[PATCH v13 03/11] mm/hmm: preparations for HMM to participate in migration

[mpenttil@redhat.com]

From: Mika Penttilä <mpenttil@redhat.com>

For migration to happen after hmm_range_fault(), the vma has to
retrieved. Luckily, pagewalk already resolves that for us, so
just have to save it for further use. For migration, mmap_lock
has to be hold for the whole operation, so vma stays stable.

Take care also of firing the mmu_notifier when migrating.

Also, prepare for differencies of how mm_struct * is retrieved
in fault and migrate_vma paths.

Cc: David Hildenbrand <david@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Suggested-by: Alistair Popple <apopple@nvidia.com>
Signed-off-by: Mika Penttilä <mpenttil@redhat.com>
---
 include/linux/migrate.h | 45 ++++++++++++++++++++-
 lib/test_hmm.c          |  2 +-
 mm/hmm.c                | 86 ++++++++++++++++++++++++++++++++++++++---
 3 files changed, 125 insertions(+), 8 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 425ab5242da0..7380a89756ee 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -106,6 +106,28 @@ static inline void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *p
 	spin_unlock(ptl);
 }
 
+enum migrate_vma_info {
+	MIGRATE_VMA_SELECT_NONE = 0,
+	MIGRATE_VMA_SELECT_COMPOUND = MIGRATE_VMA_SELECT_NONE,
+};
+
+static inline enum migrate_vma_info hmm_select_migrate(struct hmm_range *range)
+{
+	return MIGRATE_VMA_SELECT_NONE;
+}
+
+static inline void hmm_fill_migrate_vma(struct hmm_range *range,
+					struct vm_area_struct *vma,
+					unsigned long start,
+					unsigned long end)
+{
+}
+
+static inline struct mm_struct *hmm_range_fault_mm(struct hmm_range *range)
+{
+	return range->notifier->mm;
+}
+
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -149,7 +171,7 @@ static inline unsigned long migrate_pfn(unsigned long pfn)
 	return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID;
 }
 
-enum migrate_vma_direction {
+enum migrate_vma_info {
 	MIGRATE_VMA_SELECT_SYSTEM = 1 << 0,
 	MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1,
 	MIGRATE_VMA_SELECT_DEVICE_COHERENT = 1 << 2,
@@ -191,6 +213,27 @@ struct migrate_vma {
 	struct page		*fault_page;
 };
 
+// TODO: enable migration
+static inline enum migrate_vma_info hmm_select_migrate(struct hmm_range *range)
+{
+	return 0;
+}
+
+static inline struct mm_struct *hmm_range_fault_mm(struct hmm_range *range)
+{
+	return range->notifier ? range->notifier->mm : range->migrate->vma->vm_mm;
+}
+
+static inline void hmm_fill_migrate_vma(struct hmm_range *range,
+					struct vm_area_struct *vma,
+					unsigned long start,
+					unsigned long end)
+{
+	range->migrate->vma   = vma;
+	range->migrate->start = start;
+	range->migrate->end   = end;
+}
+
 int migrate_vma_setup(struct migrate_vma *args);
 void migrate_vma_pages(struct migrate_vma *migrate);
 void migrate_vma_finalize(struct migrate_vma *migrate);
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index c4adbf98fac7..79cb7487d211 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -145,7 +145,7 @@ static bool dmirror_is_private_zone(struct dmirror_device *mdevice)
 		HMM_DMIRROR_MEMORY_DEVICE_PRIVATE);
 }
 
-static enum migrate_vma_direction
+static enum migrate_vma_info
 dmirror_select_device(struct dmirror *dmirror)
 {
 	return (dmirror->mdevice->zone_device_type ==
diff --git a/mm/hmm.c b/mm/hmm.c
index c72c9ddfdb2f..637c00188b3e 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -20,6 +20,7 @@
 #include <linux/pagemap.h>
 #include <linux/leafops.h>
 #include <linux/hugetlb.h>
+#include <linux/migrate.h>
 #include <linux/memremap.h>
 #include <linux/sched/mm.h>
 #include <linux/jump_label.h>
@@ -27,12 +28,17 @@
 #include <linux/pci-p2pdma.h>
 #include <linux/mmu_notifier.h>
 #include <linux/memory_hotplug.h>
+#include <asm/tlbflush.h>
 
 #include "internal.h"
 
 struct hmm_vma_walk {
-	struct hmm_range	*range;
-	unsigned long		last;
+	struct mmu_notifier_range	mmu_range;
+	struct vm_area_struct		*vma;
+	struct hmm_range		*range;
+	unsigned long			start;
+	unsigned long			end;
+	unsigned long			last;
 };
 
 enum {
@@ -393,6 +399,57 @@ static int hmm_vma_handle_absent_pmd(struct mm_walk *walk, unsigned long start,
 }
 #endif  /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
 
+static int hmm_vma_capture_migrate_range(unsigned long start,
+					 unsigned long end,
+					 struct mm_walk *walk)
+{
+	struct hmm_vma_walk *hmm_vma_walk = walk->private;
+	struct hmm_range *range = hmm_vma_walk->range;
+
+	if (!hmm_select_migrate(range))
+		return 0;
+
+	if (hmm_vma_walk->vma && (hmm_vma_walk->vma != walk->vma))
+		return -ERANGE;
+
+	hmm_vma_walk->vma = walk->vma;
+	hmm_vma_walk->start = start;
+	hmm_vma_walk->end = end;
+
+	if (end - start > range->end - range->start)
+		return -ERANGE;
+
+	if (!hmm_vma_walk->mmu_range.owner) {
+		mmu_notifier_range_init_owner(&hmm_vma_walk->mmu_range, MMU_NOTIFY_MIGRATE, 0,
+					      walk->vma->vm_mm, start, end,
+					      range->dev_private_owner);
+		mmu_notifier_invalidate_range_start(&hmm_vma_walk->mmu_range);
+	}
+
+	return 0;
+}
+
+static void hmm_vma_post_range_fault(struct hmm_vma_walk *hmm_vma_walk)
+{
+
+	struct hmm_range *range = hmm_vma_walk->range;
+
+	if (hmm_select_migrate(range) &&
+	    hmm_vma_walk->mmu_range.owner) {
+		/*
+		 *  The migrate_vma path has the following initialized,
+		 *  so take care of fault path below.
+		 */
+		if (range->notifier) {
+			hmm_fill_migrate_vma(range,
+					     hmm_vma_walk->vma,
+					     hmm_vma_walk->start,
+					     hmm_vma_walk->end);
+		}
+		mmu_notifier_invalidate_range_end(&hmm_vma_walk->mmu_range);
+	}
+}
+
 static int hmm_vma_walk_pmd(pmd_t *pmdp,
 			    unsigned long start,
 			    unsigned long end,
@@ -600,6 +657,11 @@ static int hmm_vma_walk_test(unsigned long start, unsigned long end,
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
 	struct vm_area_struct *vma = walk->vma;
+	int r;
+
+	r = hmm_vma_capture_migrate_range(start, end, walk);
+	if (r)
+		return r;
 
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)) &&
 	    vma->vm_flags & VM_READ)
@@ -662,16 +724,25 @@ int hmm_range_fault(struct hmm_range *range)
 		.range = range,
 		.last = range->start,
 	};
-	struct mm_struct *mm = range->notifier->mm;
+	/*
+	 *  Could be serving a device fault or come from migrate
+	 *  entry point. For the former we have not resolved the vma
+	 *  yet, and the latter we don't have a notifier (but have a vma).
+	 *
+	 */
+	struct mm_struct *mm = hmm_range_fault_mm(range);
 	int ret;
 
 	mmap_assert_locked(mm);
 
 	do {
 		/* If range is no longer valid force retry. */
-		if (mmu_interval_check_retry(range->notifier,
-					     range->notifier_seq))
-			return -EBUSY;
+		if (range->notifier && mmu_interval_check_retry(range->notifier,
+								range->notifier_seq)) {
+			ret = -EBUSY;
+			break;
+		}
+
 		ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
 				      &hmm_walk_ops, &hmm_vma_walk);
 		/*
@@ -681,6 +752,9 @@ int hmm_range_fault(struct hmm_range *range)
 		 * output, and all >= are still at their input values.
 		 */
 	} while (ret == -EBUSY);
+
+	hmm_vma_post_range_fault(&hmm_vma_walk);
+
 	return ret;
 }
 EXPORT_SYMBOL(hmm_range_fault);
-- 
2.55.0