void mmdrop(struct mm_struct *mm)
__mmdrop(mm);
}
-/*
- * This has to be called after a get_task_mm()/mmget_not_zero()
- * followed by taking the mmap_lock for writing before modifying the
- * vmas or anything the coredump pretends not to change from under it.
- *
- * It also has to be called when mmgrab() is used in the context of
- * the process, but then the mm_count refcount is transferred outside
- * the context of the process to run down_write() on that pinned mm.
- *
- * NOTE: find_extend_vma() called from GUP context is the only place
- * that can modify the "mm" (notably the vm_start/end) under mmap_lock
- * for reading and outside the context of the process, so it is also
- * the only case that holds the mmap_lock for reading that must call
- * this function. Generally if the mmap_lock is hold for reading
- * there's no need of this check after get_task_mm()/mmget_not_zero().
- *
- * This function can be obsoleted and the check can be removed, after
- * the coredump code will hold the mmap_lock for writing before
- * invoking the ->core_dump methods.
- */
-static inline bool mmget_still_valid(struct mm_struct *mm)
-{
- return likely(!mm->core_state);
-}
-
/**
* mmget() - Pin the address space associated with a &struct mm_struct.
* @mm: The address space to pin.
@@ -304,39 +279,38 @@ static inline void memalloc_nocma_restore(unsigned int flags)
#endif
#ifdef CONFIG_MEMCG
+DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
/**
- * memalloc_use_memcg - Starts the remote memcg charging scope.
+ * set_active_memcg - Starts the remote memcg charging scope.
* @memcg: memcg to charge.
*
* This function marks the beginning of the remote memcg charging scope. All the
* __GFP_ACCOUNT allocations till the end of the scope will be charged to the
* given memcg.
*
- * NOTE: This function is not nesting safe.
+ * NOTE: This function can nest. Users must save the return value and
+ * reset the previous value after their own charging scope is over.
*/
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
{
- WARN_ON_ONCE(current->active_memcg);
- current->active_memcg = memcg;
-}
+ struct mem_cgroup *old;
+
+ if (in_interrupt()) {
+ old = this_cpu_read(int_active_memcg);
+ this_cpu_write(int_active_memcg, memcg);
+ } else {
+ old = current->active_memcg;
+ current->active_memcg = memcg;
+ }
-/**
- * memalloc_unuse_memcg - Ends the remote memcg charging scope.
- *
- * This function marks the end of the remote memcg charging scope started by
- * memalloc_use_memcg().
- */
-static inline void memalloc_unuse_memcg(void)
-{
- current->active_memcg = NULL;
+ return old;
}
#else
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
-{
-}
-
-static inline void memalloc_unuse_memcg(void)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
{
+ return NULL;
}
#endif
@@ -348,10 +322,13 @@ enum {
MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5),
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6),
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7),
};
enum {
MEMBARRIER_FLAG_SYNC_CORE = (1U << 0),
+ MEMBARRIER_FLAG_RSEQ = (1U << 1),
};
#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
new file mode 100644
index 000000000000..34b21e971d77
--- /dev/null
+++ b/include/linux/sched/sd_flags.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sched-domains (multiprocessor balancing) flag declarations.
+ */
+
+#ifndef SD_FLAG
+# error "Incorrect import of SD flags definitions"
+#endif
+
+/*
+ * Hierarchical metaflags
+ *
+ * SHARED_CHILD: These flags are meant to be set from the base domain upwards.
+ * If a domain has this flag set, all of its children should have it set. This
+ * is usually because the flag describes some shared resource (all CPUs in that
+ * domain share the same resource), or because they are tied to a scheduling
+ * behaviour that we want to disable at some point in the hierarchy for
+ * scalability reasons.
+ *
+ * In those cases it doesn't make sense to have the flag set for a domain but
+ * not have it in (some of) its children: sched domains ALWAYS span their child
+ * domains, so operations done with parent domains will cover CPUs in the lower
+ * child domains.
+ *
+ *
+ * SHARED_PARENT: These flags are meant to be set from the highest domain
+ * downwards. If a domain has this flag set, all of its parents should have it
+ * set. This is usually for topology properties that start to appear above a
+ * certain level (e.g. domain starts spanning CPUs outside of the base CPU's
+ * socket).
+ */
+#define SDF_SHARED_CHILD 0x1
+#define SDF_SHARED_PARENT 0x2
+
+/*
+ * Behavioural metaflags
+ *
+ * NEEDS_GROUPS: These flags are only relevant if the domain they are set on has
+ * more than one group. This is usually for balancing flags (load balancing
+ * involves equalizing a metric between groups), or for flags describing some
+ * shared resource (which would be shared between groups).
+ */
+#define SDF_NEEDS_GROUPS 0x4
+
+/*
+ * Balance when about to become idle
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on exec
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on fork, clone
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on wakeup
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Consider waking task on waking CPU.
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ */
+SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD)
+
+/*
+ * Domain members have different CPU capacities
+ *
+ * SHARED_PARENT: Set from the topmost domain down to the first domain where
+ * asymmetry is detected.
+ * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups.
+ */
+SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Domain members share CPU capacity (i.e. SMT)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ * CPU capacity.
+ * NEEDS_GROUPS: Capacity is shared between groups.
+ */
+SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Domain members share CPU package resources (i.e. caches)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ * the same cache(s).
+ * NEEDS_GROUPS: Caches are shared between groups.
+ */
+SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Only a single load balancing instance
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE. Could be set from a
+ * different level upwards, but it doesn't change that if a
+ * domain has this flag set, then all of its parents need to have
+ * it too (otherwise the serialization doesn't make sense).
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
+ */
+SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Place busy tasks earlier in the domain
+ *
+ * SHARED_CHILD: Usually set on the SMT level. Technically could be set further
+ * up, but currently assumed to be set from the base domain
+ * upwards (see update_top_cache_domain()).
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Prefer to place tasks in a sibling domain
+ *
+ * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD
+ * flag, but cleared below domains with SD_ASYM_CPUCAPACITY.
+ *
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS)
+
+/*
+ * sched_groups of this level overlap
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: Overlaps can only exist with more than one group.
+ */
+SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Cross-node balancing
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
+ */
+SD_FLAG(SD_NUMA, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a98965007eef..85fb2f34c59b 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -83,7 +83,7 @@ extern void do_group_exit(int);
extern void exit_files(struct task_struct *);
extern void exit_itimers(struct signal_struct *);
-extern long _do_fork(struct kernel_clone_args *kargs);
+extern pid_t kernel_clone(struct kernel_clone_args *kargs);
struct task_struct *fork_idle(int);
struct mm_struct *copy_init_mm(void);
extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 820511289857..9ef7bf686a9f 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -11,20 +11,29 @@
*/
#ifdef CONFIG_SMP
-#define SD_BALANCE_NEWIDLE 0x0001 /* Balance when about to become idle */
-#define SD_BALANCE_EXEC 0x0002 /* Balance on exec */
-#define SD_BALANCE_FORK 0x0004 /* Balance on fork, clone */
-#define SD_BALANCE_WAKE 0x0008 /* Balance on wakeup */
-#define SD_WAKE_AFFINE 0x0010 /* Wake task to waking CPU */
-#define SD_ASYM_CPUCAPACITY 0x0020 /* Domain members have different CPU capacities */
-#define SD_SHARE_CPUCAPACITY 0x0040 /* Domain members share CPU capacity */
-#define SD_SHARE_POWERDOMAIN 0x0080 /* Domain members share power domain */
-#define SD_SHARE_PKG_RESOURCES 0x0100 /* Domain members share CPU pkg resources */
-#define SD_SERIALIZE 0x0200 /* Only a single load balancing instance */
-#define SD_ASYM_PACKING 0x0400 /* Place busy groups earlier in the domain */
-#define SD_PREFER_SIBLING 0x0800 /* Prefer to place tasks in a sibling domain */
-#define SD_OVERLAP 0x1000 /* sched_domains of this level overlap */
-#define SD_NUMA 0x2000 /* cross-node balancing */
+/* Generate SD flag indexes */
+#define SD_FLAG(name, mflags) __##name,
+enum {
+ #include <linux/sched/sd_flags.h>
+ __SD_FLAG_CNT,
+};
+#undef SD_FLAG
+/* Generate SD flag bits */
+#define SD_FLAG(name, mflags) name = 1 << __##name,
+enum {
+ #include <linux/sched/sd_flags.h>
+};
+#undef SD_FLAG
+
+#ifdef CONFIG_SCHED_DEBUG
+
+struct sd_flag_debug {
+ unsigned int meta_flags;
+ char *name;
+};
+extern const struct sd_flag_debug sd_flag_debug[];
+
+#endif
#ifdef CONFIG_SCHED_SMT
static inline int cpu_smt_flags(void)
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 917d88edb7b9..a8ec3b6093fc 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -36,6 +36,9 @@ struct user_struct {
defined(CONFIG_NET) || defined(CONFIG_IO_URING)
atomic_long_t locked_vm;
#endif
+#ifdef CONFIG_WATCH_QUEUE
+ atomic_t nr_watches; /* The number of watches this user currently has */
+#endif
/* Miscellaneous per-user rate limit */
struct ratelimit_state ratelimit;