It's necessary to monitor lockless pagetable walks, in order to avoid doing
THP splitting/collapsing during them.
Some methods rely on local_irq_{save,restore}, but that can be slow on
cases with a lot of cpus are used for the process.
In order to speedup some cases, I propose a refcount-based approach, that
counts the number of lockless pagetable walks happening on the process.
This method does not exclude the current irq-oriented method. It works as a
complement to skip unnecessary waiting.
start_lockless_pgtbl_walk(mm)
Insert before starting any lockless pgtable walk
end_lockless_pgtbl_walk(mm)
Insert after the end of any lockless pgtable walk
(Mostly after the ptep is last used)
running_lockless_pgtbl_walk(mm)
Returns the number of lockless pgtable walks running
Signed-off-by: Leonardo Bras <leonardo@xxxxxxxxxxxxx>
---
arch/powerpc/include/asm/book3s/64/mmu.h | 3 ++
arch/powerpc/mm/book3s64/mmu_context.c | 1 +
arch/powerpc/mm/book3s64/pgtable.c | 45 ++++++++++++++++++++++++
3 files changed, 49 insertions(+)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 23b83d3593e2..13b006e7dde4 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -116,6 +116,9 @@ typedef struct {
/* Number of users of the external (Nest) MMU */
atomic_t copros;
+ /* Number of running instances of lockless pagetable walk*/
+ atomic_t lockless_pgtbl_walk_count;
+
struct hash_mm_context *hash_context;
unsigned long vdso_base;
diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c
index 2d0cb5ba9a47..3dd01c0ca5be 100644
--- a/arch/powerpc/mm/book3s64/mmu_context.c
+++ b/arch/powerpc/mm/book3s64/mmu_context.c
@@ -200,6 +200,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
#endif
atomic_set(&mm->context.active_cpus, 0);
atomic_set(&mm->context.copros, 0);
+ atomic_set(&mm->context.lockless_pgtbl_walk_count, 0);
return 0;
}
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 7d0e0d0d22c4..6ba6195bff1b 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -98,6 +98,51 @@ void serialize_against_pte_lookup(struct mm_struct *mm)
smp_call_function_many(mm_cpumask(mm), do_nothing, NULL, 1);
}
+/*
+ * Counting method to monitor lockless pagetable walks:
+ * Uses start_lockless_pgtbl_walk and end_lockless_pgtbl_walk to track the
+ * number of lockless pgtable walks happening, and
+ * running_lockless_pgtbl_walk to return this value.
+ */
+
+/* start_lockless_pgtbl_walk: Must be inserted before a function call that does
+ * lockless pagetable walks, such as __find_linux_pte()
+ */
+void start_lockless_pgtbl_walk(struct mm_struct *mm)
+{
+ atomic_inc(&mm->context.lockless_pgtbl_walk_count);
+ /* Avoid reorder to garantee that the increment will happen before any
+ * part of the walkless pagetable walk after it.
+ */
+ smp_mb();
+}
+EXPORT_SYMBOL(start_lockless_pgtbl_walk);
+
+/*
+ * end_lockless_pgtbl_walk: Must be inserted after the last use of a pointer
+ * returned by a lockless pagetable walk, such as __find_linux_pte()
+*/
+void end_lockless_pgtbl_walk(struct mm_struct *mm)
+{
+ /* Avoid reorder to garantee that it will only decrement after the last
+ * use of the returned ptep from the lockless pagetable walk.
+ */
+ smp_mb();
+ atomic_dec(&mm->context.lockless_pgtbl_walk_count);
+}
+EXPORT_SYMBOL(end_lockless_pgtbl_walk);
+
+/*
+ * running_lockless_pgtbl_walk: Returns the number of lockless pagetable walks
+ * currently running. If it returns 0, there is no running pagetable walk, and
+ * THP split/collapse can be safely done. This can be used to avoid more
+ * expensive approaches like serialize_against_pte_lookup()
+ */
+int running_lockless_pgtbl_walk(struct mm_struct *mm)
+{
+ return atomic_read(&mm->context.lockless_pgtbl_walk_count);
+}
+
/*
* We use this to invalidate a pmdp entry before switching from a
* hugepte to regular pmd entry.
--
2.20.1
