lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1540990801-4261-5-git-send-email-schwidefsky@de.ibm.com>
Date:   Wed, 31 Oct 2018 14:00:01 +0100
From:   Martin Schwidefsky <schwidefsky@...ibm.com>
To:     Li Wang <liwang@...hat.com>, Guenter Roeck <linux@...ck-us.net>,
        Janosch Frank <frankja@...ux.vnet.ibm.com>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Heiko Carstens <heiko.carstens@...ibm.com>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        Linux-MM <linux-mm@...ck.org>
Cc:     Martin Schwidefsky <schwidefsky@...ibm.com>
Subject: [PATCH 4/4] s390/mm: fix mis-accounting of pgtable_bytes

In case a fork or a clone system fails in copy_process and the error
handling does the mmput() at the bad_fork_cleanup_mm label, the
following warning messages will appear on the console:

  BUG: non-zero pgtables_bytes on freeing mm: 16384

The reason for that is the tricks we play with mm_inc_nr_puds() and
mm_inc_nr_pmds() in init_new_context().

A normal 64-bit process has 3 levels of page table, the p4d level and
the pud level are folded. On process termination the free_pud_range()
function in mm/memory.c will subtract 16KB from pgtable_bytes with a
mm_dec_nr_puds() call, but there actually is not really a pud table.

One issue with this is the fact that pgtable_bytes is usually off
by a few kilobytes, but the more severe problem is that for a failed
fork or clone the free_pgtables() function is not called. In this case
there is no mm_dec_nr_puds() or mm_dec_nr_pmds() that go together with
the mm_inc_nr_puds() and mm_inc_nr_pmds in init_new_context().
The pgtable_bytes will be off by 16384 or 32768 bytes and we get the
BUG message. The message itself is purely cosmetic, but annoying.

To fix this override the mm_pmd_folded, mm_pud_folded and mm_p4d_folded
function to check for the true size of the address space.

Reported-by: Li Wang <liwang@...hat.com>
Tested-by: Li Wang <liwang@...hat.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@...ibm.com>
---
 arch/s390/include/asm/mmu_context.h |  5 -----
 arch/s390/include/asm/pgalloc.h     |  6 +++---
 arch/s390/include/asm/pgtable.h     | 18 ++++++++++++++++++
 arch/s390/include/asm/tlb.h         |  6 +++---
 arch/s390/mm/pgalloc.c              |  1 +
 5 files changed, 25 insertions(+), 11 deletions(-)

diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index dbd689d..ccbb53e 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -46,8 +46,6 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.asce_limit = STACK_TOP_MAX;
 		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				   _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
-		/* pgd_alloc() did not account this pud */
-		mm_inc_nr_puds(mm);
 		break;
 	case -PAGE_SIZE:
 		/* forked 5-level task, set new asce with new_mm->pgd */
@@ -63,9 +61,6 @@ static inline int init_new_context(struct task_struct *tsk,
 		/* forked 2-level compat task, set new asce with new mm->pgd */
 		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
-		/* pgd_alloc() did not account this pmd */
-		mm_inc_nr_pmds(mm);
-		mm_inc_nr_puds(mm);
 	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index f0f9bcf..5ee7337 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -36,11 +36,11 @@ static inline void crst_table_init(unsigned long *crst, unsigned long entry)
 
 static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 {
-	if (mm->context.asce_limit <= _REGION3_SIZE)
+	if (mm_pmd_folded(mm))
 		return _SEGMENT_ENTRY_EMPTY;
-	if (mm->context.asce_limit <= _REGION2_SIZE)
+	if (mm_pud_folded(mm))
 		return _REGION3_ENTRY_EMPTY;
-	if (mm->context.asce_limit <= _REGION1_SIZE)
+	if (mm_p4d_folded(mm))
 		return _REGION2_ENTRY_EMPTY;
 	return _REGION1_ENTRY_EMPTY;
 }
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 411d435..0637324 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -493,6 +493,24 @@ static inline int is_module_addr(void *addr)
 				   _REGION_ENTRY_PROTECT | \
 				   _REGION_ENTRY_NOEXEC)
 
+static inline bool mm_p4d_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION1_SIZE;
+}
+#define mm_p4d_folded(mm) mm_p4d_folded(mm)
+
+static inline bool mm_pud_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION2_SIZE;
+}
+#define mm_pud_folded(mm) mm_pud_folded(mm)
+
+static inline bool mm_pmd_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION3_SIZE;
+}
+#define mm_pmd_folded(mm) mm_pmd_folded(mm)
+
 static inline int mm_has_pgste(struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 457b7ba..b31c779 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -136,7 +136,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION3_SIZE)
+	if (mm_pmd_folded(tlb->mm))
 		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	tlb_remove_table(tlb, pmd);
@@ -152,7 +152,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION1_SIZE)
+	if (mm_p4d_folded(tlb->mm))
 		return;
 	tlb_remove_table(tlb, p4d);
 }
@@ -167,7 +167,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION2_SIZE)
+	if (mm_pud_folded(tlb->mm))
 		return;
 	tlb_remove_table(tlb, pud);
 }
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 76d89ee..814f265 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -101,6 +101,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 			mm->context.asce_limit = _REGION1_SIZE;
 			mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				_ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+			mm_inc_nr_puds(mm);
 		} else {
 			crst_table_init(table, _REGION1_ENTRY_EMPTY);
 			pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd);
-- 
2.7.4

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ