From b512719f771a82180211c9a315b8a7f628832b3d Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 26 Jul 2018 16:37:08 -0700
Subject: delayacct: fix crash in delayacct_blkio_end() after delayacct init
 failure

While forking, if delayacct init fails due to memory shortage, it
continues expecting all delayacct users to check task->delays pointer
against NULL before dereferencing it, which all of them used to do.

Commit c96f5471ce7d ("delayacct: Account blkio completion on the correct
task"), while updating delayacct_blkio_end() to take the target task
instead of always using %current, made the function test NULL on
%current->delays and then continue to operated on @p->delays.  If
%current succeeded init while @p didn't, it leads to the following
crash.

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
 IP: __delayacct_blkio_end+0xc/0x40
 PGD 8000001fd07e1067 P4D 8000001fd07e1067 PUD 1fcffbb067 PMD 0
 Oops: 0000 [#1] SMP PTI
 CPU: 4 PID: 25774 Comm: QIOThread0 Not tainted 4.16.0-9_fbk1_rc2_1180_g6b593215b4d7 #9
 RIP: 0010:__delayacct_blkio_end+0xc/0x40
 Call Trace:
  try_to_wake_up+0x2c0/0x600
  autoremove_wake_function+0xe/0x30
  __wake_up_common+0x74/0x120
  wake_up_page_bit+0x9c/0xe0
  mpage_end_io+0x27/0x70
  blk_update_request+0x78/0x2c0
  scsi_end_request+0x2c/0x1e0
  scsi_io_completion+0x20b/0x5f0
  blk_mq_complete_request+0xa2/0x100
  ata_scsi_qc_complete+0x79/0x400
  ata_qc_complete_multiple+0x86/0xd0
  ahci_handle_port_interrupt+0xc9/0x5c0
  ahci_handle_port_intr+0x54/0xb0
  ahci_single_level_irq_intr+0x3b/0x60
  __handle_irq_event_percpu+0x43/0x190
  handle_irq_event_percpu+0x20/0x50
  handle_irq_event+0x2a/0x50
  handle_edge_irq+0x80/0x1c0
  handle_irq+0xaf/0x120
  do_IRQ+0x41/0xc0
  common_interrupt+0xf/0xf

Fix it by updating delayacct_blkio_end() check @p->delays instead.

Link: http://lkml.kernel.org/r/20180724175542.GP1934745@devbig577.frc2.facebook.com
Fixes: c96f5471ce7d ("delayacct: Account blkio completion on the correct task")
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Dave Jones <dsj@fb.com>
Debugged-by: Dave Jones <dsj@fb.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Josh Snyder <joshs@netflix.com>
Cc: <stable@vger.kernel.org>	[4.15+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/delayacct.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index e6c0448ebcc7..31c865d1842e 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -124,7 +124,7 @@ static inline void delayacct_blkio_start(void)
 
 static inline void delayacct_blkio_end(struct task_struct *p)
 {
-	if (current->delays)
+	if (p->delays)
 		__delayacct_blkio_end(p);
 	delayacct_clear_flag(DELAYACCT_PF_BLKIO);
 }
-- 
cgit v1.2.3


From 03758dbbe2b5c0627b361ad5b4a2c60f9964ccde Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 26 Jul 2018 16:37:12 -0700
Subject: kasan: only select SLUB_DEBUG with SYSFS=y

Building with KASAN and SLUB but without sysfs now results in a
build-time error:

  WARNING: unmet direct dependencies detected for SLUB_DEBUG
    Depends on [n]: SLUB [=y] && SYSFS [=n]
    Selected by [y]:
    - KASAN [=y] && HAVE_ARCH_KASAN [=y] && (SLUB [=y] || SLAB [=n] && !DEBUG_SLAB [=n]) && SLUB [=y]
  mm/slub.c:4565:12: error: 'list_locations' defined but not used [-Werror=unused-function]
   static int list_locations(struct kmem_cache *s, char *buf,
              ^~~~~~~~~~~~~~
  mm/slub.c:4406:13: error: 'validate_slab_cache' defined but not used [-Werror=unused-function]
   static long validate_slab_cache(struct kmem_cache *s)

This disallows that broken configuration in Kconfig.

Link: http://lkml.kernel.org/r/20180709154019.1693026-1-arnd@arndb.de
Fixes: dd275caf4a0d ("kasan: depend on CONFIG_SLUB_DEBUG")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/Kconfig.kasan | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index c253c1b46c6b..befb127507c0 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -5,7 +5,7 @@ if HAVE_ARCH_KASAN
 
 config KASAN
 	bool "KASan: runtime memory debugger"
-	depends on SLUB || (SLAB && !DEBUG_SLAB)
+	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
 	select SLUB_DEBUG if SLUB
 	select CONSTRUCTORS
 	select STACKDEPOT
-- 
cgit v1.2.3


From 15d36fecd0bdc7510b70a0e5ec6671140b3fce0c Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 26 Jul 2018 16:37:15 -0700
Subject: mm: disallow mappings that conflict for devm_memremap_pages()

When pmem namespaces created are smaller than section size, this can
cause an issue during removal and gpf was observed:

  general protection fault: 0000 1 SMP PTI
  CPU: 36 PID: 3941 Comm: ndctl Tainted: G W 4.14.28-1.el7uek.x86_64 #2
  task: ffff88acda150000 task.stack: ffffc900233a4000
  RIP: 0010:__put_page+0x56/0x79
  Call Trace:
    devm_memremap_pages_release+0x155/0x23a
    release_nodes+0x21e/0x260
    devres_release_all+0x3c/0x48
    device_release_driver_internal+0x15c/0x207
    device_release_driver+0x12/0x14
    unbind_store+0xba/0xd8
    drv_attr_store+0x27/0x31
    sysfs_kf_write+0x3f/0x46
    kernfs_fop_write+0x10f/0x18b
    __vfs_write+0x3a/0x16d
    vfs_write+0xb2/0x1a1
    SyS_write+0x55/0xb9
    do_syscall_64+0x79/0x1ae
    entry_SYSCALL_64_after_hwframe+0x3d/0x0

Add code to check whether we have a mapping already in the same section
and prevent additional mappings from being created if that is the case.

Link: http://lkml.kernel.org/r/152909478401.50143.312364396244072931.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Robert Elliott <elliott@hpe.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/memremap.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5857267a4af5..a734b1747466 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
+	struct dev_pagemap *conflict_pgmap;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
 		- align_start;
+	align_end = align_start + align_size - 1;
+
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
+	if (conflict_pgmap) {
+		dev_WARN(dev, "Conflicting mapping in same section\n");
+		put_dev_pagemap(conflict_pgmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
+	if (conflict_pgmap) {
+		dev_WARN(dev, "Conflicting mapping in same section\n");
+		put_dev_pagemap(conflict_pgmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	is_ram = region_intersects(align_start, align_size,
 		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
@@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
-	align_end = align_start + align_size - 1;
 
 	foreach_order_pgoff(res, order, pgoff) {
 		error = __radix_tree_insert(&pgmap_radix,
-- 
cgit v1.2.3


From f075faa300acc4f6301e348acde0a4580ed5f77c Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Thu, 26 Jul 2018 16:37:19 -0700
Subject: ipc/sem.c: prevent queue.status tearing in semop

In order for load/store tearing prevention to work, _all_ accesses to
the variable in question need to be done around READ and WRITE_ONCE()
macros.  Ensure everyone does so for q->status variable for
semtimedop().

Link: http://lkml.kernel.org/r/20180717052654.676-1-dave@stgolabs.net
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 ipc/sem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ipc/sem.c b/ipc/sem.c
index 5af1943ad782..76e95e4f3aa2 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -2118,7 +2118,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops,
 	}
 
 	do {
-		queue.status = -EINTR;
+		WRITE_ONCE(queue.status, -EINTR);
 		queue.sleeper = current;
 
 		__set_current_state(TASK_INTERRUPTIBLE);
-- 
cgit v1.2.3


From 31c5bda3a656089f01963d290a40ccda181f816e Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 26 Jul 2018 16:37:22 -0700
Subject: mm: fix exports that inadvertently make put_page() EXPORT_SYMBOL_GPL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit e76384884344 ("mm: introduce MEMORY_DEVICE_FS_DAX and
CONFIG_DEV_PAGEMAP_OPS") added two EXPORT_SYMBOL_GPL() symbols, but
these symbols are required by the inlined put_page(), thus accidentally
making put_page() a GPL export only.  This breaks OpenAFS (at least).

Mark them EXPORT_SYMBOL() instead.

Link: http://lkml.kernel.org/r/153128611970.2928.11310692420711601254.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: e76384884344 ("mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reported-by: Joe Gorse <jhgorse@gmail.com>
Reported-by: John Hubbard <jhubbard@nvidia.com>
Tested-by: Joe Gorse <jhgorse@gmail.com>
Tested-by: John Hubbard <jhubbard@nvidia.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Mark Vitale <mvitale@sinenomine.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/memremap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/memremap.c b/kernel/memremap.c
index a734b1747466..38283363da06 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -321,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
 DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL_GPL(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
 static atomic_t devmap_enable;
 
 /*
@@ -362,5 +362,5 @@ void __put_devmap_managed_page(struct page *page)
 	} else if (!count)
 		__put_page(page);
 }
-EXPORT_SYMBOL_GPL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page);
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
-- 
cgit v1.2.3


From 027232da7c7c1c7f04383f93bd798e475dde5285 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 26 Jul 2018 16:37:25 -0700
Subject: mm: introduce vma_init()

Not all VMAs allocated with vm_area_alloc().  Some of them allocated on
stack or in data segment.

The new helper can be use to initialize VMA properly regardless where it
was allocated.

Link: http://lkml.kernel.org/r/20180724121139.62570-2-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 6 ++++++
 kernel/fork.c      | 6 ++----
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index d3a3842316b8..31540f166987 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -452,6 +452,12 @@ struct vm_operations_struct {
 					  unsigned long addr);
 };
 
+static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
+{
+	vma->vm_mm = mm;
+	INIT_LIST_HEAD(&vma->anon_vma_chain);
+}
+
 struct mmu_gather;
 struct inode;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index a191c05e757d..1b27babc4c78 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -312,10 +312,8 @@ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
 
-	if (vma) {
-		vma->vm_mm = mm;
-		INIT_LIST_HEAD(&vma->anon_vma_chain);
-	}
+	if (vma)
+		vma_init(vma, mm);
 	return vma;
 }
 
-- 
cgit v1.2.3


From 2c4541e24c55e2847bede93e33d749280edd429a Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 26 Jul 2018 16:37:30 -0700
Subject: mm: use vma_init() to initialize VMAs on stack and data segments

Make sure to initialize all VMAs properly, not only those which come
from vm_area_cachep.

Link: http://lkml.kernel.org/r/20180724121139.62570-3-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/process.c    | 1 +
 arch/arm/mach-rpc/ecard.c    | 2 +-
 arch/arm64/include/asm/tlb.h | 4 +++-
 arch/arm64/mm/hugetlbpage.c  | 7 +++++--
 arch/ia64/include/asm/tlb.h  | 2 +-
 arch/ia64/mm/init.c          | 2 +-
 arch/x86/um/mem_32.c         | 2 +-
 fs/hugetlbfs/inode.c         | 2 ++
 mm/mempolicy.c               | 1 +
 mm/shmem.c                   | 1 +
 10 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 225d1c58d2de..d9c299133111 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -338,6 +338,7 @@ static struct vm_area_struct gate_vma = {
 
 static int __init gate_vma_init(void)
 {
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
 	return 0;
 }
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index 39aef4876ed4..8db62cc54a6a 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -237,8 +237,8 @@ static void ecard_init_pgtables(struct mm_struct *mm)
 
 	memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE));
 
+	vma_init(&vma, mm);
 	vma.vm_flags = VM_EXEC;
-	vma.vm_mm = mm;
 
 	flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE);
 	flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE);
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index ffdaea7954bb..d87f2d646caa 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -37,7 +37,9 @@ static inline void __tlb_remove_table(void *_table)
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+	struct vm_area_struct vma;
+
+	vma_init(&vma, tlb->mm);
 
 	/*
 	 * The ASID allocator will either invalidate the ASID or mark
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index ecc6818191df..1854e49aa18a 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -108,11 +108,13 @@ static pte_t get_clear_flush(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	struct vm_area_struct vma = { .vm_mm = mm };
+	struct vm_area_struct vma;
 	pte_t orig_pte = huge_ptep_get(ptep);
 	bool valid = pte_valid(orig_pte);
 	unsigned long i, saddr = addr;
 
+	vma_init(&vma, mm);
+
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
 		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
 
@@ -145,9 +147,10 @@ static void clear_flush(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	struct vm_area_struct vma = { .vm_mm = mm };
+	struct vm_area_struct vma;
 	unsigned long i, saddr = addr;
 
+	vma_init(&vma, mm);
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
 		pte_clear(mm, addr, ptep);
 
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 44f0ac0df308..db89e7306081 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -120,7 +120,7 @@ ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned
 		 */
 		struct vm_area_struct vma;
 
-		vma.vm_mm = tlb->mm;
+		vma_init(&vma, tlb->mm);
 		/* flush the address range from the tlb: */
 		flush_tlb_range(&vma, start, end);
 		/* now flush the virt. page-table area mapping the address range: */
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index bdb14a369137..e6c6dfd98de2 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -273,7 +273,7 @@ static struct vm_area_struct gate_vma;
 
 static int __init gate_vma_init(void)
 {
-	gate_vma.vm_mm = NULL;
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c
index 744afdc18cf3..56c44d865f7b 100644
--- a/arch/x86/um/mem_32.c
+++ b/arch/x86/um/mem_32.c
@@ -16,7 +16,7 @@ static int __init gate_vma_init(void)
 	if (!FIXADDR_USER_START)
 		return 0;
 
-	gate_vma.vm_mm = NULL;
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d508c7844681..40d4c66c7751 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -411,6 +411,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	bool truncate_op = (lend == LLONG_MAX);
 
 	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	vma_init(&pseudo_vma, current->mm);
 	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pagevec_init(&pvec);
 	next = start;
@@ -595,6 +596,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	 * as input to create an allocation policy.
 	 */
 	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	vma_init(&pseudo_vma, mm);
 	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pseudo_vma.vm_file = file;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 9ac49ef17b4e..01f1a14facc4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2505,6 +2505,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 
 		/* Create pseudo-vma that contains just the policy */
 		memset(&pvma, 0, sizeof(struct vm_area_struct));
+		vma_init(&pvma, NULL);
 		pvma.vm_end = TASK_SIZE;	/* policy covers entire file */
 		mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 2cab84403055..41b9bbf24e16 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1421,6 +1421,7 @@ static void shmem_pseudo_vma_init(struct vm_area_struct *vma,
 {
 	/* Create a pseudo vma that just contains the policy */
 	memset(vma, 0, sizeof(*vma));
+	vma_init(vma, NULL);
 	/* Bias interleave by inode number to distribute better across nodes */
 	vma->vm_pgoff = index + info->vfs_inode.i_ino;
 	vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index);
-- 
cgit v1.2.3


From bfd40eaff5abb9f62c8ef94ca13ed0d94a560f10 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 26 Jul 2018 16:37:35 -0700
Subject: mm: fix vma_is_anonymous() false-positives

vma_is_anonymous() relies on ->vm_ops being NULL to detect anonymous
VMA.  This is unreliable as ->mmap may not set ->vm_ops.

False-positive vma_is_anonymous() may lead to crashes:

	next ffff8801ce5e7040 prev ffff8801d20eca50 mm ffff88019c1e13c0
	prot 27 anon_vma ffff88019680cdd8 vm_ops 0000000000000000
	pgoff 0 file ffff8801b2ec2d00 private_data 0000000000000000
	flags: 0xff(read|write|exec|shared|mayread|maywrite|mayexec|mayshare)
	------------[ cut here ]------------
	kernel BUG at mm/memory.c:1422!
	invalid opcode: 0000 [#1] SMP KASAN
	CPU: 0 PID: 18486 Comm: syz-executor3 Not tainted 4.18.0-rc3+ #136
	Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google
	01/01/2011
	RIP: 0010:zap_pmd_range mm/memory.c:1421 [inline]
	RIP: 0010:zap_pud_range mm/memory.c:1466 [inline]
	RIP: 0010:zap_p4d_range mm/memory.c:1487 [inline]
	RIP: 0010:unmap_page_range+0x1c18/0x2220 mm/memory.c:1508
	Call Trace:
	 unmap_single_vma+0x1a0/0x310 mm/memory.c:1553
	 zap_page_range_single+0x3cc/0x580 mm/memory.c:1644
	 unmap_mapping_range_vma mm/memory.c:2792 [inline]
	 unmap_mapping_range_tree mm/memory.c:2813 [inline]
	 unmap_mapping_pages+0x3a7/0x5b0 mm/memory.c:2845
	 unmap_mapping_range+0x48/0x60 mm/memory.c:2880
	 truncate_pagecache+0x54/0x90 mm/truncate.c:800
	 truncate_setsize+0x70/0xb0 mm/truncate.c:826
	 simple_setattr+0xe9/0x110 fs/libfs.c:409
	 notify_change+0xf13/0x10f0 fs/attr.c:335
	 do_truncate+0x1ac/0x2b0 fs/open.c:63
	 do_sys_ftruncate+0x492/0x560 fs/open.c:205
	 __do_sys_ftruncate fs/open.c:215 [inline]
	 __se_sys_ftruncate fs/open.c:213 [inline]
	 __x64_sys_ftruncate+0x59/0x80 fs/open.c:213
	 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
	 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Reproducer:

	#include <stdio.h>
	#include <stddef.h>
	#include <stdint.h>
	#include <stdlib.h>
	#include <string.h>
	#include <sys/types.h>
	#include <sys/stat.h>
	#include <sys/ioctl.h>
	#include <sys/mman.h>
	#include <unistd.h>
	#include <fcntl.h>

	#define KCOV_INIT_TRACE			_IOR('c', 1, unsigned long)
	#define KCOV_ENABLE			_IO('c', 100)
	#define KCOV_DISABLE			_IO('c', 101)
	#define COVER_SIZE			(1024<<10)

	#define KCOV_TRACE_PC  0
	#define KCOV_TRACE_CMP 1

	int main(int argc, char **argv)
	{
		int fd;
		unsigned long *cover;

		system("mount -t debugfs none /sys/kernel/debug");
		fd = open("/sys/kernel/debug/kcov", O_RDWR);
		ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE);
		cover = mmap(NULL, COVER_SIZE * sizeof(unsigned long),
				PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
		munmap(cover, COVER_SIZE * sizeof(unsigned long));
		cover = mmap(NULL, COVER_SIZE * sizeof(unsigned long),
				PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
		memset(cover, 0, COVER_SIZE * sizeof(unsigned long));
		ftruncate(fd, 3UL << 20);
		return 0;
	}

This can be fixed by assigning anonymous VMAs own vm_ops and not relying
on it being NULL.

If ->mmap() failed to set ->vm_ops, mmap_region() will set it to
dummy_vm_ops.  This way we will have non-NULL ->vm_ops for all VMAs.

Link: http://lkml.kernel.org/r/20180724121139.62570-4-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: syzbot+3f84280d52be9b7083cc@syzkaller.appspotmail.com
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/char/mem.c | 1 +
 fs/exec.c          | 1 +
 include/linux/mm.h | 8 ++++++++
 mm/mmap.c          | 3 +++
 mm/nommu.c         | 2 ++
 5 files changed, 15 insertions(+)

diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index ffeb60d3434c..df66a9dd0aae 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -708,6 +708,7 @@ static int mmap_zero(struct file *file, struct vm_area_struct *vma)
 #endif
 	if (vma->vm_flags & VM_SHARED)
 		return shmem_zero_setup(vma);
+	vma_set_anonymous(vma);
 	return 0;
 }
 
diff --git a/fs/exec.c b/fs/exec.c
index 72e961a62adb..bdd0eacefdf5 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -293,6 +293,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	bprm->vma = vma = vm_area_alloc(mm);
 	if (!vma)
 		return -ENOMEM;
+	vma_set_anonymous(vma);
 
 	if (down_write_killable(&mm->mmap_sem)) {
 		err = -EINTR;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 31540f166987..7ba6d356d18f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -454,10 +454,18 @@ struct vm_operations_struct {
 
 static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 {
+	static const struct vm_operations_struct dummy_vm_ops = {};
+
 	vma->vm_mm = mm;
+	vma->vm_ops = &dummy_vm_ops;
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 }
 
+static inline void vma_set_anonymous(struct vm_area_struct *vma)
+{
+	vma->vm_ops = NULL;
+}
+
 struct mmu_gather;
 struct inode;
 
diff --git a/mm/mmap.c b/mm/mmap.c
index ff1944d8d458..17bbf4d3e24f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1778,6 +1778,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		error = shmem_zero_setup(vma);
 		if (error)
 			goto free_vma;
+	} else {
+		vma_set_anonymous(vma);
 	}
 
 	vma_link(mm, vma, prev, rb_link, rb_parent);
@@ -2983,6 +2985,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla
 		return -ENOMEM;
 	}
 
+	vma_set_anonymous(vma);
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 	vma->vm_pgoff = pgoff;
diff --git a/mm/nommu.c b/mm/nommu.c
index 1d22fdbf7d7c..9fc9e43335b6 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1145,6 +1145,8 @@ static int do_mmap_private(struct vm_area_struct *vma,
 		if (ret < len)
 			memset(base + ret, 0, len - ret);
 
+	} else {
+		vma_set_anonymous(vma);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From fa3fc2ad99b4f025446d1cff589a8d2dd7db92f2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 26 Jul 2018 16:37:38 -0700
Subject: include/linux/eventfd.h: include linux/errno.h

The new gasket staging driver ran into a randconfig build failure when
CONFIG_EVENTFD is disabled:

  In file included from drivers/staging/gasket/gasket_interrupt.h:11,
                   from drivers/staging/gasket/gasket_interrupt.c:4:
  include/linux/eventfd.h: In function 'eventfd_ctx_fdget':
  include/linux/eventfd.h:51:9: error: implicit declaration of function 'ERR_PTR' [-Werror=implicit-function-declaration]

I can't see anything wrong with including eventfd.h before err.h, so the
easiest fix is to make it possible to do this by including the file
where it is needed.

Link: http://lkml.kernel.org/r/20180724110737.3985088-1-arnd@arndb.de
Fixes: 9a69f5087ccc ("drivers/staging: Gasket driver framework + Apex driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/eventfd.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 7094718b653b..ffcc7724ca21 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -11,6 +11,7 @@
 
 #include <linux/fcntl.h>
 #include <linux/wait.h>
+#include <linux/err.h>
 
 /*
  * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
-- 
cgit v1.2.3


From 16e536ef47f567289a5699abee9ff7bb304bc12d Mon Sep 17 00:00:00 2001
From: Li Wang <liwang@redhat.com>
Date: Thu, 26 Jul 2018 16:37:42 -0700
Subject: zswap: re-check zswap_is_full() after do zswap_shrink()

/sys/../zswap/stored_pages keeps rising in a zswap test with
"zswap.max_pool_percent=0" parameter.  But it should not compress or
store pages any more since there is no space in the compressed pool.

Reproduce steps:
  1. Boot kernel with "zswap.enabled=1"
  2. Set the max_pool_percent to 0
      # echo 0 > /sys/module/zswap/parameters/max_pool_percent
  3. Do memory stress test to see if some pages have been compressed
      # stress --vm 1 --vm-bytes $mem_available"M" --timeout 60s
  4. Watching the 'stored_pages' number increasing or not

The root cause is:

  When zswap_max_pool_percent is set to 0 via kernel parameter,
  zswap_is_full() will always return true due to zswap_shrink().  But if
  the shinking is able to reclain a page successfully the code then
  proceeds to compressing/storing another page, so the value of
  stored_pages will keep changing.

To solve the issue, this patch adds a zswap_is_full() check again after
  zswap_shrink() to make sure it's now under the max_pool_percent, and to
  not compress/store if we reached the limit.

Link: http://lkml.kernel.org/r/20180530103936.17812-1-liwang@redhat.com
Signed-off-by: Li Wang <liwang@redhat.com>
Acked-by: Dan Streetman <ddstreet@ieee.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Huang Ying <huang.ying.caritas@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/zswap.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/mm/zswap.c b/mm/zswap.c
index 7d34e69507e3..cd91fd9d96b8 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1026,6 +1026,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 			ret = -ENOMEM;
 			goto reject;
 		}
+
+		/* A second zswap_is_full() check after
+		 * zswap_shrink() to make sure it's now
+		 * under the max_pool_percent
+		 */
+		if (zswap_is_full()) {
+			ret = -ENOMEM;
+			goto reject;
+		}
 	}
 
 	/* allocate entry */
-- 
cgit v1.2.3


From d97e5e6160c0e0a23963ec198c7cb1c69e6bf9e8 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Thu, 26 Jul 2018 16:37:45 -0700
Subject: kvm, mm: account shadow page tables to kmemcg
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The size of kvm's shadow page tables corresponds to the size of the
guest virtual machines on the system.  Large VMs can spend a significant
amount of memory as shadow page tables which can not be left as system
memory overhead.  So, account shadow page tables to the kmemcg.

[shakeelb@google.com: replace (GFP_KERNEL|__GFP_ACCOUNT) with GFP_KERNEL_ACCOUNT]
  Link: http://lkml.kernel.org/r/20180629140224.205849-1-shakeelb@google.com
Link: http://lkml.kernel.org/r/20180627181349.149778-1-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kvm/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d594690d8b95..6b8f11521c41 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
 	if (cache->nobjs >= min)
 		return 0;
 	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
-		page = (void *)__get_free_page(GFP_KERNEL);
+		page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
 		if (!page)
 			return -ENOMEM;
 		cache->objects[cache->nobjs++] = page;
-- 
cgit v1.2.3