summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-12-13 19:29:45 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2022-12-13 19:29:45 -0800
commite2ca6ba6ba0152361aa4fcbf6067db71b2c7a770 (patch)
treef7ed7753a2e66486a4ffe0fbbf98404ec4ba2212 /kernel
parent7e68dd7d07a28faa2e6574dd6b9dbd90cdeaae91 (diff)
parentc45bc55a99957b20e4e0333bcd42e12d1833a7f5 (diff)
Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton: - More userfaultfs work from Peter Xu - Several convert-to-folios series from Sidhartha Kumar and Huang Ying - Some filemap cleanups from Vishal Moola - David Hildenbrand added the ability to selftest anon memory COW handling - Some cpuset simplifications from Liu Shixin - Addition of vmalloc tracing support by Uladzislau Rezki - Some pagecache folioifications and simplifications from Matthew Wilcox - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use it - Miguel Ojeda contributed some cleanups for our use of the __no_sanitize_thread__ gcc keyword. This series should have been in the non-MM tree, my bad - Naoya Horiguchi improved the interaction between memory poisoning and memory section removal for huge pages - DAMON cleanups and tuneups from SeongJae Park - Tony Luck fixed the handling of COW faults against poisoned pages - Peter Xu utilized the PTE marker code for handling swapin errors - Hugh Dickins reworked compound page mapcount handling, simplifying it and making it more efficient - Removal of the autonuma savedwrite infrastructure from Nadav Amit and David Hildenbrand - zram support for multiple compression streams from Sergey Senozhatsky - David Hildenbrand reworked the GUP code's R/O long-term pinning so that drivers no longer need to use the FOLL_FORCE workaround which didn't work very well anyway - Mel Gorman altered the page allocator so that local IRQs can remnain enabled during per-cpu page allocations - Vishal Moola removed the try_to_release_page() wrapper - Stefan Roesch added some per-BDI sysfs tunables which are used to prevent network block devices from dirtying excessive amounts of pagecache - David Hildenbrand did some cleanup and repair work on KSM COW breaking - Nhat Pham and Johannes Weiner have implemented writeback in zswap's zsmalloc backend - Brian Foster has fixed a longstanding corner-case oddity in file[map]_write_and_wait_range() - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang Chen - Shiyang Ruan has done some work on fsdax, to make its reflink mode work better under xfstests. Better, but still not perfect - Christoph Hellwig has removed the .writepage() method from several filesystems. They only need .writepages() - Yosry Ahmed wrote a series which fixes the memcg reclaim target beancounting - David Hildenbrand has fixed some of our MM selftests for 32-bit machines - Many singleton patches, as usual * tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits) mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio mm: mmu_gather: allow more than one batch of delayed rmaps mm: fix typo in struct pglist_data code comment kmsan: fix memcpy tests mm: add cond_resched() in swapin_walk_pmd_entry() mm: do not show fs mm pc for VM_LOCKONFAULT pages selftests/vm: ksm_functional_tests: fixes for 32bit selftests/vm: cow: fix compile warning on 32bit selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem mm,thp,rmap: fix races between updates of subpages_mapcount mm: memcg: fix swapcached stat accounting mm: add nodes= arg to memory.reclaim mm: disable top-tier fallback to reclaim on proactive reclaim selftests: cgroup: make sure reclaim target memcg is unprotected selftests: cgroup: refactor proactive reclaim code to reclaim_until() mm: memcg: fix stale protection of reclaim target memcg mm/mmap: properly unaccount memory on mas_preallocate() failure omfs: remove ->writepage jfs: remove ->writepage ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup/cpuset.c7
-rw-r--r--kernel/fork.c21
-rw-r--r--kernel/locking/Makefile1
-rw-r--r--kernel/sysctl.c1
4 files changed, 22 insertions, 8 deletions
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 589827ccda8b..a29c0b13706b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3660,11 +3660,6 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
return NOTIFY_OK;
}
-static struct notifier_block cpuset_track_online_nodes_nb = {
- .notifier_call = cpuset_track_online_nodes,
- .priority = 10, /* ??! */
-};
-
/**
* cpuset_init_smp - initialize cpus_allowed
*
@@ -3682,7 +3677,7 @@ void __init cpuset_init_smp(void)
cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask);
top_cpuset.effective_mems = node_states[N_MEMORY];
- register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
+ hotplug_memory_notifier(cpuset_track_online_nodes, CPUSET_CALLBACK_PRI);
cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0);
BUG_ON(!cpuset_migrate_mm_wq);
diff --git a/kernel/fork.c b/kernel/fork.c
index 89b8b6c08592..7a08025d2c99 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -756,8 +756,13 @@ static void check_mm(struct mm_struct *mm)
"Please make sure 'struct resident_page_types[]' is updated as well");
for (i = 0; i < NR_MM_COUNTERS; i++) {
- long x = atomic_long_read(&mm->rss_stat.count[i]);
+ long x = percpu_counter_sum(&mm->rss_stat[i]);
+ if (likely(!x))
+ continue;
+
+ /* Making sure this is not due to race with CPU offlining. */
+ x = percpu_counter_sum_all(&mm->rss_stat[i]);
if (unlikely(x))
pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n",
mm, resident_page_types[i], x);
@@ -782,6 +787,8 @@ static void check_mm(struct mm_struct *mm)
*/
void __mmdrop(struct mm_struct *mm)
{
+ int i;
+
BUG_ON(mm == &init_mm);
WARN_ON_ONCE(mm == current->mm);
WARN_ON_ONCE(mm == current->active_mm);
@@ -791,6 +798,9 @@ void __mmdrop(struct mm_struct *mm)
check_mm(mm);
put_user_ns(mm->user_ns);
mm_pasid_drop(mm);
+
+ for (i = 0; i < NR_MM_COUNTERS; i++)
+ percpu_counter_destroy(&mm->rss_stat[i]);
free_mm(mm);
}
EXPORT_SYMBOL_GPL(__mmdrop);
@@ -1110,6 +1120,8 @@ static void mm_init_uprobes_state(struct mm_struct *mm)
static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
struct user_namespace *user_ns)
{
+ int i;
+
mt_init_flags(&mm->mm_mt, MM_MT_FLAGS);
mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock);
atomic_set(&mm->mm_users, 1);
@@ -1151,10 +1163,17 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
if (init_new_context(p, mm))
goto fail_nocontext;
+ for (i = 0; i < NR_MM_COUNTERS; i++)
+ if (percpu_counter_init(&mm->rss_stat[i], 0, GFP_KERNEL_ACCOUNT))
+ goto fail_pcpu;
+
mm->user_ns = get_user_ns(user_ns);
lru_gen_init_mm(mm);
return mm;
+fail_pcpu:
+ while (i > 0)
+ percpu_counter_destroy(&mm->rss_stat[--i]);
fail_nocontext:
mm_free_pgd(mm);
fail_nopgd:
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index ea925731fa40..0db4093d17b8 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -7,7 +7,6 @@ obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
# Avoid recursion lockdep -> sanitizer -> ... -> lockdep.
KCSAN_SANITIZE_lockdep.o := n
-KMSAN_SANITIZE_lockdep.o := n
ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index a4d8e19e231a..137d4abe3eda 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2106,6 +2106,7 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
+ .extra2 = (void *)&page_cluster_max,
},
{
.procname = "dirtytime_expire_seconds",