hugetlbfs: flush TLBs correctly after huge_pmd_unshare

commit a4a118f2eead1d6c49e00765de89878288d4b890 upstream.

When __unmap_hugepage_range() calls to huge_pmd_unshare() succeed, a TLB
flush is missing.  This TLB flush must be performed before releasing the
i_mmap_rwsem, in order to prevent an unshared PMDs page from being
released and reused before the TLB flush took place.

Arguably, a comprehensive solution would use mmu_gather interface to
batch the TLB flushes and the PMDs page release, however it is not an
easy solution: (1) try_to_unmap_one() and try_to_migrate_one() also call
huge_pmd_unshare() and they cannot use the mmu_gather interface; and (2)
deferring the release of the page reference for the PMDs page until
after i_mmap_rwsem is dropeed can confuse huge_pmd_unshare() into
thinking PMDs are shared when they are not.

Fix __unmap_hugepage_range() by adding the missing TLB flush, and
forcing a flush when unshare is successful.

Fixes: 24669e58477e ("hugetlb: use mmu_gather instead of a temporary linked list for accumulating pages)" # 3.6
Signed-off-by: Nadav Amit <namit@vmware.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

5 files changed, 53 insertions, 0 deletions

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 3cadb726ec88..4bb55e4ce5d7 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -257,6 +257,14 @@ tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr
 	tlb_add_flush(tlb, addr);
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	tlb_add_flush(tlb, address);
+	tlb_add_flush(tlb, address + size - PMD_SIZE);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
 #define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 39d64e0df1de..249bdf1b4ea2 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -251,6 +251,16 @@ __tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long addre
 	tlb->end_addr = address + PAGE_SIZE;
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	if (tlb->start_addr > address)
+		tlb->start_addr = address;
+	if (tlb->end_addr < address + size)
+		tlb->end_addr = address + size;
+}
+
 #define tlb_migrate_finish(mm)	platform_tlb_migrate_finish(mm)
 
 #define tlb_start_vma(tlb, vma)			do { } while (0)
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 7a92e69c50bc..687a4567d4ad 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -97,6 +97,19 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	free_page_and_swap_cache(page);
 }
+static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
+				unsigned long address, unsigned long size)
+{
+	/*
+	 * the range might exceed the original range that was provided to
+	 * tlb_gather_mmu(), so we need to update it despite the fact it is
+	 * usually not updated.
+	 */
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + size)
+		tlb->end = address + size;
+}
 
 /*
  * pte_free_tlb frees a pte table and clears the CRSTE for the
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 62f80d2a9df9..3ee32d21fe9f 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -65,6 +65,16 @@ tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
 		tlb->end = address + PAGE_SIZE;
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + size)
+		tlb->end = address + size;
+}
+
 /*
  * 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,
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 16eb63fac57d..f9d7e92dbac9 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -110,6 +110,18 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	__tlb_remove_page(tlb, page);
 }
 
+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+		    unsigned long size)
+{
+	tlb->need_flush = 1;
+
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + size)
+		tlb->end = address + size;
+}
+
 /**
  * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
  *