Merge branch 'tlb/asm-generic' of git://git.kernel.org/pub/scm/linux/…

…kernel/git/arm64/linux into x86/mm

Pull in the generic mmu_gather changes from the ARM64 tree such that we
can put x86 specific things on top as well.

MAINTAINERS

@@ -9698,6 +9698,19 @@ S:	Maintained
 F:	arch/arm/boot/dts/mmp*
 F:	arch/arm/mach-mmp/
 
+MMU GATHER AND TLB INVALIDATION
+M:	Will Deacon <[email protected]>
+M:	"Aneesh Kumar K.V" <[email protected]>
+M:	Andrew Morton <[email protected]>
+M:	Nick Piggin <[email protected]>
+M:	Peter Zijlstra <[email protected]>
+L:	[email protected]
+L:	[email protected]
+S:	Maintained
+F:	arch/*/include/asm/tlb.h
+F:	include/asm-generic/tlb.h
+F:	mm/mmu_gather.c
+
 MN88472 MEDIA DRIVER
 M:	Antti Palosaari <[email protected]>
 L:	[email protected]

include/asm-generic/tlb.h

@@ -20,6 +20,8 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
+#ifdef CONFIG_MMU
+
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 /*
  * Semi RCU freeing of the page directories.
@@ -97,12 +99,30 @@ struct mmu_gather {
 #endif
 	unsigned long		start;
 	unsigned long		end;
-	/* we are in the middle of an operation to clear
-	 * a full mm and can make some optimizations */
-	unsigned int		fullmm : 1,
-	/* we have performed an operation which
-	 * requires a complete flush of the tlb */
-				need_flush_all : 1;
+	/*
+	 * we are in the middle of an operation to clear
+	 * a full mm and can make some optimizations
+	 */
+	unsigned int		fullmm : 1;
+
+	/*
+	 * we have performed an operation which
+	 * requires a complete flush of the tlb
+	 */
+	unsigned int		need_flush_all : 1;
+
+	/*
+	 * we have removed page directories
+	 */
+	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;
@@ -118,6 +138,7 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb,
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 			 unsigned long start, unsigned long end, bool force);
+void tlb_flush_mmu_free(struct mmu_gather *tlb);
 extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 				   int page_size);
 
@@ -137,6 +158,11 @@ 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 void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
@@ -186,6 +212,25 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 }
 #endif
 
+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;
+	if (tlb->cleared_p4ds)
+		return P4D_SHIFT;
+
+	return PAGE_SHIFT;
+}
+
+static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
+{
+	return 1UL << tlb_get_unmap_shift(tlb);
+}
+
 /*
  * In the case of tlb vma handling, we can optimise these away in the
  * case where we're doing a full MM flush.  When we're doing a munmap,
@@ -219,13 +264,19 @@ static inline void tlb_remove_check_page_size_change(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)
 
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	     \
-	do {							     \
-		__tlb_adjust_range(tlb, address, huge_page_size(h)); \
-		__tlb_remove_tlb_entry(tlb, ptep, address);	     \
+#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
+	do {							\
+		unsigned long _sz = huge_page_size(h);		\
+		__tlb_adjust_range(tlb, address, _sz);		\
+		if (_sz == PMD_SIZE)				\
+			tlb->cleared_pmds = 1;			\
+		else if (_sz == PUD_SIZE)			\
+			tlb->cleared_puds = 1;			\
+		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
 /**
@@ -239,6 +290,7 @@ static inline void tlb_remove_check_page_size_change(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)
 
@@ -253,6 +305,7 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #define tlb_remove_pud_tlb_entry(tlb, pudp, address)			\
 	do {								\
 		__tlb_adjust_range(tlb, address, HPAGE_PUD_SIZE);	\
+		tlb->cleared_puds = 1;					\
 		__tlb_remove_pud_tlb_entry(tlb, pudp, address);		\
 	} while (0)
 
@@ -278,14 +331,18 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;				\
+		tlb->cleared_pmds = 1;				\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 #endif
 
 #ifndef pmd_free_tlb
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;				\
+		tlb->cleared_puds = 1;				\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 #endif
@@ -295,6 +352,8 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;				\
+		tlb->cleared_p4ds = 1;				\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
@@ -304,12 +363,15 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #ifndef p4d_free_tlb
 #define p4d_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;				\
 		__p4d_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
 #endif
 
+#endif /* CONFIG_MMU */
+
 #define tlb_migrate_finish(mm) do {} while (0)
 
 #endif /* _ASM_GENERIC__TLB_H */

mm/Makefile

@@ -23,9 +23,9 @@ KCOV_INSTRUMENT_vmstat.o := n
 
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= gup.o highmem.o memory.o mincore.o \
-			   mlock.o mmap.o mprotect.o mremap.o msync.o \
-			   page_vma_mapped.o pagewalk.o pgtable-generic.o \
-			   rmap.o vmalloc.o
+			   mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \
+			   msync.o page_vma_mapped.o pagewalk.o \
+			   pgtable-generic.o rmap.o vmalloc.o
 
 
 ifdef CONFIG_CROSS_MEMORY_ATTACH