[Devel] [PATCH RHEL7 COMMIT] asm-generic/tlb: Track which levels of the page tables have been cleared

[Vasily Averin]

The commit is pushed to "branch-rh7-3.10.0-1127.10.1.vz7.162.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-1127.10.1.vz7.162.13
------>
commit a67d2f03fd7fa7e727d060857a22c56ec858cdb9
Author: Will Deacon <will.deacon at arm.com>
Date:   Tue Jul 21 17:58:46 2020 +0300

    asm-generic/tlb: Track which levels of the page tables have been cleared
    
    It is common for architectures with hugepage support to require only a
    single TLB invalidation operation per hugepage during unmap(), rather than
    iterating through the mapping at a PAGE_SIZE increment. Currently,
    however, the level in the page table where the unmap() operation occurs
    is not stored in the mmu_gather structure, therefore forcing
    architectures to issue additional TLB invalidation operations or to give
    up and over-invalidate by e.g. invalidating the entire TLB.
    
    Ideally, we could add an interval rbtree to the mmu_gather structure,
    which would allow us to associate the correct mapping granule with the
    various sub-mappings within the range being invalidated. However, this
    is costly in terms of book-keeping and memory management, so instead we
    approximate by keeping track of the page table levels that are cleared
    and provide a means to query the smallest granule required for invalidation.
    
    Acked-by: Peter Zijlstra (Intel) <peterz at infradead.org>
    Acked-by: Nicholas Piggin <npiggin at gmail.com>
    Signed-off-by: Will Deacon <will.deacon at arm.com>
    
    https://jira.sw.ru/browse/PSBM-101300
    (cherry picked from commit a6d60245d6d9b1caf66b0d94419988c4836980af)
    Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 include/asm-generic/tlb.h | 41 ++++++++++++++++++++++++++++++++++++++---
 mm/memory.c               |  4 +++-
 2 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index bb8fd22ec20b3..e667f8e557d0e 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -113,6 +113,14 @@ struct mmu_gather {
 	 */
 	unsigned int		freed_tables : 1;
 
+	/*
+	 * at which levels have we cleared entries?
+	 */
+	unsigned int		cleared_ptes : 1;
+	unsigned int		cleared_pmds : 1;
+	unsigned int		cleared_puds : 1;
+	unsigned int		cleared_p4ds : 1;
+
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
@@ -151,6 +159,27 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	tlb->start = TASK_SIZE;
 	tlb->end = 0;
 	tlb->freed_tables = 0;
+	tlb->cleared_ptes = 0;
+	tlb->cleared_pmds = 0;
+	tlb->cleared_puds = 0;
+	tlb->cleared_p4ds = 0;
+}
+
+static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb)
+{
+	if (tlb->cleared_ptes)
+		return PAGE_SHIFT;
+	if (tlb->cleared_pmds)
+		return PMD_SHIFT;
+	if (tlb->cleared_puds)
+		return PUD_SHIFT;
+
+	return PAGE_SHIFT;
+}
+
+static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
+{
+	return 1UL << tlb_get_unmap_shift(tlb);
 }
 
 /*
@@ -188,6 +217,7 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 #define tlb_remove_tlb_entry(tlb, ptep, address)		\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->cleared_ptes = 1;				\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
@@ -202,6 +232,7 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)			\
 	do {								\
 		__tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE);	\
+		tlb->cleared_pmds = 1;					\
 		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);		\
 	} while (0)
 
@@ -216,13 +247,15 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 #define tlb_remove_pud_tlb_entry(tlb, pudp, address)			\
 	do {								\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		tlb->cleared_puds = 1;					\
 		__tlb_remove_pud_tlb_entry(tlb, pudp, address);		\
 	} while (0)
 
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
-		tlb->freed_tables = 1;			\
+		tlb->freed_tables = 1;				\
+		tlb->cleared_pmds = 1;				\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 
@@ -230,7 +263,8 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
-		tlb->freed_tables = 1;			\
+		tlb->freed_tables = 1;				\
+		tlb->cleared_p4ds = 1;				\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
@@ -238,7 +272,8 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
-		tlb->freed_tables = 1;
+		tlb->freed_tables = 1;				\
+		tlb->cleared_puds = 1;				\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 
diff --git a/mm/memory.c b/mm/memory.c
index 0ec7b1ffd434c..f4874a2b8be84 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -288,8 +288,10 @@ void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 {
 	struct mmu_gather_batch *batch, *next;
 
-	if (force)
+	if (force) {
+		__tlb_reset_range(tlb);
 		__tlb_adjust_range(tlb, start, end - start);
+	}
 
 	tlb_flush_mmu(tlb);