Merge tag 'irqchip-5.16' into irq/core

Merge irqchip updates for Linux 5.16 from Marc Zyngier:

- A large cross-arch rework to move irq_enter()/irq_exit() into
  the arch code, and removing it from the generic irq code.
  Thanks to Mark Rutland for the huge effort!

- A few irqchip drivers are made modular (broadcom, meson), because
  that's apparently a thing...

- A new driver for the Microchip External Interrupt Controller

- The irq_cpu_offline()/irq_cpu_online() API is now deprecated and
  can only be selected on the Cavium Octeon platform. Once this
  platform is removed, the API will be removed at the same time.

- A sprinkle of devm_* helper, as people seem to love that.

- The usual spattering of small fixes and minor improvements.

* tag 'irqchip-5.16': (912 commits)
  h8300: Fix linux/irqchip.h include mess
  dt-bindings: irqchip: renesas-irqc: Document r8a774e1 bindings
  MIPS: irq: Avoid an unused-variable error
  genirq: Hide irq_cpu_{on,off}line() behind a deprecated option
  irqchip/mips-gic: Get rid of the reliance on irq_cpu_online()
  MIPS: loongson64: Drop call to irq_cpu_offline()
  irq: remove handle_domain_{irq,nmi}()
  irq: remove CONFIG_HANDLE_DOMAIN_IRQ_IRQENTRY
  irq: riscv: perform irqentry in entry code
  irq: openrisc: perform irqentry in entry code
  irq: csky: perform irqentry in entry code
  irq: arm64: perform irqentry in entry code
  irq: arm: perform irqentry in entry code
  irq: add a (temporary) CONFIG_HANDLE_DOMAIN_IRQ_IRQENTRY
  irq: nds32: avoid CONFIG_HANDLE_DOMAIN_IRQ
  irq: arc: avoid CONFIG_HANDLE_DOMAIN_IRQ
  irq: add generic_handle_arch_irq()
  irq: unexport handle_irq_desc()
  irq: simplify handle_domain_{irq,nmi}()
  irq: mips: simplify do_domain_IRQ()
  ...

Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211029083332.3680101-1-maz@kernel.org

11 files changed, 54 insertions, 35 deletions

diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h
index 930e83bceef0..4eddcfa73996 100644
--- a/mm/damon/dbgfs-test.h
+++ b/mm/damon/dbgfs-test.h
@@ -20,27 +20,27 @@ static void damon_dbgfs_test_str_to_target_ids(struct kunit *test)
 	ssize_t nr_integers = 0, i;
 
 	question = "123";
-	answers = str_to_target_ids(question, strnlen(question, 128),
+	answers = str_to_target_ids(question, strlen(question),
 			&nr_integers);
 	KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers);
 	KUNIT_EXPECT_EQ(test, 123ul, answers[0]);
 	kfree(answers);
 
 	question = "123abc";
-	answers = str_to_target_ids(question, strnlen(question, 128),
+	answers = str_to_target_ids(question, strlen(question),
 			&nr_integers);
 	KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers);
 	KUNIT_EXPECT_EQ(test, 123ul, answers[0]);
 	kfree(answers);
 
 	question = "a123";
-	answers = str_to_target_ids(question, strnlen(question, 128),
+	answers = str_to_target_ids(question, strlen(question),
 			&nr_integers);
 	KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers);
 	kfree(answers);
 
 	question = "12 35";
-	answers = str_to_target_ids(question, strnlen(question, 128),
+	answers = str_to_target_ids(question, strlen(question),
 			&nr_integers);
 	KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers);
 	for (i = 0; i < nr_integers; i++)
@@ -48,7 +48,7 @@ static void damon_dbgfs_test_str_to_target_ids(struct kunit *test)
 	kfree(answers);
 
 	question = "12 35 46";
-	answers = str_to_target_ids(question, strnlen(question, 128),
+	answers = str_to_target_ids(question, strlen(question),
 			&nr_integers);
 	KUNIT_EXPECT_EQ(test, (ssize_t)3, nr_integers);
 	for (i = 0; i < nr_integers; i++)
@@ -56,7 +56,7 @@ static void damon_dbgfs_test_str_to_target_ids(struct kunit *test)
 	kfree(answers);
 
 	question = "12 35 abc 46";
-	answers = str_to_target_ids(question, strnlen(question, 128),
+	answers = str_to_target_ids(question, strlen(question),
 			&nr_integers);
 	KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers);
 	for (i = 0; i < 2; i++)
@@ -64,13 +64,13 @@ static void damon_dbgfs_test_str_to_target_ids(struct kunit *test)
 	kfree(answers);
 
 	question = "";
-	answers = str_to_target_ids(question, strnlen(question, 128),
+	answers = str_to_target_ids(question, strlen(question),
 			&nr_integers);
 	KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers);
 	kfree(answers);
 
 	question = "\n";
-	answers = str_to_target_ids(question, strnlen(question, 128),
+	answers = str_to_target_ids(question, strlen(question),
 			&nr_integers);
 	KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers);
 	kfree(answers);
diff --git a/mm/debug.c b/mm/debug.c
index e73fe0a8ec3d..fae0f81ad831 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -24,7 +24,9 @@ const char *migrate_reason_names[MR_TYPES] = {
 	"syscall_or_cpuset",
 	"mempolicy_mbind",
 	"numa_misplaced",
-	"cma",
+	"contig_range",
+	"longterm_pin",
+	"demotion",
 };
 
 const struct trace_print_flags pageflag_names[] = {
diff --git a/mm/ksm.c b/mm/ksm.c
index 025338128cd9..a5716fdec1aa 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -651,10 +651,8 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node)
 	 * from &migrate_nodes. This will verify that future list.h changes
 	 * don't break STABLE_NODE_DUP_HEAD. Only recent gcc can handle it.
 	 */
-#if defined(GCC_VERSION) && GCC_VERSION >= 40903
 	BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes);
 	BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1);
-#endif
 
 	if (stable_node->head == &migrate_nodes)
 		list_del(&stable_node->list);
diff --git a/mm/memblock.c b/mm/memblock.c
index 0ab5a749bfa6..184dcd2e5d99 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -472,7 +472,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 		kfree(old_array);
 	else if (old_array != memblock_memory_init_regions &&
 		 old_array != memblock_reserved_init_regions)
-		memblock_free(__pa(old_array), old_alloc_size);
+		memblock_free_ptr(old_array, old_alloc_size);
 
 	/*
 	 * Reserve the new array if that comes from the memblock.  Otherwise, we
@@ -796,6 +796,20 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
 }
 
 /**
+ * memblock_free_ptr - free boot memory allocation
+ * @ptr: starting address of the  boot memory allocation
+ * @size: size of the boot memory block in bytes
+ *
+ * Free boot memory block previously allocated by memblock_alloc_xx() API.
+ * The freeing memory will not be released to the buddy allocator.
+ */
+void __init_memblock memblock_free_ptr(void *ptr, size_t size)
+{
+	if (ptr)
+		memblock_free(__pa(ptr), size);
+}
+
+/**
  * memblock_free - free boot memory block
  * @base: phys starting address of the  boot memory block
  * @size: size of the boot memory block in bytes
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b762215d73eb..6da5020a8656 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -106,9 +106,6 @@ static bool do_memsw_account(void)
 /* memcg and lruvec stats flushing */
 static void flush_memcg_stats_dwork(struct work_struct *w);
 static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
-static void flush_memcg_stats_work(struct work_struct *w);
-static DECLARE_WORK(stats_flush_work, flush_memcg_stats_work);
-static DEFINE_PER_CPU(unsigned int, stats_flush_threshold);
 static DEFINE_SPINLOCK(stats_flush_lock);
 
 #define THRESHOLDS_EVENTS_TARGET 128
@@ -682,8 +679,6 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 
 	/* Update lruvec */
 	__this_cpu_add(pn->lruvec_stats_percpu->state[idx], val);
-	if (!(__this_cpu_inc_return(stats_flush_threshold) % MEMCG_CHARGE_BATCH))
-		queue_work(system_unbound_wq, &stats_flush_work);
 }
 
 /**
@@ -5361,11 +5356,6 @@ static void flush_memcg_stats_dwork(struct work_struct *w)
 	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ);
 }
 
-static void flush_memcg_stats_work(struct work_struct *w)
-{
-	mem_cgroup_flush_stats();
-}
-
 static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 54879c339024..3e6449f2102a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -306,6 +306,7 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page,
 		struct vm_area_struct *vma)
 {
 	unsigned long address = vma_address(page, vma);
+	unsigned long ret = 0;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
@@ -329,11 +330,10 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page,
 	if (pmd_devmap(*pmd))
 		return PMD_SHIFT;
 	pte = pte_offset_map(pmd, address);
-	if (!pte_present(*pte))
-		return 0;
-	if (pte_devmap(*pte))
-		return PAGE_SHIFT;
-	return 0;
+	if (pte_present(*pte) && pte_devmap(*pte))
+		ret = PAGE_SHIFT;
+	pte_unmap(pte);
+	return ret;
 }
 
 /*
@@ -1126,7 +1126,7 @@ static int page_action(struct page_state *ps, struct page *p,
  */
 static inline bool HWPoisonHandlable(struct page *page)
 {
-	return PageLRU(page) || __PageMovable(page);
+	return PageLRU(page) || __PageMovable(page) || is_free_buddy_page(page);
 }
 
 static int __get_hwpoison_page(struct page *page)
diff --git a/mm/memory.c b/mm/memory.c
index 25fc46e87214..adf9b9ef8277 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3403,6 +3403,7 @@ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start,
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
 	i_mmap_unlock_write(mapping);
 }
+EXPORT_SYMBOL_GPL(unmap_mapping_pages);
 
 /**
  * unmap_mapping_range - unmap the portion of all mmaps in the specified
diff --git a/mm/shmem.c b/mm/shmem.c
index 88742953532c..b5860f4a2738 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -490,9 +490,9 @@ bool shmem_is_huge(struct vm_area_struct *vma,
 	case SHMEM_HUGE_ALWAYS:
 		return true;
 	case SHMEM_HUGE_WITHIN_SIZE:
-		index = round_up(index, HPAGE_PMD_NR);
+		index = round_up(index + 1, HPAGE_PMD_NR);
 		i_size = round_up(i_size_read(inode), PAGE_SIZE);
-		if (i_size >= HPAGE_PMD_SIZE && (i_size >> PAGE_SHIFT) >= index)
+		if (i_size >> PAGE_SHIFT >= index)
 			return true;
 		fallthrough;
 	case SHMEM_HUGE_ADVISE:
diff --git a/mm/swap.c b/mm/swap.c
index 897200d27dd0..af3cad4e5378 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -620,7 +620,6 @@ void lru_add_drain_cpu(int cpu)
 		pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
 
 	activate_page_drain(cpu);
-	invalidate_bh_lrus_cpu(cpu);
 }
 
 /**
@@ -703,6 +702,20 @@ void lru_add_drain(void)
 	local_unlock(&lru_pvecs.lock);
 }
 
+/*
+ * It's called from per-cpu workqueue context in SMP case so
+ * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on
+ * the same cpu. It shouldn't be a problem in !SMP case since
+ * the core is only one and the locks will disable preemption.
+ */
+static void lru_add_and_bh_lrus_drain(void)
+{
+	local_lock(&lru_pvecs.lock);
+	lru_add_drain_cpu(smp_processor_id());
+	local_unlock(&lru_pvecs.lock);
+	invalidate_bh_lrus_cpu();
+}
+
 void lru_add_drain_cpu_zone(struct zone *zone)
 {
 	local_lock(&lru_pvecs.lock);
@@ -717,7 +730,7 @@ static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
 
 static void lru_add_drain_per_cpu(struct work_struct *dummy)
 {
-	lru_add_drain();
+	lru_add_and_bh_lrus_drain();
 }
 
 /*
@@ -858,7 +871,7 @@ void lru_cache_disable(void)
 	 */
 	__lru_add_drain_all(true);
 #else
-	lru_add_drain();
+	lru_add_and_bh_lrus_drain();
 #endif
 }
 
diff --git a/mm/util.c b/mm/util.c
index 499b6b5767ed..bacabe446906 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -787,7 +787,7 @@ int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
-	int new_policy;
+	int new_policy = -1;
 	int ret;
 
 	/*
@@ -805,7 +805,7 @@ int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
 		t = *table;
 		t.data = &new_policy;
 		ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
-		if (ret)
+		if (ret || new_policy == -1)
 			return ret;
 
 		mm_compute_batch(new_policy);
diff --git a/mm/workingset.c b/mm/workingset.c
index d4268d8e9a82..d5b81e4f4cbe 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -352,6 +352,7 @@ void workingset_refault(struct page *page, void *shadow)
 
 	inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file);
 
+	mem_cgroup_flush_stats();
 	/*
 	 * Compare the distance to the existing workingset size. We
 	 * don't activate pages that couldn't stay resident even if