[PATCH v2 2/2] mm/mmu_gather: send tlb_remove_table_smp_sync IPI only to MM CPUs

[Yair Podemsky]

Currently the tlb_remove_table_smp_sync IPI is sent to all CPUs
indiscriminately, this causes unnecessary work and delays notable in
real-time use-cases and isolated cpus.
This patch will limit this IPI on systems with ARCH_HAS_CPUMASK_BITS,
Where the IPI will only be sent to cpus referencing the affected mm.

Signed-off-by: Yair Podemsky <ypode...@redhat.com>
Suggested-by: David Hildenbrand <da...@redhat.com>
---
 include/asm-generic/tlb.h |  4 ++--
 mm/khugepaged.c           |  4 ++--
 mm/mmu_gather.c           | 17 ++++++++++++-----
 3 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index b46617207c93..0b6ba17cc8d3 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -222,7 +222,7 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void 
*table);
 #define tlb_needs_table_invalidate() (true)
 #endif
 
-void tlb_remove_table_sync_one(void);
+void tlb_remove_table_sync_one(struct mm_struct *mm);
 
 #else
 
@@ -230,7 +230,7 @@ void tlb_remove_table_sync_one(void);
 #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
 #endif
 
-static inline void tlb_remove_table_sync_one(void) { }
+static inline void tlb_remove_table_sync_one(struct mm_struct *mm) { }
 
 #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 6b9d39d65b73..3e5cb079d268 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1166,7 +1166,7 @@ static int collapse_huge_page(struct mm_struct *mm, 
unsigned long address,
        _pmd = pmdp_collapse_flush(vma, address, pmd);
        spin_unlock(pmd_ptl);
        mmu_notifier_invalidate_range_end(&range);
-       tlb_remove_table_sync_one();
+       tlb_remove_table_sync_one(mm);
 
        spin_lock(pte_ptl);
        result =  __collapse_huge_page_isolate(vma, address, pte, cc,
@@ -1525,7 +1525,7 @@ static void collapse_and_free_pmd(struct mm_struct *mm, 
struct vm_area_struct *v
                                addr + HPAGE_PMD_SIZE);
        mmu_notifier_invalidate_range_start(&range);
        pmd = pmdp_collapse_flush(vma, addr, pmdp);
-       tlb_remove_table_sync_one();
+       tlb_remove_table_sync_one(mm);
        mmu_notifier_invalidate_range_end(&range);
        mm_dec_nr_ptes(mm);
        page_table_check_pte_clear_range(mm, addr, pmd);
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index ea9683e12936..692d8175a88e 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -191,7 +191,13 @@ static void tlb_remove_table_smp_sync(void *arg)
        /* Simply deliver the interrupt */
 }
 
-void tlb_remove_table_sync_one(void)
+#ifdef CONFIG_ARCH_HAS_CPUMASK_BITS
+#define REMOVE_TABLE_IPI_MASK mm_cpumask(mm)
+#else
+#define REMOVE_TABLE_IPI_MASK cpu_online_mask
+#endif /* CONFIG_ARCH_HAS_CPUMASK_BITS */
+
+void tlb_remove_table_sync_one(struct mm_struct *mm)
 {
        /*
         * This isn't an RCU grace period and hence the page-tables cannot be
@@ -200,7 +206,8 @@ void tlb_remove_table_sync_one(void)
         * It is however sufficient for software page-table walkers that rely on
         * IRQ disabling.
         */
-       smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+       on_each_cpu_mask(REMOVE_TABLE_IPI_MASK, tlb_remove_table_smp_sync,
+                       NULL, true);
 }
 
 static void tlb_remove_table_rcu(struct rcu_head *head)
@@ -237,9 +244,9 @@ static inline void tlb_table_invalidate(struct mmu_gather 
*tlb)
        }
 }
 
-static void tlb_remove_table_one(void *table)
+static void tlb_remove_table_one(struct mm_struct *mm, void *table)
 {
-       tlb_remove_table_sync_one();
+       tlb_remove_table_sync_one(mm);
        __tlb_remove_table(table);
 }
 
@@ -262,7 +269,7 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
                *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | 
__GFP_NOWARN);
                if (*batch == NULL) {
                        tlb_table_invalidate(tlb);
-                       tlb_remove_table_one(table);
+                       tlb_remove_table_one(tlb->mm, table);
                        return;
                }
                (*batch)->nr = 0;
---
v2: replaced no REMOVE_TABLE_IPI_MASK REMOVE_TABLE_IPI_MASK to cpu_online_mask
-- 
2.39.3