mm/tlbbatch: rename and extend some functions

This patch does some preparation works to extend batched TLB flush to
arm64. Including:
- Extend set_tlb_ubc_flush_pending() and arch_tlbbatch_add_mm()
  to accept an additional argument for address, architectures
  like arm64 may need this for tlbi.
- Rename arch_tlbbatch_add_mm() to arch_tlbbatch_add_pending()
  to match its current function since we don't need to handle
  mm on architectures like arm64 and add_mm is not proper,
  add_pending will make sense to both as on x86 we're pending the
  TLB flush operations while on arm64 we're pending the synchronize
  operations.

This intends no functional changes on x86.

Link: https://lkml.kernel.org/r/20230717131004.12662-3-yangyicong@huawei.com
Tested-by: Yicong Yang <yangyicong@hisilicon.com>
Tested-by: Xin Hao <xhao@linux.alibaba.com>
Tested-by: Punit Agrawal <punit.agrawal@bytedance.com>
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Xin Hao <xhao@linux.alibaba.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Nadav Amit <namit@vmware.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Barry Song <baohua@kernel.org>
Cc: Darren Hart <darren@os.amperecomputing.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: lipeifeng <lipeifeng@oppo.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Steven Miao <realmz6@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zeng Tao <prime.zeng@hisilicon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cf2a1de5d3887345bce6d061f6c64f7c9a0f359f..1c7d3a36e16ccaac87faae867c4d9056c0a6f298 100644 (file)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -276,8 +276,9 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
        return atomic64_inc_return(&mm->context.tlb_gen);
 }
 
-static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
-                                       struct mm_struct *mm)
+static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+                                            struct mm_struct *mm,
+                                            unsigned long uaddr)
 {
        inc_mm_tlb_gen(mm);
        cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));

diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index 5414b5c6a10312042c36e398f2d0eecf3e3cf1be..aa44fff8bb9da2046995d5603ec3f54bc1a1e847 100644 (file)
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -52,8 +52,8 @@ struct tlbflush_unmap_batch {
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
        /*
         * The arch code makes the following promise: generic code can modify a
-        * PTE, then call arch_tlbbatch_add_mm() (which internally provides all
-        * needed barriers), then call arch_tlbbatch_flush(), and the entries
+        * PTE, then call arch_tlbbatch_add_pending() (which internally provides
+        * all needed barriers), then call arch_tlbbatch_flush(), and the entries
         * will be flushed on all CPUs by the time that arch_tlbbatch_flush()
         * returns.
         */

diff --git a/mm/rmap.c b/mm/rmap.c
index 7a479e22d288c88cbb4b7fdd4888404b67f4e1b4..f6fb821d56a82c954d54473fd77390ac5c260e95 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -642,7 +642,8 @@ void try_to_unmap_flush_dirty(void)
 #define TLB_FLUSH_BATCH_PENDING_LARGE                  \
        (TLB_FLUSH_BATCH_PENDING_MASK / 2)
 
-static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval)
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
+                                     unsigned long uaddr)
 {
        struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
        int batch;
@@ -651,7 +652,7 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval)
        if (!pte_accessible(mm, pteval))
                return;
 
-       arch_tlbbatch_add_mm(&tlb_ubc->arch, mm);
+       arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, uaddr);
        tlb_ubc->flush_required = true;
 
        /*
@@ -726,7 +727,8 @@ void flush_tlb_batched_pending(struct mm_struct *mm)
        }
 }
 #else
-static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval)
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
+                                     unsigned long uaddr)
 {
 }
 
@@ -1579,7 +1581,7 @@ 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);
+                               set_tlb_ubc_flush_pending(mm, pteval, address);
                        } else {
                                pteval = ptep_clear_flush(vma, address, pvmw.pte);
                        }
@@ -1962,7 +1964,7 @@ 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);
+                               set_tlb_ubc_flush_pending(mm, pteval, address);
                        } else {
                                pteval = ptep_clear_flush(vma, address, pvmw.pte);
                        }