Merge branch 'akpm' (patches from Andrew)

Merge even more updates from Andrew Morton:

 - a kernel-wide sweep of show_stack()

 - pagetable cleanups

 - abstract out accesses to mmap_sem - prep for mmap_sem scalability work

 - hch's user acess work

Subsystems affected by this patch series: debug, mm/pagemap, mm/maccess,
mm/documentation.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (93 commits)
  include/linux/cache.h: expand documentation over __read_mostly
  maccess: return -ERANGE when probe_kernel_read() fails
  x86: use non-set_fs based maccess routines
  maccess: allow architectures to provide kernel probing directly
  maccess: move user access routines together
  maccess: always use strict semantics for probe_kernel_read
  maccess: remove strncpy_from_unsafe
  tracing/kprobes: handle mixed kernel/userspace probes better
  bpf: rework the compat kernel probe handling
  bpf:bpf_seq_printf(): handle potentially unsafe format string better
  bpf: handle the compat string in bpf_trace_copy_string better
  bpf: factor out a bpf_trace_copy_string helper
  maccess: unify the probe kernel arch hooks
  maccess: remove probe_read_common and probe_write_common
  maccess: rename strnlen_unsafe_user to strnlen_user_nofault
  maccess: rename strncpy_from_unsafe_strict to strncpy_from_kernel_nofault
  maccess: rename strncpy_from_unsafe_user to strncpy_from_user_nofault
  maccess: update the top of file comment
  maccess: clarify kerneldoc comments
  maccess: remove duplicate kerneldoc comments
  ...

122 files changed, 190 insertions, 226 deletions

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 5287ab98b8c1..4da23e751bce 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -15,8 +15,7 @@
 #include <linux/nls.h>
 #include <linux/dma-mapping.h>
 #include <linux/platform_data/x86/apple.h>
-
-#include <asm/pgtable.h>
+#include <linux/pgtable.h>
 
 #include "internal.h"
 
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 2d8b9b91dee0..42c672f1584e 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -212,7 +212,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 		mm = alloc->vma_vm_mm;
 
 	if (mm) {
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 		vma = alloc->vma;
 	}
 
@@ -270,7 +270,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 		trace_binder_alloc_page_end(alloc, index);
 	}
 	if (mm) {
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		mmput(mm);
 	}
 	return 0;
@@ -303,7 +303,7 @@ err_page_ptr_cleared:
 	}
 err_no_vma:
 	if (mm) {
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		mmput(mm);
 	}
 	return vma ? -ENOMEM : -ESRCH;
@@ -932,8 +932,8 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 	mm = alloc->vma_vm_mm;
 	if (!mmget_not_zero(mm))
 		goto err_mmget;
-	if (!down_read_trylock(&mm->mmap_sem))
-		goto err_down_read_mmap_sem_failed;
+	if (!mmap_read_trylock(mm))
+		goto err_mmap_read_lock_failed;
 	vma = binder_alloc_get_vma(alloc);
 
 	list_lru_isolate(lru, item);
@@ -946,7 +946,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 
 		trace_binder_unmap_user_end(alloc, index);
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	mmput(mm);
 
 	trace_binder_unmap_kernel_start(alloc, index);
@@ -960,7 +960,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 	mutex_unlock(&alloc->mutex);
 	return LRU_REMOVED_RETRY;
 
-err_down_read_mmap_sem_failed:
+err_mmap_read_lock_failed:
 	mmput_async(mm);
 err_mmget:
 err_page_already_freed:
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index 8fbd36eb8941..f4ad7ce25ae8 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -25,6 +25,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/delay.h>
 #include <linux/firmware.h>
+#include <linux/pgtable.h>
 #include <asm/io.h>
 #include <asm/string.h>
 #include <asm/page.h>
@@ -40,7 +41,6 @@
 #include <asm/idprom.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/pgtable.h>
 #endif
 
 #if defined(CONFIG_ATM_FORE200E_USE_TASKLET) /* defer interrupt work to a tasklet */
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index bb98b813554f..9dd85bea4026 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -519,7 +519,7 @@ static void dpm_watchdog_handler(struct timer_list *t)
 	struct dpm_watchdog *wd = from_timer(wd, t, timer);
 
 	dev_emerg(wd->dev, "**** DPM device timeout ****\n");
-	show_stack(wd->tsk, NULL);
+	show_stack(wd->tsk, NULL, KERN_EMERG);
 	panic("%s %s: unrecoverable failure\n",
 		dev_driver_string(wd->dev), dev_name(wd->dev));
 }
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index 600430685e28..0e734802ee7c 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -35,10 +35,10 @@
 #include <linux/bitops.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/pgtable.h>
 
 #include <asm/setup.h>
 #include <asm/amigahw.h>
-#include <asm/pgtable.h>
 
 #include <linux/zorro.h>
 
diff --git a/drivers/char/agp/frontend.c b/drivers/char/agp/frontend.c
index 47098648502d..00ff5fcb808a 100644
--- a/drivers/char/agp/frontend.c
+++ b/drivers/char/agp/frontend.c
@@ -39,7 +39,6 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
-#include <asm/pgtable.h>
 #include "agp.h"
 
 struct agp_front_data agp_fe;
diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c
index 9e84239f88d4..3ffbb1c80c5c 100644
--- a/drivers/char/agp/generic.c
+++ b/drivers/char/agp/generic.c
@@ -42,7 +42,6 @@
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
 #endif
-#include <asm/pgtable.h>
 #include "agp.h"
 
 __u32 *agp_gatt_table;
diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c
index e5e5333f302d..cce2af5df7b4 100644
--- a/drivers/char/bsr.c
+++ b/drivers/char/bsr.c
@@ -17,7 +17,6 @@
 #include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 
 /*
diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c
index 7d583222e8fa..0fae33319d2e 100644
--- a/drivers/char/mspec.c
+++ b/drivers/char/mspec.c
@@ -39,7 +39,6 @@
 #include <linux/numa.h>
 #include <linux/refcount.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <linux/atomic.h>
 #include <asm/tlbflush.h>
 #include <asm/uncached.h>
@@ -65,7 +64,7 @@ enum mspec_page_type {
  * This structure is shared by all vma's that are split off from the
  * original vma when split_vma()'s are done.
  *
- * The refcnt is incremented atomically because mm->mmap_sem does not
+ * The refcnt is incremented atomically because mm->mmap_lock does not
  * protect in fork case where multiple tasks share the vma_data.
  */
 struct vma_data {
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 4264e64788c4..b45f8514dc82 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -34,6 +34,7 @@
 
 #include <linux/dma-resv.h>
 #include <linux/export.h>
+#include <linux/mm.h>
 #include <linux/sched/mm.h>
 
 /**
@@ -109,7 +110,7 @@ static int __init dma_resv_lockdep(void)
 
 	dma_resv_init(&obj);
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	ww_acquire_init(&ctx, &reservation_ww_class);
 	ret = dma_resv_lock(&obj, &ctx);
 	if (ret == -EDEADLK)
@@ -118,7 +119,7 @@ static int __init dma_resv_lockdep(void)
 	fs_reclaim_release(GFP_KERNEL);
 	ww_mutex_unlock(&obj.lock);
 	ww_acquire_fini(&ctx);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	
 	mmput(mm);
 
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index b876373f2297..3359ae2adf24 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -18,12 +18,12 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/pgtable.h>
 
 #include <asm/cacheflush.h>
 #include <asm/efi.h>
 #include <asm/mmu.h>
 #include <asm/pgalloc.h>
-#include <asm/pgtable.h>
 
 #if defined(CONFIG_PTDUMP_DEBUGFS) && defined(CONFIG_ARM64)
 #include <asm/ptdump.h>
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 9357d6b6e87c..7f1657b6c30d 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -54,7 +54,7 @@ struct mm_struct efi_mm = {
 	.mm_rb			= RB_ROOT,
 	.mm_users		= ATOMIC_INIT(2),
 	.mm_count		= ATOMIC_INIT(1),
-	.mmap_sem		= __RWSEM_INITIALIZER(efi_mm.mmap_sem),
+	MMAP_LOCK_INITIALIZER(efi_mm)
 	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
 	.cpu_bitmap		= { [BITS_TO_LONGS(NR_CPUS)] = 0},
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 3f2b695cf19e..53b4126373a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -186,7 +186,7 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
  * disabled. The memory must be pinned and mapped to the hardware when
  * this is called in hqd_load functions, so it should never fault in
  * the first place. This resolves a circular lock dependency involving
- * four locks, including the DQM lock and mmap_sem.
+ * four locks, including the DQM lock and mmap_lock.
  */
 #define read_user_wptr(mmptr, wptr, dst)				\
 	({								\
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 0b7e78748540..c6944739183a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -237,7 +237,7 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			     CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
 	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, data);
 
-	/* read_user_ptr may take the mm->mmap_sem.
+	/* read_user_ptr may take the mm->mmap_lock.
 	 * release srbm_mutex to avoid circular dependency between
 	 * srbm_mutex->mm_sem->reservation_ww_class_mutex->srbm_mutex.
 	 */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index ccd635b812b5..2f4bdc80a6b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -224,7 +224,7 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			     CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
 	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, data);
 
-	/* read_user_ptr may take the mm->mmap_sem.
+	/* read_user_ptr may take the mm->mmap_lock.
 	 * release srbm_mutex to avoid circular dependency between
 	 * srbm_mutex->mm_sem->reservation_ww_class_mutex->srbm_mutex.
 	 */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 68e6e1bc8f3a..b91b5171270f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1393,9 +1393,9 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 	 * concurrently and the queues are actually stopped
 	 */
 	if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) {
-		down_write(&current->mm->mmap_sem);
+		mmap_write_lock(current->mm);
 		is_invalid_userptr = atomic_read(&mem->invalid);
-		up_write(&current->mm->mmap_sem);
+		mmap_write_unlock(current->mm);
 	}
 
 	mutex_lock(&mem->lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9cbecd5ba814..e59c01a83dac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -910,7 +910,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 		goto out_free_ranges;
 	}
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	vma = find_vma(mm, start);
 	if (unlikely(!vma || start < vma->vm_start)) {
 		r = -EFAULT;
@@ -921,15 +921,15 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 		r = -EPERM;
 		goto out_unlock;
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
 
 retry:
 	range->notifier_seq = mmu_interval_read_begin(&bo->notifier);
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	r = hmm_range_fault(range);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	if (unlikely(r)) {
 		/*
 		 * FIXME: This timeout should encompass the retry from
@@ -954,7 +954,7 @@ retry:
 	return 0;
 
 out_unlock:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 out_free_pfns:
 	kvfree(range->hmm_pfns);
 out_free_ranges:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 15476fca8fa6..a9583b95fcc1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -901,7 +901,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 
 	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
 
 	memory_exception_data.gpu_id = dev->id;
@@ -924,7 +924,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 			memory_exception_data.failure.NoExecute = 0;
 	}
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	mmput(mm);
 
 	pr_debug("notpresent %d, noexecute %d, readonly %d\n",
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 56197ae0b2f9..4391e242356d 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -37,6 +37,7 @@
 #include <linux/pci.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <linux/pgtable.h>
 
 #if defined(__ia64__)
 #include <linux/efi.h>
@@ -44,7 +45,6 @@
 #endif
 #include <linux/mem_encrypt.h>
 
-#include <asm/pgtable.h>
 
 #include <drm/drm_agpsupport.h>
 #include <drm/drm_device.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index dc9ef302f517..701f3995f621 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -661,7 +661,7 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj)
 	struct etnaviv_gem_userptr *userptr = &etnaviv_obj->userptr;
 	int ret, pinned = 0, npages = etnaviv_obj->base.size >> PAGE_SHIFT;
 
-	might_lock_read(&current->mm->mmap_sem);
+	might_lock_read(&current->mm->mmap_lock);
 
 	if (userptr->mm != current->mm)
 		return -EPERM;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 70f5f82da288..fe45bd4d63a5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -93,7 +93,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 		struct mm_struct *mm = current->mm;
 		struct vm_area_struct *vma;
 
-		if (down_write_killable(&mm->mmap_sem)) {
+		if (mmap_write_lock_killable(mm)) {
 			addr = -EINTR;
 			goto err;
 		}
@@ -103,7 +103,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 				pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
 		else
 			addr = -ENOMEM;
-		up_write(&mm->mmap_sem);
+		mmap_write_unlock(mm);
 		if (IS_ERR_VALUE(addr))
 			goto err;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 33776b3f3fa5..c31a6744daee 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -200,10 +200,10 @@ i915_mmu_notifier_find(struct i915_mm_struct *mm)
 	if (IS_ERR(mn))
 		err = PTR_ERR(mn);
 
-	down_write(&mm->mm->mmap_sem);
+	mmap_write_lock(mm->mm);
 	mutex_lock(&mm->i915->mm_lock);
 	if (mm->mn == NULL && !err) {
-		/* Protected by mmap_sem (write-lock) */
+		/* Protected by mmap_lock (write-lock) */
 		err = __mmu_notifier_register(&mn->mn, mm->mm);
 		if (!err) {
 			/* Protected by mm_lock */
@@ -217,7 +217,7 @@ i915_mmu_notifier_find(struct i915_mm_struct *mm)
 		err = 0;
 	}
 	mutex_unlock(&mm->i915->mm_lock);
-	up_write(&mm->mm->mmap_sem);
+	mmap_write_unlock(mm->mm);
 
 	if (mn && !IS_ERR(mn))
 		kfree(mn);
@@ -468,7 +468,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 		if (mmget_not_zero(mm)) {
 			while (pinned < npages) {
 				if (!locked) {
-					down_read(&mm->mmap_sem);
+					mmap_read_lock(mm);
 					locked = 1;
 				}
 				ret = pin_user_pages_remote
@@ -483,7 +483,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 				pinned += ret;
 			}
 			if (locked)
-				up_read(&mm->mmap_sem);
+				mmap_read_unlock(mm);
 			mmput(mm);
 		}
 	}
@@ -522,8 +522,8 @@ __i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj)
 
 	/* Spawn a worker so that we can acquire the
 	 * user pages without holding our mutex. Access
-	 * to the user pages requires mmap_sem, and we have
-	 * a strict lock ordering of mmap_sem, struct_mutex -
+	 * to the user pages requires mmap_lock, and we have
+	 * a strict lock ordering of mmap_lock, struct_mutex -
 	 * we already hold struct_mutex here and so cannot
 	 * call gup without encountering a lock inversion.
 	 *
diff --git a/drivers/gpu/drm/i915/i915_mm.c b/drivers/gpu/drm/i915/i915_mm.c
index b6376b25ef63..43039dc8c607 100644
--- a/drivers/gpu/drm/i915/i915_mm.c
+++ b/drivers/gpu/drm/i915/i915_mm.c
@@ -25,7 +25,6 @@
 #include <linux/mm.h>
 #include <linux/io-mapping.h>
 
-#include <asm/pgtable.h>
 
 #include "i915_drv.h"
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 75c60c2afb7e..665bb076e84d 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -3676,7 +3676,7 @@ static int read_properties_unlocked(struct i915_perf *perf,
  * buffered data written by the GPU besides periodic OA metrics.
  *
  * Note we copy the properties from userspace outside of the i915 perf
- * mutex to avoid an awkward lockdep with mmap_sem.
+ * mutex to avoid an awkward lockdep with mmap_lock.
  *
  * Most of the implementation details are handled by
  * i915_perf_open_ioctl_locked() after taking the &perf->lock
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 22f054f7ee3e..ba9f9359c30e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -175,10 +175,10 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 	 */
 
 	mm = get_task_mm(current);
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 
 	if (!cli->svm.svmm) {
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		return -EINVAL;
 	}
 
@@ -205,7 +205,7 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 	 */
 	args->result = 0;
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	mmput(mm);
 
 	return 0;
@@ -355,7 +355,7 @@ nouveau_svmm_init(struct drm_device *dev, void *data,
 	if (ret)
 		goto out_free;
 
-	down_write(&current->mm->mmap_sem);
+	mmap_write_lock(current->mm);
 	svmm->notifier.ops = &nouveau_mn_ops;
 	ret = __mmu_notifier_register(&svmm->notifier, current->mm);
 	if (ret)
@@ -364,12 +364,12 @@ nouveau_svmm_init(struct drm_device *dev, void *data,
 
 	cli->svm.svmm = svmm;
 	cli->svm.cli = cli;
-	up_write(&current->mm->mmap_sem);
+	mmap_write_unlock(current->mm);
 	mutex_unlock(&cli->mutex);
 	return 0;
 
 out_mm_unlock:
-	up_write(&current->mm->mmap_sem);
+	mmap_write_unlock(current->mm);
 out_free:
 	mutex_unlock(&cli->mutex);
 	kfree(svmm);
@@ -571,9 +571,9 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 			return -EBUSY;
 
 		range.notifier_seq = mmu_interval_read_begin(range.notifier);
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 		ret = hmm_range_fault(&range);
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		if (ret) {
 			/*
 			 * FIXME: the input PFN_REQ flags are destroyed on
@@ -705,18 +705,18 @@ nouveau_svm_fault(struct nvif_notify *notify)
 		/* Intersect fault window with the CPU VMA, cancelling
 		 * the fault if the address is invalid.
 		 */
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 		vma = find_vma_intersection(mm, start, limit);
 		if (!vma) {
 			SVMM_ERR(svmm, "wndw %016llx-%016llx", start, limit);
-			up_read(&mm->mmap_sem);
+			mmap_read_unlock(mm);
 			mmput(mm);
 			nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]);
 			continue;
 		}
 		start = max_t(u64, start, vma->vm_start);
 		limit = min_t(u64, limit, vma->vm_end);
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		SVMM_DBG(svmm, "wndw %016llx-%016llx", start, limit);
 
 		if (buffer->fault[fi]->addr != start) {
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 0d0ab8e0ff3b..cc31d187042e 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -196,12 +196,12 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		p->vm_bos = radeon_vm_get_bos(p->rdev, p->ib.vm,
 					      &p->validated);
 	if (need_mmap_lock)
-		down_read(&current->mm->mmap_sem);
+		mmap_read_lock(current->mm);
 
 	r = radeon_bo_list_validate(p->rdev, &p->ticket, &p->validated, p->ring);
 
 	if (need_mmap_lock)
-		up_read(&current->mm->mmap_sem);
+		mmap_read_unlock(current->mm);
 
 	return r;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 068c3e5da173..3c8f570a20ee 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -342,17 +342,17 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
 	}
 
 	if (args->flags & RADEON_GEM_USERPTR_VALIDATE) {
-		down_read(&current->mm->mmap_sem);
+		mmap_read_lock(current->mm);
 		r = radeon_bo_reserve(bo, true);
 		if (r) {
-			up_read(&current->mm->mmap_sem);
+			mmap_read_unlock(current->mm);
 			goto release_object;
 		}
 
 		radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_GTT);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		radeon_bo_unreserve(bo);
-		up_read(&current->mm->mmap_sem);
+		mmap_read_unlock(current->mm);
 		if (r)
 			goto release_object;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 0ad30b112982..a43aa7275f12 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -58,7 +58,7 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 		goto out_clear;
 
 	/*
-	 * If possible, avoid waiting for GPU with mmap_sem
+	 * If possible, avoid waiting for GPU with mmap_lock
 	 * held.  We only do this if the fault allows retry and this
 	 * is the first attempt.
 	 */
@@ -68,7 +68,7 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 			goto out_unlock;
 
 		ttm_bo_get(bo);
-		up_read(&vmf->vma->vm_mm->mmap_sem);
+		mmap_read_unlock(vmf->vma->vm_mm);
 		(void) dma_fence_wait(bo->moving, true);
 		dma_resv_unlock(bo->base.resv);
 		ttm_bo_put(bo);
@@ -131,20 +131,20 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
 {
 	/*
 	 * Work around locking order reversal in fault / nopfn
-	 * between mmap_sem and bo_reserve: Perform a trylock operation
+	 * between mmap_lock and bo_reserve: Perform a trylock operation
 	 * for reserve, and if it fails, retry the fault after waiting
 	 * for the buffer to become unreserved.
 	 */
 	if (unlikely(!dma_resv_trylock(bo->base.resv))) {
 		/*
 		 * If the fault allows retry and this is the first
-		 * fault attempt, we try to release the mmap_sem
+		 * fault attempt, we try to release the mmap_lock
 		 * before waiting
 		 */
 		if (fault_flag_allow_retry_first(vmf->flags)) {
 			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
 				ttm_bo_get(bo);
-				up_read(&vmf->vma->vm_mm->mmap_sem);
+				mmap_read_unlock(vmf->vma->vm_mm);
 				if (!dma_resv_lock_interruptible(bo->base.resv,
 								 NULL))
 					dma_resv_unlock(bo->base.resv);
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 3b1e627d9a8d..ccd28405451c 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -429,7 +429,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 				ALIGN(bcnt, PAGE_SIZE) / PAGE_SIZE,
 				PAGE_SIZE / sizeof(struct page *));
 
-		down_read(&owning_mm->mmap_sem);
+		mmap_read_lock(owning_mm);
 		/*
 		 * Note: this might result in redundent page getting. We can
 		 * avoid this by checking dma_list to be 0 before calling
@@ -440,7 +440,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 		npages = get_user_pages_remote(owning_process, owning_mm,
 				user_virt, gup_num_pages,
 				flags, local_page_list, NULL, NULL);
-		up_read(&owning_mm->mmap_sem);
+		mmap_read_unlock(owning_mm);
 
 		if (npages < 0) {
 			if (npages != -EAGAIN)
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 47794c85e9af..69e4755cc04b 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -835,12 +835,12 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 			return;
 
 		/*
-		 * The umap_lock is nested under mmap_sem since it used within
+		 * The umap_lock is nested under mmap_lock since it used within
 		 * the vma_ops callbacks, so we have to clean the list one mm
 		 * at a time to get the lock ordering right. Typically there
 		 * will only be one mm, so no big deal.
 		 */
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 		if (!mmget_still_valid(mm))
 			goto skip_mm;
 		mutex_lock(&ufile->umap_lock);
@@ -862,7 +862,7 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 		}
 		mutex_unlock(&ufile->umap_lock);
 	skip_mm:
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		mmput(mm);
 	}
 }
diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c
index 14d2a90964c3..24ca17b77b72 100644
--- a/drivers/infiniband/hw/hfi1/mmu_rb.c
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.c
@@ -333,7 +333,7 @@ static void do_remove(struct mmu_rb_handler *handler,
 
 /*
  * Work queue function to remove all nodes that have been queued up to
- * be removed.  The key feature is that mm->mmap_sem is not being held
+ * be removed.  The key feature is that mm->mmap_lock is not being held
  * and the remove callback can sleep while taking it, if needed.
  */
 static void handle_remove(struct work_struct *work)
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index e2fb71b23c80..7e0b205c05eb 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -380,7 +380,7 @@ static struct ib_umem *mlx4_get_umem_mr(struct ib_device *device, u64 start,
 		unsigned long untagged_start = untagged_addr(start);
 		struct vm_area_struct *vma;
 
-		down_read(&current->mm->mmap_sem);
+		mmap_read_lock(current->mm);
 		/*
 		 * FIXME: Ideally this would iterate over all the vmas that
 		 * cover the memory, but for now it requires a single vma to
@@ -395,7 +395,7 @@ static struct ib_umem *mlx4_get_umem_mr(struct ib_device *device, u64 start,
 			access_flags |= IB_ACCESS_LOCAL_WRITE;
 		}
 
-		up_read(&current->mm->mmap_sem);
+		mmap_read_unlock(current->mm);
 	}
 
 	return ib_umem_get(device, start, length, access_flags);
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index b0144229cf3b..ff87a67dd7b7 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -40,10 +40,10 @@
 #include <linux/highmem.h>
 #include <linux/io.h>
 #include <linux/jiffies.h>
-#include <asm/pgtable.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/uio.h>
+#include <linux/pgtable.h>
 
 #include <rdma/ib.h>
 
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 342e3172ca40..4c24e83f3175 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -106,18 +106,18 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,
 		goto bail;
 	}
 
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(current->mm);
 	for (got = 0; got < num_pages; got += ret) {
 		ret = pin_user_pages(start_page + got * PAGE_SIZE,
 				     num_pages - got,
 				     FOLL_LONGTERM | FOLL_WRITE | FOLL_FORCE,
 				     p + got, NULL);
 		if (ret < 0) {
-			up_read(&current->mm->mmap_sem);
+			mmap_read_unlock(current->mm);
 			goto bail_release;
 		}
 	}
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
 	return 0;
 bail_release:
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index bd9f944b68fc..760b254ba42d 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -123,7 +123,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
 	npages = PAGE_ALIGN(size + (addr & ~PAGE_MASK)) >> PAGE_SHIFT;
 
 	uiomr->owning_mm = mm = current->mm;
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 
 	locked = atomic64_add_return(npages, &current->mm->pinned_vm);
 	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
@@ -187,7 +187,7 @@ out:
 	} else
 		mmgrab(uiomr->owning_mm);
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	free_page((unsigned long) page_list);
 	return ret;
 }
diff --git a/drivers/infiniband/sw/rdmavt/mmap.c b/drivers/infiniband/sw/rdmavt/mmap.c
index 37853aa3bcf7..f5d0e33cf3d7 100644
--- a/drivers/infiniband/sw/rdmavt/mmap.c
+++ b/drivers/infiniband/sw/rdmavt/mmap.c
@@ -48,7 +48,6 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
-#include <asm/pgtable.h>
 #include <rdma/uverbs_ioctl.h>
 #include "mmap.h"
 
diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c
index 6a413d73b95d..7887f623f62c 100644
--- a/drivers/infiniband/sw/rxe/rxe_mmap.c
+++ b/drivers/infiniband/sw/rxe/rxe_mmap.c
@@ -35,7 +35,6 @@
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
-#include <asm/pgtable.h>
 #include <rdma/uverbs_ioctl.h>
 
 #include "rxe.h"
diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c
index 87117781d637..34a910cf0edb 100644
--- a/drivers/infiniband/sw/siw/siw_mem.c
+++ b/drivers/infiniband/sw/siw/siw_mem.c
@@ -394,7 +394,7 @@ struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable)
 	if (!writable)
 		foll_flags |= FOLL_FORCE;
 
-	down_read(&mm_s->mmap_sem);
+	mmap_read_lock(mm_s);
 
 	mlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 
@@ -438,7 +438,7 @@ struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable)
 		num_pages -= got;
 	}
 out_sem_up:
-	up_read(&mm_s->mmap_sem);
+	mmap_read_unlock(mm_s);
 
 	if (rv > 0)
 		return umem;
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index c8a7b6b39222..e4b025c5637c 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -485,7 +485,7 @@ static void do_fault(struct work_struct *work)
 		flags |= FAULT_FLAG_WRITE;
 	flags |= FAULT_FLAG_REMOTE;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	vma = find_extend_vma(mm, address);
 	if (!vma || address < vma->vm_start)
 		/* failed to get a vma in the right range */
@@ -497,7 +497,7 @@ static void do_fault(struct work_struct *work)
 
 	ret = handle_mm_fault(vma, address, flags);
 out:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	if (ret & VM_FAULT_ERROR)
 		/* failed to service fault */
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index a035ef911fba..6c87c807a0ab 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -863,7 +863,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		if (!mmget_not_zero(svm->mm))
 			goto bad_req;
 
-		down_read(&svm->mm->mmap_sem);
+		mmap_read_lock(svm->mm);
 		vma = find_extend_vma(svm->mm, address);
 		if (!vma || address < vma->vm_start)
 			goto invalid;
@@ -878,7 +878,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 
 		result = QI_RESP_SUCCESS;
 	invalid:
-		up_read(&svm->mm->mmap_sem);
+		mmap_read_unlock(svm->mm);
 		mmput(svm->mm);
 	bad_req:
 		/* Accounting for major/minor faults? */
diff --git a/drivers/macintosh/macio-adb.c b/drivers/macintosh/macio-adb.c
index eb3adfb7f88d..d4759db002c6 100644
--- a/drivers/macintosh/macio-adb.c
+++ b/drivers/macintosh/macio-adb.c
@@ -9,10 +9,10 @@
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
+#include <linux/pgtable.h>
 #include <asm/prom.h>
 #include <linux/adb.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/hydra.h>
 #include <asm/irq.h>
 #include <linux/init.h>
diff --git a/drivers/macintosh/mediabay.c b/drivers/macintosh/mediabay.c
index 74bf2938276b..eab7e83c11c4 100644
--- a/drivers/macintosh/mediabay.c
+++ b/drivers/macintosh/mediabay.c
@@ -16,8 +16,8 @@
 #include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/mutex.h>
+#include <linux/pgtable.h>
 #include <asm/prom.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 8450d7c008d0..73e6ae88fafd 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -50,9 +50,9 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/uaccess.h>
+#include <linux/pgtable.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/sections.h>
 #include <asm/irq.h>
 #ifdef CONFIG_PPC_PMAC
diff --git a/drivers/media/pci/bt8xx/bt878.c b/drivers/media/pci/bt8xx/bt878.c
index 53af26ad1dfb..79ba15a9385a 100644
--- a/drivers/media/pci/bt8xx/bt878.c
+++ b/drivers/media/pci/bt8xx/bt878.c
@@ -13,9 +13,9 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/pgtable.h>
 #include <asm/io.h>
 #include <linux/ioport.h>
-#include <asm/pgtable.h>
 #include <asm/page.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
diff --git a/drivers/media/pci/bt8xx/btcx-risc.c b/drivers/media/pci/bt8xx/btcx-risc.c
index 1139a5ad2418..51257980f539 100644
--- a/drivers/media/pci/bt8xx/btcx-risc.c
+++ b/drivers/media/pci/bt8xx/btcx-risc.c
@@ -17,8 +17,8 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/videodev2.h>
+#include <linux/pgtable.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 
 #include "btcx-risc.h"
 
diff --git a/drivers/media/pci/bt8xx/bttv-risc.c b/drivers/media/pci/bt8xx/bttv-risc.c
index fc8708047be8..4af72826b006 100644
--- a/drivers/media/pci/bt8xx/bttv-risc.c
+++ b/drivers/media/pci/bt8xx/bttv-risc.c
@@ -20,8 +20,8 @@
 #include <linux/pci.h>
 #include <linux/vmalloc.h>
 #include <linux/interrupt.h>
+#include <linux/pgtable.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <media/v4l2-ioctl.h>
 
 #include "bttvp.h"
diff --git a/drivers/media/platform/davinci/vpbe_display.c b/drivers/media/platform/davinci/vpbe_display.c
index 38d3088d4d38..7ab13eb7527d 100644
--- a/drivers/media/platform/davinci/vpbe_display.c
+++ b/drivers/media/platform/davinci/vpbe_display.c
@@ -17,7 +17,6 @@
 #include <linux/videodev2.h>
 #include <linux/slab.h>
 
-#include <asm/pgtable.h>
 
 #include <media/v4l2-dev.h>
 #include <media/v4l2-common.h>
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 9e8eb45a5b03..3dc17ebe14fa 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -41,7 +41,6 @@
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/uaccess.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/div64.h>
 #include <media/v4l2-common.h>
diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c
index 2686f03b322e..5c91fc3e65b5 100644
--- a/drivers/media/v4l2-core/videobuf-core.c
+++ b/drivers/media/v4l2-core/videobuf-core.c
@@ -535,7 +535,7 @@ int videobuf_qbuf(struct videobuf_queue *q, struct v4l2_buffer *b)
 	MAGIC_CHECK(q->int_ops->magic, MAGIC_QTYPE_OPS);
 
 	if (b->memory == V4L2_MEMORY_MMAP)
-		down_read(&current->mm->mmap_sem);
+		mmap_read_lock(current->mm);
 
 	videobuf_queue_lock(q);
 	retval = -EBUSY;
@@ -622,7 +622,7 @@ done:
 	videobuf_queue_unlock(q);
 
 	if (b->memory == V4L2_MEMORY_MMAP)
-		up_read(&current->mm->mmap_sem);
+		mmap_read_unlock(current->mm);
 
 	return retval;
 }
diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c
index aeb2f497c683..52312ce2ba05 100644
--- a/drivers/media/v4l2-core/videobuf-dma-contig.c
+++ b/drivers/media/v4l2-core/videobuf-dma-contig.c
@@ -169,7 +169,7 @@ static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem,
 	mem->size = PAGE_ALIGN(vb->size + offset);
 	ret = -EINVAL;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 
 	vma = find_vma(mm, untagged_baddr);
 	if (!vma)
@@ -201,7 +201,7 @@ static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem,
 	}
 
 out_up:
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
 	return ret;
 }
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 13b65ed9e74c..46ff19df9f53 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -21,13 +21,13 @@
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
+#include <linux/pgtable.h>
 
 #include <linux/dma-mapping.h>
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
 #include <linux/scatterlist.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 
 #include <media/videobuf-dma-sg.h>
 
@@ -200,9 +200,9 @@ static int videobuf_dma_init_user(struct videobuf_dmabuf *dma, int direction,
 {
 	int ret;
 
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(current->mm);
 	ret = videobuf_dma_init_user_locked(dma, direction, data, size);
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
 	return ret;
 }
@@ -533,7 +533,7 @@ static int __videobuf_iolock(struct videobuf_queue *q,
 		} else {
 			/* NOTE: HACK: videobuf_iolock on V4L2_MEMORY_MMAP
 			buffers can only be called from videobuf_qbuf
-			we take current->mm->mmap_sem there, to prevent
+			we take current->mm->mmap_lock there, to prevent
 			locking inversion, so don't take it here */
 
 			err = videobuf_dma_init_user_locked(&mem->dma,
diff --git a/drivers/media/v4l2-core/videobuf-vmalloc.c b/drivers/media/v4l2-core/videobuf-vmalloc.c
index f8bd5a369560..9b2443720ab0 100644
--- a/drivers/media/v4l2-core/videobuf-vmalloc.c
+++ b/drivers/media/v4l2-core/videobuf-vmalloc.c
@@ -15,12 +15,12 @@
 #include <linux/moduleparam.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
+#include <linux/pgtable.h>
 
 #include <linux/pci.h>
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 
 #include <media/videobuf-vmalloc.h>
 
diff --git a/drivers/misc/cxl/cxllib.c b/drivers/misc/cxl/cxllib.c
index 258c43a95ac3..2a1783f32254 100644
--- a/drivers/misc/cxl/cxllib.c
+++ b/drivers/misc/cxl/cxllib.c
@@ -207,7 +207,7 @@ static int get_vma_info(struct mm_struct *mm, u64 addr,
 	struct vm_area_struct *vma = NULL;
 	int rc = 0;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 
 	vma = find_vma(mm, addr);
 	if (!vma) {
@@ -218,7 +218,7 @@ static int get_vma_info(struct mm_struct *mm, u64 addr,
 	*vma_start = vma->vm_start;
 	*vma_end = vma->vm_end;
 out:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	return rc;
 }
 
@@ -245,9 +245,8 @@ int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags)
 	     dar += page_size) {
 		if (dar < vma_start || dar >= vma_end) {
 			/*
-			 * We don't hold the mm->mmap_sem semaphore
-			 * while iterating, since the semaphore is
-			 * required by one of the lower-level page
+			 * We don't hold mm->mmap_lock while iterating, since
+			 * the lock is required by one of the lower-level page
 			 * fault processing functions and it could
 			 * create a deadlock.
 			 *
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 2297e6fc1544..01153b74334a 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -321,7 +321,7 @@ static void cxl_prefault_vma(struct cxl_context *ctx)
 		return;
 	}
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		for (ea = vma->vm_start; ea < vma->vm_end;
 				ea = next_segment(ea, slb.vsid)) {
@@ -336,7 +336,7 @@ static void cxl_prefault_vma(struct cxl_context *ctx)
 			last_esid = slb.esid;
 		}
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	mmput(mm);
 }
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 60460a053b2d..77c21caf2acd 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -27,7 +27,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
-#include <asm/pgtable.h>
+#include <linux/pgtable.h>
 
 #include "genwqe_driver.h"
 #include "card_base.h"
diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index 4b713a80b572..b1521112dbbd 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -21,7 +21,6 @@
 #include <linux/uaccess.h>
 #include <linux/security.h>
 #include <linux/prefetch.h>
-#include <asm/pgtable.h>
 #include "gru.h"
 #include "grutables.h"
 #include "grulib.h"
@@ -43,7 +42,7 @@ static inline int is_gru_paddr(unsigned long paddr)
 }
 
 /*
- * Find the vma of a GRU segment. Caller must hold mmap_sem.
+ * Find the vma of a GRU segment. Caller must hold mmap_lock.
  */
 struct vm_area_struct *gru_find_vma(unsigned long vaddr)
 {
@@ -59,7 +58,7 @@ struct vm_area_struct *gru_find_vma(unsigned long vaddr)
  * Find and lock the gts that contains the specified user vaddr.
  *
  * Returns:
- * 	- *gts with the mmap_sem locked for read and the GTS locked.
+ * 	- *gts with the mmap_lock locked for read and the GTS locked.
  *	- NULL if vaddr invalid OR is not a valid GSEG vaddr.
  */
 
@@ -69,14 +68,14 @@ static struct gru_thread_state *gru_find_lock_gts(unsigned long vaddr)
 	struct vm_area_struct *vma;
 	struct gru_thread_state *gts = NULL;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	vma = gru_find_vma(vaddr);
 	if (vma)
 		gts = gru_find_thread_state(vma, TSID(vaddr, vma));
 	if (gts)
 		mutex_lock(&gts->ts_ctxlock);
 	else
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 	return gts;
 }
 
@@ -86,7 +85,7 @@ static struct gru_thread_state *gru_alloc_locked_gts(unsigned long vaddr)
 	struct vm_area_struct *vma;
 	struct gru_thread_state *gts = ERR_PTR(-EINVAL);
 
-	down_write(&mm->mmap_sem);
+	mmap_write_lock(mm);
 	vma = gru_find_vma(vaddr);
 	if (!vma)
 		goto err;
@@ -95,11 +94,11 @@ static struct gru_thread_state *gru_alloc_locked_gts(unsigned long vaddr)
 	if (IS_ERR(gts))
 		goto err;
 	mutex_lock(&gts->ts_ctxlock);
-	downgrade_write(&mm->mmap_sem);
+	mmap_write_downgrade(mm);
 	return gts;
 
 err:
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 	return gts;
 }
 
@@ -109,7 +108,7 @@ err:
 static void gru_unlock_gts(struct gru_thread_state *gts)
 {
 	mutex_unlock(&gts->ts_ctxlock);
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 }
 
 /*
@@ -199,7 +198,7 @@ static int non_atomic_pte_lookup(struct vm_area_struct *vma,
  * Only supports Intel large pages (2MB only) on x86_64.
  *	ZZZ - hugepage support is incomplete
  *
- * NOTE: mmap_sem is already held on entry to this function. This
+ * NOTE: mmap_lock is already held on entry to this function. This
  * guarantees existence of the page tables.
  */
 static int atomic_pte_lookup(struct vm_area_struct *vma, unsigned long vaddr,
@@ -570,14 +569,14 @@ static irqreturn_t gru_intr(int chiplet, int blade)
 		}
 
 		/*
-		 * This is running in interrupt context. Trylock the mmap_sem.
+		 * This is running in interrupt context. Trylock the mmap_lock.
 		 * If it fails, retry the fault in user context.
 		 */
 		gts->ustats.fmm_tlbmiss++;
 		if (!gts->ts_force_cch_reload &&
-					down_read_trylock(&gts->ts_mm->mmap_sem)) {
+					mmap_read_trylock(gts->ts_mm)) {
 			gru_try_dropin(gru, gts, tfh, NULL);
-			up_read(&gts->ts_mm->mmap_sem);
+			mmap_read_unlock(gts->ts_mm);
 		} else {
 			tfh_user_polling_mode(tfh);
 			STAT(intr_mm_lock_failed);
diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c
index 9d042310214f..93bb49ddda1f 100644
--- a/drivers/misc/sgi-gru/grufile.c
+++ b/drivers/misc/sgi-gru/grufile.c
@@ -135,7 +135,7 @@ static int gru_create_new_context(unsigned long arg)
 	if (!(req.options & GRU_OPT_MISS_MASK))
 		req.options |= GRU_OPT_MISS_FMM_INTR;
 
-	down_write(&current->mm->mmap_sem);
+	mmap_write_lock(current->mm);
 	vma = gru_find_vma(req.gseg);
 	if (vma) {
 		vdata = vma->vm_private_data;
@@ -146,7 +146,7 @@ static int gru_create_new_context(unsigned long arg)
 		vdata->vd_tlb_preload_count = req.tlb_preload_count;
 		ret = 0;
 	}
-	up_write(&current->mm->mmap_sem);
+	mmap_write_unlock(current->mm);
 
 	return ret;
 }
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index 73c67e5c08f8..da0bee13fe7f 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -26,7 +26,7 @@
 #include <linux/notifier.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/ubi.h>
-#include <asm/pgtable.h>
+#include <linux/pgtable.h>
 
 #include "ubi-media.h"
 
diff --git a/drivers/net/ethernet/amd/7990.c b/drivers/net/ethernet/amd/7990.c
index 50fb66369415..ef512cf89abf 100644
--- a/drivers/net/ethernet/amd/7990.c
+++ b/drivers/net/ethernet/amd/7990.c
@@ -28,6 +28,7 @@
 #include <linux/route.h>
 #include <linux/string.h>
 #include <linux/skbuff.h>
+#include <linux/pgtable.h>
 #include <asm/irq.h>
 /* Used for the temporal inet entries and routing */
 #include <linux/socket.h>
@@ -35,7 +36,6 @@
 
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/pgtable.h>
 #ifdef CONFIG_HP300
 #include <asm/blinken.h>
 #endif
diff --git a/drivers/net/ethernet/amd/hplance.c b/drivers/net/ethernet/amd/hplance.c
index 1381a474063f..e10aceb2b767 100644
--- a/drivers/net/ethernet/amd/hplance.c
+++ b/drivers/net/ethernet/amd/hplance.c
@@ -15,6 +15,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/errno.h>
+#include <linux/pgtable.h>
 /* Used for the temporal inet entries and routing */
 #include <linux/socket.h>
 #include <linux/route.h>
@@ -24,7 +25,6 @@
 #include <linux/skbuff.h>
 
 #include <asm/io.h>
-#include <asm/pgtable.h>
 
 #include "hplance.h"
 
diff --git a/drivers/net/ethernet/amd/mvme147.c b/drivers/net/ethernet/amd/mvme147.c
index 72abd3f82249..3f2e4cdd0b83 100644
--- a/drivers/net/ethernet/amd/mvme147.c
+++ b/drivers/net/ethernet/amd/mvme147.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/gfp.h>
+#include <linux/pgtable.h>
 /* Used for the temporal inet entries and routing */
 #include <linux/socket.h>
 #include <linux/route.h>
@@ -24,7 +25,6 @@
 #include <linux/skbuff.h>
 
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/mvme147hw.h>
 
 /* We have 32K of RAM for the init block and buffers. This places
diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c
index da7e3d4f4166..e1fde585fd0d 100644
--- a/drivers/net/ethernet/amd/sun3lance.c
+++ b/drivers/net/ethernet/amd/sun3lance.c
@@ -37,12 +37,12 @@ static const char version[] =
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 #include <linux/bitops.h>
+#include <linux/pgtable.h>
 
 #include <asm/cacheflush.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/dvma.h>
 #include <asm/idprom.h>
 #include <asm/machines.h>
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index a21b2e60157e..ddece276ae23 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -94,10 +94,10 @@ static char lancestr[] = "LANCE";
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/gfp.h>
+#include <linux/pgtable.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/pgtable.h>
 #include <asm/byteorder.h>	/* Used by the checksum routines */
 #include <asm/idprom.h>
 #include <asm/prom.h>
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 3e3711b60d01..1e4e402f07d7 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -24,11 +24,11 @@
 #include <linux/bitrev.h>
 #include <linux/ethtool.h>
 #include <linux/slab.h>
+#include <linux/pgtable.h>
 #include <asm/prom.h>
 #include <asm/dbdma.h>
 #include <asm/io.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
 #include <asm/macio.h>
diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c
index b8ba2abf5b3a..9e5006e59215 100644
--- a/drivers/net/ethernet/apple/mace.c
+++ b/drivers/net/ethernet/apple/mace.c
@@ -19,10 +19,10 @@
 #include <linux/spinlock.h>
 #include <linux/bitrev.h>
 #include <linux/slab.h>
+#include <linux/pgtable.h>
 #include <asm/prom.h>
 #include <asm/dbdma.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/macio.h>
 
 #include "mace.h"
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index ce85feaac357..b0d4b1984a70 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -40,9 +40,9 @@
 #include <linux/of_platform.h>
 #include <linux/of_gpio.h>
 #include <linux/of_net.h>
+#include <linux/pgtable.h>
 
 #include <linux/vmalloc.h>
-#include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <linux/uaccess.h>
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index 6e64989f8478..b47490be872c 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -35,12 +35,12 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/gfp.h>
+#include <linux/pgtable.h>
 
 #include <asm/immap_cpm2.h>
 #include <asm/mpc8260.h>
 #include <asm/cpm2.h>
 
-#include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <linux/uaccess.h>
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index 1582d82483ec..8b51ee142fa3 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -32,8 +32,8 @@
 #include <linux/platform_device.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
+#include <linux/pgtable.h>
 
-#include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <linux/uaccess.h>
 #include <asm/mpc5xxx.h>
diff --git a/drivers/net/ethernet/i825xx/82596.c b/drivers/net/ethernet/i825xx/82596.c
index bef676d93339..fc8c7cd67471 100644
--- a/drivers/net/ethernet/i825xx/82596.c
+++ b/drivers/net/ethernet/i825xx/82596.c
@@ -53,10 +53,10 @@
 #include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/gfp.h>
+#include <linux/pgtable.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 
 static char version[] __initdata =
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index f1d84921e42b..03e034918d14 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -53,10 +53,10 @@
 #include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/crc32.h>
+#include <linux/pgtable.h>
 
 #include <asm/bootinfo.h>
 #include <asm/bitops.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 17243bb5ba91..eb8cf60ecf12 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -31,8 +31,8 @@
 #include <linux/types.h>
 #include <linux/udp.h>
 #include <linux/workqueue.h>
+#include <linux/pgtable.h>
 
-#include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 
 #define DRIVER_NAME	"pxa168-eth"
diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c
index 8b018ed37b1b..ce3eca5d152b 100644
--- a/drivers/net/ethernet/natsemi/jazzsonic.c
+++ b/drivers/net/ethernet/natsemi/jazzsonic.c
@@ -36,9 +36,9 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
+#include <linux/pgtable.h>
 
 #include <asm/bootinfo.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/jazz.h>
diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c
index 1b5559aacb38..776b7d264dc3 100644
--- a/drivers/net/ethernet/natsemi/macsonic.c
+++ b/drivers/net/ethernet/natsemi/macsonic.c
@@ -51,8 +51,8 @@
 #include <linux/dma-mapping.h>
 #include <linux/bitrev.h>
 #include <linux/slab.h>
+#include <linux/pgtable.h>
 
-#include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/hwtest.h>
 #include <asm/dma.h>
diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c
index dda9ec7d9cee..afa166ff7aef 100644
--- a/drivers/net/ethernet/natsemi/xtsonic.c
+++ b/drivers/net/ethernet/natsemi/xtsonic.c
@@ -35,9 +35,9 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
+#include <linux/pgtable.h>
 
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/dma.h>
 
 static char xtsonic_string[] = "xtsonic";
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index c5add0b45eed..34fdbc6d6031 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/pgtable.h>
 
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -34,7 +35,6 @@
 #include <asm/io.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/pgtable.h>
 
 #include "sunbmac.h"
 
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index f0fe7bb2a750..54b53dbdb33c 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -52,7 +52,6 @@
 #endif
 #include <linux/uaccess.h>
 
-#include <asm/pgtable.h>
 #include <asm/irq.h>
 
 #ifdef CONFIG_PCI
diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c
index 2102b95ec347..577cd9753d8e 100644
--- a/drivers/net/ethernet/sun/sunqe.c
+++ b/drivers/net/ethernet/sun/sunqe.c
@@ -28,6 +28,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/pgtable.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
@@ -36,7 +37,6 @@
 #include <asm/openprom.h>
 #include <asm/oplib.h>
 #include <asm/auxio.h>
-#include <asm/pgtable.h>
 #include <asm/irq.h>
 
 #include "sunqe.h"
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index ac27f3d3fbb4..4d7695289eda 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -91,11 +91,11 @@ munmap_notify(struct notifier_block *self, unsigned long val, void *data)
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *mpnt;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 
 	mpnt = find_vma(mm, addr);
 	if (mpnt && mpnt->vm_file && (mpnt->vm_flags & VM_EXEC)) {
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		/* To avoid latency problems, we only process the current CPU,
 		 * hoping that most samples for the task are on this CPU
 		 */
@@ -103,7 +103,7 @@ munmap_notify(struct notifier_block *self, unsigned long val, void *data)
 		return 0;
 	}
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	return 0;
 }
 
@@ -256,7 +256,7 @@ lookup_dcookie(struct mm_struct *mm, unsigned long addr, off_t *offset)
 	unsigned long cookie = NO_COOKIE;
 	struct vm_area_struct *vma;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
 
 		if (addr < vma->vm_start || addr >= vma->vm_end)
@@ -276,7 +276,7 @@ lookup_dcookie(struct mm_struct *mm, unsigned long addr, off_t *offset)
 
 	if (!vma)
 		cookie = INVALID_COOKIE;
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	return cookie;
 }
@@ -486,7 +486,7 @@ typedef enum {
 
 /* Sync one of the CPU's buffers into the global event buffer.
  * Here we need to go through each batch of samples punctuated
- * by context switch notes, taking the task's mmap_sem and doing
+ * by context switch notes, taking the task's mmap_lock and doing
  * lookup in task->mm->mmap to convert EIP into dcookie/offset
  * value.
  */
diff --git a/drivers/sbus/char/flash.c b/drivers/sbus/char/flash.c
index 4147d22fd448..3adfef210d8e 100644
--- a/drivers/sbus/char/flash.c
+++ b/drivers/sbus/char/flash.c
@@ -17,7 +17,6 @@
 #include <linux/of_device.h>
 
 #include <linux/uaccess.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/upa.h>
 
diff --git a/drivers/sbus/char/uctrl.c b/drivers/sbus/char/uctrl.c
index 37d252f2548d..05de0ce79cb9 100644
--- a/drivers/sbus/char/uctrl.c
+++ b/drivers/sbus/char/uctrl.c
@@ -21,7 +21,6 @@
 #include <asm/oplib.h>
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 
 #define DEBUG 1
 #ifdef DEBUG
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 0068963bb933..461b3babb601 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -116,9 +116,9 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/device.h>
+#include <linux/pgtable.h>
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/byteorder.h>
 
 #include <scsi/scsi.h>
diff --git a/drivers/scsi/a2091.c b/drivers/scsi/a2091.c
index 564b35473672..5853db36eceb 100644
--- a/drivers/scsi/a2091.c
+++ b/drivers/scsi/a2091.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/amigaints.h>
 #include <asm/amigahw.h>
 
diff --git a/drivers/scsi/a3000.c b/drivers/scsi/a3000.c
index b6a0432f305a..86f1da22aaa5 100644
--- a/drivers/scsi/a3000.c
+++ b/drivers/scsi/a3000.c
@@ -10,7 +10,6 @@
 #include <linux/module.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/amigaints.h>
 #include <asm/amigahw.h>
 
diff --git a/drivers/scsi/arm/cumana_2.c b/drivers/scsi/arm/cumana_2.c
index a1f3e9ee4e63..65691c21f133 100644
--- a/drivers/scsi/arm/cumana_2.c
+++ b/drivers/scsi/arm/cumana_2.c
@@ -23,11 +23,11 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
+#include <linux/pgtable.h>
 
 #include <asm/dma.h>
 #include <asm/ecard.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 
 #include "../scsi.h"
 #include <scsi/scsi_host.h>
diff --git a/drivers/scsi/arm/eesox.c b/drivers/scsi/arm/eesox.c
index 134f040d58e2..6e204a2e0c8d 100644
--- a/drivers/scsi/arm/eesox.c
+++ b/drivers/scsi/arm/eesox.c
@@ -29,11 +29,11 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
+#include <linux/pgtable.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/ecard.h>
-#include <asm/pgtable.h>
 
 #include "../scsi.h"
 #include <scsi/scsi_host.h>
diff --git a/drivers/scsi/arm/powertec.c b/drivers/scsi/arm/powertec.c
index c795537a671c..772a13e5fd91 100644
--- a/drivers/scsi/arm/powertec.c
+++ b/drivers/scsi/arm/powertec.c
@@ -14,11 +14,11 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
+#include <linux/pgtable.h>
 
 #include <asm/dma.h>
 #include <asm/ecard.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 
 #include "../scsi.h"
 #include <scsi/scsi_host.h>
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index 2cf889512ece..0497ef6a9453 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -27,6 +27,7 @@
 /*#define UARTDELAY 1 */
 
 #include <linux/module.h>
+#include <linux/pgtable.h>
 
 MODULE_AUTHOR("Deanna Bonds, with _lots_ of help from Mark Salyzyn");
 MODULE_DESCRIPTION("Adaptec I2O RAID Driver");
@@ -55,7 +56,6 @@ MODULE_DESCRIPTION("Adaptec I2O RAID Driver");
 #include <linux/mutex.h>
 
 #include <asm/processor.h>	/* for boot_cpu_data */
-#include <asm/pgtable.h>
 #include <asm/io.h>		/* for virt_to_bus, etc. */
 
 #include <scsi/scsi.h>
diff --git a/drivers/scsi/gvp11.c b/drivers/scsi/gvp11.c
index 11df0eca0293..727f8c8f30b5 100644
--- a/drivers/scsi/gvp11.c
+++ b/drivers/scsi/gvp11.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/amigaints.h>
 #include <asm/amigahw.h>
 
diff --git a/drivers/scsi/lasi700.c b/drivers/scsi/lasi700.c
index c48a73a0f517..de71d240a56f 100644
--- a/drivers/scsi/lasi700.c
+++ b/drivers/scsi/lasi700.c
@@ -31,7 +31,6 @@
 #include <linux/slab.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <asm/hardware.h>
 #include <asm/parisc-device.h>
diff --git a/drivers/scsi/mac53c94.c b/drivers/scsi/mac53c94.c
index 35d3e322d6d5..43edf83fdb62 100644
--- a/drivers/scsi/mac53c94.c
+++ b/drivers/scsi/mac53c94.c
@@ -20,9 +20,9 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pgtable.h>
 #include <asm/dbdma.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/prom.h>
 #include <asm/macio.h>
 
diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c
index 74fb50644678..f9f8f4921654 100644
--- a/drivers/scsi/mesh.c
+++ b/drivers/scsi/mesh.c
@@ -31,9 +31,9 @@
 #include <linux/reboot.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
+#include <linux/pgtable.h>
 #include <asm/dbdma.h>
 #include <asm/io.h>
-#include <asm/pgtable.h>
 #include <asm/prom.h>
 #include <asm/irq.h>
 #include <asm/hydra.h>
diff --git a/drivers/scsi/mvme147.c b/drivers/scsi/mvme147.c
index ca96d6d9c350..869b8b058a43 100644
--- a/drivers/scsi/mvme147.c
+++ b/drivers/scsi/mvme147.c
@@ -8,7 +8,6 @@
 #include <linux/module.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/mvme147hw.h>
 #include <asm/irq.h>
 
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index d539beef3ce8..3790e8b70bba 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -30,6 +30,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/firmware.h>
+#include <linux/pgtable.h>
 
 #include <asm/byteorder.h>
 
@@ -37,7 +38,6 @@
 
 #include <asm/dma.h>
 #include <asm/ptrace.h>
-#include <asm/pgtable.h>
 #include <asm/oplib.h>
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/drivers/scsi/sni_53c710.c b/drivers/scsi/sni_53c710.c
index f8397978f8ab..03d43f016397 100644
--- a/drivers/scsi/sni_53c710.c
+++ b/drivers/scsi/sni_53c710.c
@@ -28,7 +28,6 @@
 #include <linux/platform_device.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <asm/delay.h>
 
diff --git a/drivers/scsi/zorro_esp.c b/drivers/scsi/zorro_esp.c
index c6727bcbc2e3..928c8adf5cb3 100644
--- a/drivers/scsi/zorro_esp.c
+++ b/drivers/scsi/zorro_esp.c
@@ -34,9 +34,9 @@
 #include <linux/delay.h>
 #include <linux/zorro.h>
 #include <linux/slab.h>
+#include <linux/pgtable.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 #include <asm/amigahw.h>
 #include <asm/amigaints.h>
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 8044510d8ec6..c05a214191da 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -555,7 +555,7 @@ static int set_name(struct ashmem_area *asma, void __user *name)
 
 	/*
 	 * Holding the ashmem_mutex while doing a copy_from_user might cause
-	 * an data abort which would try to access mmap_sem. If another
+	 * an data abort which would try to access mmap_lock. If another
 	 * thread has invoked ashmem_mmap then it will be holding the
 	 * semaphore and will be waiting for ashmem_mutex, there by leading to
 	 * deadlock. We'll release the mutex and take the name to a local
@@ -586,7 +586,7 @@ static int get_name(struct ashmem_area *asma, void __user *name)
 	 * Have a local variable to which we'll copy the content
 	 * from asma with the lock held. Later we can copy this to the user
 	 * space safely without holding any locks. So even if we proceed to
-	 * wait for mmap_sem, it won't lead to deadlock.
+	 * wait for mmap_lock, it won't lead to deadlock.
 	 */
 	char local_name[ASHMEM_NAME_LEN];
 
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index a56c8f74a27b..e85a99b68f31 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -2325,7 +2325,7 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
 	int retval = 0;
 
 	/*
-	 * 'trylock' avoids circular dependency with current->mm->mmap_sem
+	 * 'trylock' avoids circular dependency with current->mm->mmap_lock
 	 * and down-reading &dev->attach_lock should normally succeed without
 	 * contention unless the device is in the process of being attached
 	 * or detached.
diff --git a/drivers/staging/kpc2000/kpc_dma/fileops.c b/drivers/staging/kpc2000/kpc_dma/fileops.c
index 7caabdd77bbf..89753463e926 100644
--- a/drivers/staging/kpc2000/kpc_dma/fileops.c
+++ b/drivers/staging/kpc2000/kpc_dma/fileops.c
@@ -75,9 +75,9 @@ static int kpc_dma_transfer(struct dev_private_data *priv,
 	}
 
 	// Lock the user buffer pages in memory, and hold on to the page pointers (for the sglist)
-	down_read(&current->mm->mmap_sem);      /*  get memory map semaphore */
+	mmap_read_lock(current->mm);      /*  get memory map semaphore */
 	rv = get_user_pages(iov_base, acd->page_count, FOLL_TOUCH | FOLL_WRITE | FOLL_GET, acd->user_pages, NULL);
-	up_read(&current->mm->mmap_sem);        /*  release the semaphore */
+	mmap_read_unlock(current->mm);        /*  release the semaphore */
 	if (rv != acd->page_count) {
 		dev_err(&priv->ldev->pldev->dev, "Couldn't get_user_pages (%ld)\n", rv);
 		goto err_get_user_pages;
diff --git a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c
index 492b76c29490..c9e7df0ea5a6 100644
--- a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c
+++ b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c
@@ -982,9 +982,9 @@ static int alloc_user_pages(struct hmm_buffer_object *bo,
 	}
 
 	mutex_unlock(&bo->mutex);
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(current->mm);
 	vma = find_vma(current->mm, (unsigned long)userptr);
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 	if (!vma) {
 		dev_err(atomisp_dev, "find_vma failed\n");
 		kfree(bo->page_obj);
diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c
index dbed3f480dc0..20b6fd7383c5 100644
--- a/drivers/tee/optee/call.c
+++ b/drivers/tee/optee/call.c
@@ -565,10 +565,10 @@ static int check_mem_type(unsigned long start, size_t num_pages)
 	if (virt_addr_valid(start))
 		return 0;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	rc = __check_mem_type(find_vma(mm, start),
 			      start + num_pages * PAGE_SIZE);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	return rc;
 }
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 477cdc1e9cf3..7c95afa905a0 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -235,7 +235,7 @@ static void showacpu(void *dummy)
 
 	raw_spin_lock_irqsave(&show_lock, flags);
 	pr_info("CPU%d:\n", smp_processor_id());
-	show_stack(NULL, NULL);
+	show_stack(NULL, NULL, KERN_INFO);
 	raw_spin_unlock_irqrestore(&show_lock, flags);
 }
 
diff --git a/drivers/tty/vt/consolemap.c b/drivers/tty/vt/consolemap.c
index b28aa0d289f8..c1be96bb3ecf 100644
--- a/drivers/tty/vt/consolemap.c
+++ b/drivers/tty/vt/consolemap.c
@@ -12,7 +12,7 @@
  * Fix bug in inverse translation. Stanislav Voronyi <stas@cnti.uanet.kharkov.ua>, Dec 1998
  *
  * In order to prevent the following circular lock dependency:
- *   &mm->mmap_sem --> cpu_hotplug.lock --> console_lock --> &mm->mmap_sem
+ *   &mm->mmap_lock --> cpu_hotplug.lock --> console_lock --> &mm->mmap_lock
  *
  * We cannot allow page fault to happen while holding the console_lock.
  * Therefore, all the userspace copy operations have to be done outside
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 3fc198f3eeb5..7c0779018b1b 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1185,7 +1185,7 @@ reset_info_exit:
 
 		/*
 		 * We need to get memory_lock for each device, but devices
-		 * can share mmap_sem, therefore we need to zap and hold
+		 * can share mmap_lock, therefore we need to zap and hold
 		 * the vma_lock for each device, and only then get each
 		 * memory_lock.
 		 */
@@ -1375,26 +1375,26 @@ static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
 
 	/*
 	 * Lock ordering:
-	 * vma_lock is nested under mmap_sem for vm_ops callback paths.
+	 * vma_lock is nested under mmap_lock for vm_ops callback paths.
 	 * The memory_lock semaphore is used by both code paths calling
 	 * into this function to zap vmas and the vm_ops.fault callback
 	 * to protect the memory enable state of the device.
 	 *
-	 * When zapping vmas we need to maintain the mmap_sem => vma_lock
+	 * When zapping vmas we need to maintain the mmap_lock => vma_lock
 	 * ordering, which requires using vma_lock to walk vma_list to
-	 * acquire an mm, then dropping vma_lock to get the mmap_sem and
+	 * acquire an mm, then dropping vma_lock to get the mmap_lock and
 	 * reacquiring vma_lock.  This logic is derived from similar
 	 * requirements in uverbs_user_mmap_disassociate().
 	 *
-	 * mmap_sem must always be the top-level lock when it is taken.
+	 * mmap_lock must always be the top-level lock when it is taken.
 	 * Therefore we can only hold the memory_lock write lock when
-	 * vma_list is empty, as we'd need to take mmap_sem to clear
+	 * vma_list is empty, as we'd need to take mmap_lock to clear
 	 * entries.  vma_list can only be guaranteed empty when holding
 	 * vma_lock, thus memory_lock is nested under vma_lock.
 	 *
 	 * This enables the vm_ops.fault callback to acquire vma_lock,
 	 * followed by memory_lock read lock, while already holding
-	 * mmap_sem without risk of deadlock.
+	 * mmap_lock without risk of deadlock.
 	 */
 	while (1) {
 		struct mm_struct *mm = NULL;
@@ -1422,17 +1422,17 @@ static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
 		mutex_unlock(&vdev->vma_lock);
 
 		if (try) {
-			if (!down_read_trylock(&mm->mmap_sem)) {
+			if (!mmap_read_trylock(mm)) {
 				mmput(mm);
 				return 0;
 			}
 		} else {
-			down_read(&mm->mmap_sem);
+			mmap_read_lock(mm);
 		}
 		if (mmget_still_valid(mm)) {
 			if (try) {
 				if (!mutex_trylock(&vdev->vma_lock)) {
-					up_read(&mm->mmap_sem);
+					mmap_read_unlock(mm);
 					mmput(mm);
 					return 0;
 				}
@@ -1454,7 +1454,7 @@ static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
 			}
 			mutex_unlock(&vdev->vma_lock);
 		}
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		mmput(mm);
 	}
 }
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 391fafe82c5c..186acd8675ff 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -376,11 +376,11 @@ static int vfio_lock_acct(struct vfio_dma *dma, long npage, bool async)
 	if (!mm)
 		return -ESRCH; /* process exited */
 
-	ret = down_write_killable(&mm->mmap_sem);
+	ret = mmap_write_lock_killable(mm);
 	if (!ret) {
 		ret = __account_locked_vm(mm, abs(npage), npage > 0, dma->task,
 					  dma->lock_cap);
-		up_write(&mm->mmap_sem);
+		mmap_write_unlock(mm);
 	}
 
 	if (async)
@@ -452,7 +452,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 	if (prot & IOMMU_WRITE)
 		flags |= FOLL_WRITE;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	ret = pin_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM,
 				    page, NULL, NULL);
 	if (ret == 1) {
@@ -475,7 +475,7 @@ retry:
 			ret = -EFAULT;
 	}
 done:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	return ret;
 }
 
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 0968361e3b77..40e2a5747c98 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -527,7 +527,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
 	if (!npages)
 		return -EINVAL;
 
-	down_read(&dev->mm->mmap_sem);
+	mmap_read_lock(dev->mm);
 
 	locked = atomic64_add_return(npages, &dev->mm->pinned_vm);
 	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
@@ -580,7 +580,7 @@ out:
 		vhost_vdpa_unmap(v, msg->iova, msg->size);
 		atomic64_sub(npages, &dev->mm->pinned_vm);
 	}
-	up_read(&dev->mm->mmap_sem);
+	mmap_read_unlock(dev->mm);
 	free_page((unsigned long)page_list);
 	return ret;
 }
diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c
index 00dddf6e08b0..504cda38763e 100644
--- a/drivers/video/console/newport_con.c
+++ b/drivers/video/console/newport_con.c
@@ -24,7 +24,6 @@
 #include <asm/io.h>
 #include <linux/uaccess.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/gio_device.h>
 
 #include <video/newport.h>
diff --git a/drivers/video/fbdev/acornfb.c b/drivers/video/fbdev/acornfb.c
index a3af49529173..09a9ad901dad 100644
--- a/drivers/video/fbdev/acornfb.c
+++ b/drivers/video/fbdev/acornfb.c
@@ -30,7 +30,6 @@
 #include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/mach-types.h>
-#include <asm/pgtable.h>
 
 #include "acornfb.h"
 
diff --git a/drivers/video/fbdev/atafb.c b/drivers/video/fbdev/atafb.c
index 51f5d1c56fd9..f253daa05d9d 100644
--- a/drivers/video/fbdev/atafb.c
+++ b/drivers/video/fbdev/atafb.c
@@ -58,7 +58,6 @@
 
 #include <asm/setup.h>
 #include <linux/uaccess.h>
-#include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <asm/io.h>
 
diff --git a/drivers/video/fbdev/cirrusfb.c b/drivers/video/fbdev/cirrusfb.c
index c3a3e344cee3..3df64a973194 100644
--- a/drivers/video/fbdev/cirrusfb.c
+++ b/drivers/video/fbdev/cirrusfb.c
@@ -42,7 +42,6 @@
 #include <linux/delay.h>
 #include <linux/fb.h>
 #include <linux/init.h>
-#include <asm/pgtable.h>
 
 #ifdef CONFIG_ZORRO
 #include <linux/zorro.h>
diff --git a/drivers/video/fbdev/cyber2000fb.c b/drivers/video/fbdev/cyber2000fb.c
index 513f58f28b0f..42d37bed518a 100644
--- a/drivers/video/fbdev/cyber2000fb.c
+++ b/drivers/video/fbdev/cyber2000fb.c
@@ -47,7 +47,6 @@
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 
-#include <asm/pgtable.h>
 
 #ifdef __arm__
 #include <asm/mach-types.h>
diff --git a/drivers/video/fbdev/fb-puv3.c b/drivers/video/fbdev/fb-puv3.c
index 75df6aabac21..030e85c11a78 100644
--- a/drivers/video/fbdev/fb-puv3.c
+++ b/drivers/video/fbdev/fb-puv3.c
@@ -18,7 +18,6 @@
 #include <linux/mm.h>
 
 #include <linux/sizes.h>
-#include <asm/pgtable.h>
 #include <mach/hardware.h>
 
 /* Platform_data reserved for unifb registers. */
diff --git a/drivers/video/fbdev/hitfb.c b/drivers/video/fbdev/hitfb.c
index 009e5d2aa100..bbb0f1d953cc 100644
--- a/drivers/video/fbdev/hitfb.c
+++ b/drivers/video/fbdev/hitfb.c
@@ -23,7 +23,6 @@
 
 #include <asm/machvec.h>
 #include <linux/uaccess.h>
-#include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/hd64461.h>
 #include <cpu/dac.h>
diff --git a/drivers/video/fbdev/neofb.c b/drivers/video/fbdev/neofb.c
index e6ea853c1723..f5a676bfd67a 100644
--- a/drivers/video/fbdev/neofb.c
+++ b/drivers/video/fbdev/neofb.c
@@ -70,7 +70,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/pgtable.h>
 #include <video/vga.h>
 #include <video/neomagic.h>
 
diff --git a/drivers/video/fbdev/q40fb.c b/drivers/video/fbdev/q40fb.c
index 79ff14a35c85..079a2a7fb2c5 100644
--- a/drivers/video/fbdev/q40fb.c
+++ b/drivers/video/fbdev/q40fb.c
@@ -23,7 +23,6 @@
 #include <asm/q40_master.h>
 #include <linux/fb.h>
 #include <linux/module.h>
-#include <asm/pgtable.h>
 
 #define Q40_PHYS_SCREEN_ADDR 0xFE800000
 
diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c
index aab312a7d9da..3c8ae87f0ea7 100644
--- a/drivers/video/fbdev/savage/savagefb_driver.c
+++ b/drivers/video/fbdev/savage/savagefb_driver.c
@@ -55,7 +55,6 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/pgtable.h>
 
 #include "savagefb.h"
 
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 0c142bcab79d..77c57568e5d7 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -59,7 +59,6 @@
 
 #include <asm/page.h>
 #include <asm/pgalloc.h>
-#include <asm/pgtable.h>
 #include <asm/tlb.h>
 
 #include <asm/xen/hypervisor.h>
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 50651e566564..64a9025a87be 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -625,7 +625,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 		return -EFAULT;
 	pr_debug("priv %p, offset for vaddr %lx\n", priv, (unsigned long)op.vaddr);
 
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(current->mm);
 	vma = find_vma(current->mm, op.vaddr);
 	if (!vma || vma->vm_ops != &gntdev_vmops)
 		goto out_unlock;
@@ -639,7 +639,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 	rv = 0;
 
  out_unlock:
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
 	if (rv == 0 && copy_to_user(u, &op, sizeof(op)) != 0)
 		return -EFAULT;
@@ -1014,7 +1014,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		 * to the PTE from going stale.
 		 *
 		 * Since this vma's mappings can't be touched without the
-		 * mmap_sem, and we are holding it now, there is no need for
+		 * mmap_lock, and we are holding it now, there is no need for
 		 * the notifier_range locking pattern.
 		 */
 		mmu_interval_read_begin(&map->notifier);
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 7b36b51cdb9f..8d06bf1cc347 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -64,7 +64,6 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
-#include <asm/pgtable.h>
 #include <asm/sync_bitops.h>
 
 /* External tools reserve first few grant table entries. */
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index b8ccb8990bfd..a250d118144a 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -26,7 +26,6 @@
 #include <linux/moduleparam.h>
 
 #include <asm/pgalloc.h>
-#include <asm/pgtable.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
@@ -277,7 +276,7 @@ static long privcmd_ioctl_mmap(struct file *file, void __user *udata)
 	if (rc || list_empty(&pagelist))
 		goto out;
 
-	down_write(&mm->mmap_sem);
+	mmap_write_lock(mm);
 
 	{
 		struct page *page = list_first_entry(&pagelist,
@@ -302,7 +301,7 @@ static long privcmd_ioctl_mmap(struct file *file, void __user *udata)
 
 
 out_up:
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 
 out:
 	free_page_list(&pagelist);
@@ -498,7 +497,7 @@ static long privcmd_ioctl_mmap_batch(
 		}
 	}
 
-	down_write(&mm->mmap_sem);
+	mmap_write_lock(mm);
 
 	vma = find_vma(mm, m.addr);
 	if (!vma ||
@@ -554,7 +553,7 @@ static long privcmd_ioctl_mmap_batch(
 	BUG_ON(traverse_pages_block(m.num, sizeof(xen_pfn_t),
 				    &pagelist, mmap_batch_fn, &state));
 
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 
 	if (state.global_error) {
 		/* Write back errors in second pass. */
@@ -575,7 +574,7 @@ out:
 	return ret;
 
 out_unlock:
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 	goto out;
 }
 
@@ -740,7 +739,7 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
 	if (data->domid != DOMID_INVALID && data->domid != kdata.dom)
 		return -EPERM;
 
-	down_write(&mm->mmap_sem);
+	mmap_write_lock(mm);
 
 	vma = find_vma(mm, kdata.addr);
 	if (!vma || vma->vm_ops != &privcmd_vm_ops) {
@@ -819,7 +818,7 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
 	}
 
 out:
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 	kfree(pfns);
 
 	return rc;
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 8c4d05b687b7..dc81e9926a76 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -51,7 +51,6 @@
 #include <linux/module.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/xen/hypervisor.h>
 
 #include <xen/xen.h>
diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c
index 9b2fbe69bccc..2ba699897e6d 100644
--- a/drivers/xen/xenbus/xenbus_probe_backend.c
+++ b/drivers/xen/xenbus/xenbus_probe_backend.c
@@ -48,7 +48,6 @@
 #include <linux/semaphore.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/hypervisor.h>
 #include <xen/xenbus.h>
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index 8a1650bbe18f..15379089853b 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -19,7 +19,6 @@
 #include <linux/module.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/xen/hypervisor.h>
 #include <xen/xenbus.h>
 #include <xen/events.h>