diff mbox series

[RFC,v12,20/26] mm, fs: skip tlb flushes for luf'd filemap that already has been done

Message ID 20250220052027.58847-21-byungchul@sk.com (mailing list archive)
State New
Headers show
Series LUF(Lazy Unmap Flush) reducing tlb numbers over 90% | expand

Commit Message

Byungchul Park Feb. 20, 2025, 5:20 a.m. UTC 
For luf'd filemap, tlb shootdown is performed when updating page cache,
no matter whether tlb flushes required already has been done or not.

By storing luf meta data in struct address_space and updating the luf
meta data properly, we can skip unnecessary tlb flush.

Signed-off-by: Byungchul Park <byungchul@sk.com>
---
 fs/inode.c               |  1 +
 include/linux/fs.h       |  4 ++-
 include/linux/mm_types.h |  2 ++
 mm/memory.c              |  4 +--
 mm/rmap.c                | 59 +++++++++++++++++++++++++---------------
 mm/truncate.c            | 14 +++++-----
 mm/vmscan.c              |  2 +-
 7 files changed, 53 insertions(+), 33 deletions(-)
diff mbox series

Patch

diff --git a/fs/inode.c b/fs/inode.c
index 46fbd5b234822..e155e51be2d28 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -404,6 +404,7 @@  static void __address_space_init_once(struct address_space *mapping)
 	init_rwsem(&mapping->i_mmap_rwsem);
 	INIT_LIST_HEAD(&mapping->i_private_list);
 	spin_lock_init(&mapping->i_private_lock);
+	luf_batch_init(&mapping->luf_batch);
 	mapping->i_mmap = RB_ROOT_CACHED;
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ec88270221bfe..0cc588c704cd1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -461,6 +461,7 @@  extern const struct address_space_operations empty_aops;
  * @i_private_lock: For use by the owner of the address_space.
  * @i_private_list: For use by the owner of the address_space.
  * @i_private_data: For use by the owner of the address_space.
+ * @luf_batch: Data to track need of tlb flush by luf.
  */
 struct address_space {
 	struct inode		*host;
@@ -482,6 +483,7 @@  struct address_space {
 	struct list_head	i_private_list;
 	struct rw_semaphore	i_mmap_rwsem;
 	void *			i_private_data;
+	struct luf_batch	luf_batch;
 } __attribute__((aligned(sizeof(long)))) __randomize_layout;
 	/*
 	 * On most architectures that alignment is already the case; but
@@ -508,7 +510,7 @@  static inline int mapping_write_begin(struct file *file,
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
 	if (!ret)
-		luf_flush(0);
+		luf_flush_mapping(mapping);
 
 	return ret;
 }
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8de4c190ad514..c50cfc1c6282f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1279,10 +1279,12 @@  extern void tlb_finish_mmu(struct mmu_gather *tlb);
 void luf_flush(unsigned short luf_key);
 void luf_flush_mm(struct mm_struct *mm);
 void luf_flush_vma(struct vm_area_struct *vma);
+void luf_flush_mapping(struct address_space *mapping);
 #else
 static inline void luf_flush(unsigned short luf_key) {}
 static inline void luf_flush_mm(struct mm_struct *mm) {}
 static inline void luf_flush_vma(struct vm_area_struct *vma) {}
+static inline void luf_flush_mapping(struct address_space *mapping) {}
 #endif
 
 struct vm_fault;
diff --git a/mm/memory.c b/mm/memory.c
index b02f86b1adb91..c98af5e567e89 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6161,10 +6161,10 @@  vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	if (flush) {
 		/*
 		 * If it has a VM_SHARED mapping, all the mms involved
-		 * should be luf_flush'ed.
+		 * in the struct address_space should be luf_flush'ed.
 		 */
 		if (mapping)
-			luf_flush(0);
+			luf_flush_mapping(mapping);
 		luf_flush_mm(mm);
 	}
 
diff --git a/mm/rmap.c b/mm/rmap.c
index e0304dc74c3a7..0cb13e8fcd739 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -691,7 +691,7 @@  void fold_batch(struct tlbflush_unmap_batch *dst,
 #define NR_LUF_BATCH (1 << (sizeof(short) * 8))
 
 /*
- * Use 0th entry as accumulated batch.
+ * XXX: Reserve the 0th entry for later use.
  */
 struct luf_batch luf_batch[NR_LUF_BATCH];
 
@@ -936,7 +936,7 @@  void luf_flush_vma(struct vm_area_struct *vma)
 		mapping = vma->vm_file->f_mapping;
 
 	if (mapping)
-		luf_flush(0);
+		luf_flush_mapping(mapping);
 	luf_flush_mm(mm);
 }
 
@@ -962,6 +962,29 @@  void luf_flush_mm(struct mm_struct *mm)
 	try_to_unmap_flush();
 }
 
+void luf_flush_mapping(struct address_space *mapping)
+{
+	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
+	struct luf_batch *lb;
+	unsigned long flags;
+	unsigned long lb_ugen;
+
+	if (!mapping)
+		return;
+
+	lb = &mapping->luf_batch;
+	read_lock_irqsave(&lb->lock, flags);
+	fold_batch(tlb_ubc, &lb->batch, false);
+	lb_ugen = lb->ugen;
+	read_unlock_irqrestore(&lb->lock, flags);
+
+	if (arch_tlbbatch_diet(&tlb_ubc->arch, lb_ugen))
+		return;
+
+	try_to_unmap_flush();
+}
+EXPORT_SYMBOL(luf_flush_mapping);
+
 /*
  * Flush TLB entries for recently unmapped pages from remote CPUs. It is
  * important if a PTE was dirty when it was unmapped that it's flushed
@@ -1010,7 +1033,8 @@  void try_to_unmap_flush_dirty(void)
 
 static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
 				      unsigned long uaddr,
-				      struct vm_area_struct *vma)
+				      struct vm_area_struct *vma,
+				      struct address_space *mapping)
 {
 	struct tlbflush_unmap_batch *tlb_ubc;
 	int batch;
@@ -1032,27 +1056,15 @@  static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
 		tlb_ubc = &current->tlb_ubc;
 	else {
 		tlb_ubc = &current->tlb_ubc_ro;
+
 		fold_luf_batch_mm(&mm->luf_batch, mm);
+		if (mapping)
+			fold_luf_batch_mm(&mapping->luf_batch, mm);
 	}
 
 	arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, uaddr);
 	tlb_ubc->flush_required = true;
 
-	if (can_luf_test()) {
-		struct luf_batch *lb;
-		unsigned long flags;
-
-		/*
-		 * Accumulate to the 0th entry right away so that
-		 * luf_flush(0) can be uesed to properly perform pending
-		 * TLB flush once this unmapping is observed.
-		 */
-		lb = &luf_batch[0];
-		write_lock_irqsave(&lb->lock, flags);
-		__fold_luf_batch(lb, tlb_ubc, new_luf_ugen());
-		write_unlock_irqrestore(&lb->lock, flags);
-	}
-
 	/*
 	 * Ensure compiler does not re-order the setting of tlb_flush_batched
 	 * before the PTE is cleared.
@@ -1134,7 +1146,8 @@  void flush_tlb_batched_pending(struct mm_struct *mm)
 #else
 static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
 				      unsigned long uaddr,
-				      struct vm_area_struct *vma)
+				      struct vm_area_struct *vma,
+				      struct address_space *mapping)
 {
 }
 
@@ -1503,7 +1516,7 @@  int folio_mkclean(struct folio *folio)
 	/*
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
-	luf_flush(0);
+	luf_flush_mapping(mapping);
 
 	return cleaned;
 }
@@ -2037,6 +2050,7 @@  static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
 	unsigned long pfn;
 	unsigned long hsz = 0;
+	struct address_space *mapping = folio_mapping(folio);
 
 	/*
 	 * When racing against e.g. zap_pte_range() on another cpu,
@@ -2174,7 +2188,7 @@  static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				 */
 				pteval = ptep_get_and_clear(mm, address, pvmw.pte);
 
-				set_tlb_ubc_flush_pending(mm, pteval, address, vma);
+				set_tlb_ubc_flush_pending(mm, pteval, address, vma, mapping);
 			} else {
 				pteval = ptep_clear_flush(vma, address, pvmw.pte);
 			}
@@ -2414,6 +2428,7 @@  static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
 	unsigned long pfn;
 	unsigned long hsz = 0;
+	struct address_space *mapping = folio_mapping(folio);
 
 	/*
 	 * When racing against e.g. zap_pte_range() on another cpu,
@@ -2563,7 +2578,7 @@  static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				 */
 				pteval = ptep_get_and_clear(mm, address, pvmw.pte);
 
-				set_tlb_ubc_flush_pending(mm, pteval, address, vma);
+				set_tlb_ubc_flush_pending(mm, pteval, address, vma, mapping);
 			} else {
 				pteval = ptep_clear_flush(vma, address, pvmw.pte);
 			}
diff --git a/mm/truncate.c b/mm/truncate.c
index 14618c53f1910..f9a3416610231 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -128,7 +128,7 @@  void folio_invalidate(struct folio *folio, size_t offset, size_t length)
 	/*
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
-	luf_flush(0);
+	luf_flush_mapping(folio->mapping);
 }
 EXPORT_SYMBOL_GPL(folio_invalidate);
 
@@ -170,7 +170,7 @@  int truncate_inode_folio(struct address_space *mapping, struct folio *folio)
 	/*
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
-	luf_flush(0);
+	luf_flush_mapping(mapping);
 	return 0;
 }
 
@@ -220,7 +220,7 @@  bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 	/*
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
-	luf_flush(0);
+	luf_flush_mapping(folio->mapping);
 
 	if (!folio_test_large(folio))
 		return true;
@@ -282,7 +282,7 @@  long mapping_evict_folio(struct address_space *mapping, struct folio *folio)
 	/*
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
-	luf_flush(0);
+	luf_flush_mapping(mapping);
 
 	return ret;
 }
@@ -417,7 +417,7 @@  void truncate_inode_pages_range(struct address_space *mapping,
 	/*
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
-	luf_flush(0);
+	luf_flush_mapping(mapping);
 }
 EXPORT_SYMBOL(truncate_inode_pages_range);
 
@@ -537,7 +537,7 @@  unsigned long mapping_try_invalidate(struct address_space *mapping,
 	/*
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
-	luf_flush(0);
+	luf_flush_mapping(mapping);
 	return count;
 }
 
@@ -704,7 +704,7 @@  int invalidate_inode_pages2_range(struct address_space *mapping,
 	/*
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
-	luf_flush(0);
+	luf_flush_mapping(mapping);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ffc4a48710f1d..cbca027d2a10e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -836,7 +836,7 @@  long remove_mapping(struct address_space *mapping, struct folio *folio)
 	/*
 	 * Ensure to clean stale tlb entries for this mapping.
 	 */
-	luf_flush(0);
+	luf_flush_mapping(mapping);
 
 	return ret;
 }