mm/mmu_notifier: use structure for invalidate_range_start/end callback

Patch series "mmu notifier contextual informations", v2.

This patchset adds contextual information, why an invalidation is
happening, to mmu notifier callback.  This is necessary for user of mmu
notifier that wish to maintains their own data structure without having to
add new fields to struct vm_area_struct (vma).

For instance device can have they own page table that mirror the process
address space.  When a vma is unmap (munmap() syscall) the device driver
can free the device page table for the range.

Today we do not have any information on why a mmu notifier call back is
happening and thus device driver have to assume that it is always an
munmap().  This is inefficient at it means that it needs to re-allocate
device page table on next page fault and rebuild the whole device driver
data structure for the range.

Other use case beside munmap() also exist, for instance it is pointless
for device driver to invalidate the device page table when the
invalidation is for the soft dirtyness tracking.  Or device driver can
optimize away mprotect() that change the page table permission access for
the range.

This patchset enables all this optimizations for device drivers.  I do not
include any of those in this series but another patchset I am posting will
leverage this.

The patchset is pretty simple from a code point of view.  The first two
patches consolidate all mmu notifier arguments into a struct so that it is
easier to add/change arguments.  The last patch adds the contextual
information (munmap, protection, soft dirty, clear, ...).

This patch (of 3):

To avoid having to change many callback definition everytime we want to
add a parameter use a structure to group all parameters for the
mmu_notifier invalidate_range_start/end callback.  No functional changes
with this patch.

[akpm@linux-foundation.org: fix drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c kerneldoc]
Link: http://lkml.kernel.org/r/20181205053628.3210-2-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Jason Gunthorpe <jgg@mellanox.com>	[infiniband]
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Ross Zwisler <zwisler@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Felix Kuehling <felix.kuehling@amd.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 13 insertions, 20 deletions

diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 9608681224e6..a4ec43093cb3 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -146,15 +146,12 @@ static int invalidate_range_start_trampoline(struct ib_umem_odp *item,
 }
 
 static int ib_umem_notifier_invalidate_range_start(struct mmu_notifier *mn,
-						    struct mm_struct *mm,
-						    unsigned long start,
-						    unsigned long end,
-						    bool blockable)
+				const struct mmu_notifier_range *range)
 {
 	struct ib_ucontext_per_mm *per_mm =
 		container_of(mn, struct ib_ucontext_per_mm, mn);
 
-	if (blockable)
+	if (range->blockable)
 		down_read(&per_mm->umem_rwsem);
 	else if (!down_read_trylock(&per_mm->umem_rwsem))
 		return -EAGAIN;
@@ -169,9 +166,10 @@ static int ib_umem_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		return 0;
 	}
 
-	return rbt_ib_umem_for_each_in_range(&per_mm->umem_tree, start, end,
+	return rbt_ib_umem_for_each_in_range(&per_mm->umem_tree, range->start,
+					     range->end,
 					     invalidate_range_start_trampoline,
-					     blockable, NULL);
+					     range->blockable, NULL);
 }
 
 static int invalidate_range_end_trampoline(struct ib_umem_odp *item, u64 start,
@@ -182,9 +180,7 @@ static int invalidate_range_end_trampoline(struct ib_umem_odp *item, u64 start,
 }
 
 static void ib_umem_notifier_invalidate_range_end(struct mmu_notifier *mn,
-						  struct mm_struct *mm,
-						  unsigned long start,
-						  unsigned long end)
+				const struct mmu_notifier_range *range)
 {
 	struct ib_ucontext_per_mm *per_mm =
 		container_of(mn, struct ib_ucontext_per_mm, mn);
@@ -192,8 +188,8 @@ static void ib_umem_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	if (unlikely(!per_mm->active))
 		return;
 
-	rbt_ib_umem_for_each_in_range(&per_mm->umem_tree, start,
-				      end,
+	rbt_ib_umem_for_each_in_range(&per_mm->umem_tree, range->start,
+				      range->end,
 				      invalidate_range_end_trampoline, true, NULL);
 	up_read(&per_mm->umem_rwsem);
 }
diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c
index 475b769e120c..14d2a90964c3 100644
--- a/drivers/infiniband/hw/hfi1/mmu_rb.c
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.c
@@ -68,8 +68,7 @@ struct mmu_rb_handler {
 static unsigned long mmu_node_start(struct mmu_rb_node *);
 static unsigned long mmu_node_last(struct mmu_rb_node *);
 static int mmu_notifier_range_start(struct mmu_notifier *,
-				     struct mm_struct *,
-				     unsigned long, unsigned long, bool);
+		const struct mmu_notifier_range *);
 static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *,
 					   unsigned long, unsigned long);
 static void do_remove(struct mmu_rb_handler *handler,
@@ -284,10 +283,7 @@ void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler,
 }
 
 static int mmu_notifier_range_start(struct mmu_notifier *mn,
-				     struct mm_struct *mm,
-				     unsigned long start,
-				     unsigned long end,
-				     bool blockable)
+		const struct mmu_notifier_range *range)
 {
 	struct mmu_rb_handler *handler =
 		container_of(mn, struct mmu_rb_handler, mn);
@@ -297,10 +293,11 @@ static int mmu_notifier_range_start(struct mmu_notifier *mn,
 	bool added = false;
 
 	spin_lock_irqsave(&handler->lock, flags);
-	for (node = __mmu_int_rb_iter_first(root, start, end - 1);
+	for (node = __mmu_int_rb_iter_first(root, range->start, range->end-1);
 	     node; node = ptr) {
 		/* Guard against node removal. */
-		ptr = __mmu_int_rb_iter_next(node, start, end - 1);
+		ptr = __mmu_int_rb_iter_next(node, range->start,
+					     range->end - 1);
 		trace_hfi1_mmu_mem_invalidate(node->addr, node->len);
 		if (handler->ops->invalidate(handler->ops_arg, node)) {
 			__mmu_int_rb_remove(node, root);