Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull hmm updates from Jason Gunthorpe:
 "This is more cleanup and consolidation of the hmm APIs and the very
  strongly related mmu_notifier interfaces. Many places across the tree
  using these interfaces are touched in the process. Beyond that a
  cleanup to the page walker API and a few memremap related changes
  round out the series:

   - General improvement of hmm_range_fault() and related APIs, more
     documentation, bug fixes from testing, API simplification &
     consolidation, and unused API removal

   - Simplify the hmm related kconfigs to HMM_MIRROR and DEVICE_PRIVATE,
     and make them internal kconfig selects

   - Hoist a lot of code related to mmu notifier attachment out of
     drivers by using a refcount get/put attachment idiom and remove the
     convoluted mmu_notifier_unregister_no_release() and related APIs.

   - General API improvement for the migrate_vma API and revision of its
     only user in nouveau

   - Annotate mmu_notifiers with lockdep and sleeping region debugging

  Two series unrelated to HMM or mmu_notifiers came along due to
  dependencies:

   - Allow pagemap's memremap_pages family of APIs to work without
     providing a struct device

   - Make walk_page_range() and related use a constant structure for
     function pointers"

* tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (75 commits)
  libnvdimm: Enable unit test infrastructure compile checks
  mm, notifier: Catch sleeping/blocking for !blockable
  kernel.h: Add non_block_start/end()
  drm/radeon: guard against calling an unpaired radeon_mn_unregister()
  csky: add missing brackets in a macro for tlb.h
  pagewalk: use lockdep_assert_held for locking validation
  pagewalk: separate function pointers from iterator data
  mm: split out a new pagewalk.h header from mm.h
  mm/mmu_notifiers: annotate with might_sleep()
  mm/mmu_notifiers: prime lockdep
  mm/mmu_notifiers: add a lockdep map for invalidate_range_start/end
  mm/mmu_notifiers: remove the __mmu_notifier_invalidate_range_start/end exports
  mm/hmm: hmm_range_fault() infinite loop
  mm/hmm: hmm_range_fault() NULL pointer bug
  mm/hmm: fix hmm_range_fault()'s handling of swapped out pages
  mm/mmu_notifiers: remove unregister_no_release
  RDMA/odp: remove ib_ucontext from ib_umem
  RDMA/odp: use mmu_notifier_get/put for 'struct ib_ucontext_per_mm'
  RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
  RDMA/mlx5: Use ib_umem_start instead of umem.address
  ...

1 files changed, 42 insertions, 38 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 731642e0f5a0..bf43d1d60059 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/mm.h>
+#include <linux/pagewalk.h>
 #include <linux/vmacache.h>
 #include <linux/hugetlb.h>
 #include <linux/huge_mm.h>
@@ -513,7 +513,9 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end,
 
 	return 0;
 }
-#endif
+#else
+#define smaps_pte_hole		NULL
+#endif /* CONFIG_SHMEM */
 
 static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		struct mm_walk *walk)
@@ -729,21 +731,24 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 	}
 	return 0;
 }
+#else
+#define smaps_hugetlb_range	NULL
 #endif /* HUGETLB_PAGE */
 
+static const struct mm_walk_ops smaps_walk_ops = {
+	.pmd_entry		= smaps_pte_range,
+	.hugetlb_entry		= smaps_hugetlb_range,
+};
+
+static const struct mm_walk_ops smaps_shmem_walk_ops = {
+	.pmd_entry		= smaps_pte_range,
+	.hugetlb_entry		= smaps_hugetlb_range,
+	.pte_hole		= smaps_pte_hole,
+};
+
 static void smap_gather_stats(struct vm_area_struct *vma,
 			     struct mem_size_stats *mss)
 {
-	struct mm_walk smaps_walk = {
-		.pmd_entry = smaps_pte_range,
-#ifdef CONFIG_HUGETLB_PAGE
-		.hugetlb_entry = smaps_hugetlb_range,
-#endif
-		.mm = vma->vm_mm,
-	};
-
-	smaps_walk.private = mss;
-
 #ifdef CONFIG_SHMEM
 	/* In case of smaps_rollup, reset the value from previous vma */
 	mss->check_shmem_swap = false;
@@ -765,12 +770,13 @@ static void smap_gather_stats(struct vm_area_struct *vma,
 			mss->swap += shmem_swapped;
 		} else {
 			mss->check_shmem_swap = true;
-			smaps_walk.pte_hole = smaps_pte_hole;
+			walk_page_vma(vma, &smaps_shmem_walk_ops, mss);
+			return;
 		}
 	}
 #endif
 	/* mmap_sem is held in m_start */
-	walk_page_vma(vma, &smaps_walk);
+	walk_page_vma(vma, &smaps_walk_ops, mss);
 }
 
 #define SEQ_PUT_DEC(str, val) \
@@ -1118,6 +1124,11 @@ static int clear_refs_test_walk(unsigned long start, unsigned long end,
 	return 0;
 }
 
+static const struct mm_walk_ops clear_refs_walk_ops = {
+	.pmd_entry		= clear_refs_pte_range,
+	.test_walk		= clear_refs_test_walk,
+};
+
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -1151,12 +1162,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		struct clear_refs_private cp = {
 			.type = type,
 		};
-		struct mm_walk clear_refs_walk = {
-			.pmd_entry = clear_refs_pte_range,
-			.test_walk = clear_refs_test_walk,
-			.mm = mm,
-			.private = &cp,
-		};
 
 		if (type == CLEAR_REFS_MM_HIWATER_RSS) {
 			if (down_write_killable(&mm->mmap_sem)) {
@@ -1217,7 +1222,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 						0, NULL, mm, 0, -1UL);
 			mmu_notifier_invalidate_range_start(&range);
 		}
-		walk_page_range(0, mm->highest_vm_end, &clear_refs_walk);
+		walk_page_range(mm, 0, mm->highest_vm_end, &clear_refs_walk_ops,
+				&cp);
 		if (type == CLEAR_REFS_SOFT_DIRTY)
 			mmu_notifier_invalidate_range_end(&range);
 		tlb_finish_mmu(&tlb, 0, -1);
@@ -1489,8 +1495,16 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
 
 	return err;
 }
+#else
+#define pagemap_hugetlb_range	NULL
 #endif /* HUGETLB_PAGE */
 
+static const struct mm_walk_ops pagemap_ops = {
+	.pmd_entry	= pagemap_pmd_range,
+	.pte_hole	= pagemap_pte_hole,
+	.hugetlb_entry	= pagemap_hugetlb_range,
+};
+
 /*
  * /proc/pid/pagemap - an array mapping virtual pages to pfns
  *
@@ -1522,7 +1536,6 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 {
 	struct mm_struct *mm = file->private_data;
 	struct pagemapread pm;
-	struct mm_walk pagemap_walk = {};
 	unsigned long src;
 	unsigned long svpfn;
 	unsigned long start_vaddr;
@@ -1550,14 +1563,6 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!pm.buffer)
 		goto out_mm;
 
-	pagemap_walk.pmd_entry = pagemap_pmd_range;
-	pagemap_walk.pte_hole = pagemap_pte_hole;
-#ifdef CONFIG_HUGETLB_PAGE
-	pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
-#endif
-	pagemap_walk.mm = mm;
-	pagemap_walk.private = &pm;
-
 	src = *ppos;
 	svpfn = src / PM_ENTRY_BYTES;
 	start_vaddr = svpfn << PAGE_SHIFT;
@@ -1586,7 +1591,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		ret = down_read_killable(&mm->mmap_sem);
 		if (ret)
 			goto out_free;
-		ret = walk_page_range(start_vaddr, end, &pagemap_walk);
+		ret = walk_page_range(mm, start_vaddr, end, &pagemap_ops, &pm);
 		up_read(&mm->mmap_sem);
 		start_vaddr = end;
 
@@ -1798,6 +1803,11 @@ static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 }
 #endif
 
+static const struct mm_walk_ops show_numa_ops = {
+	.hugetlb_entry = gather_hugetlb_stats,
+	.pmd_entry = gather_pte_stats,
+};
+
 /*
  * Display pages allocated per node and memory policy via /proc.
  */
@@ -1809,12 +1819,6 @@ static int show_numa_map(struct seq_file *m, void *v)
 	struct numa_maps *md = &numa_priv->md;
 	struct file *file = vma->vm_file;
 	struct mm_struct *mm = vma->vm_mm;
-	struct mm_walk walk = {
-		.hugetlb_entry = gather_hugetlb_stats,
-		.pmd_entry = gather_pte_stats,
-		.private = md,
-		.mm = mm,
-	};
 	struct mempolicy *pol;
 	char buffer[64];
 	int nid;
@@ -1848,7 +1852,7 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_puts(m, " huge");
 
 	/* mmap_sem is held by m_start */
-	walk_page_vma(vma, &walk);
+	walk_page_vma(vma, &show_numa_ops, md);
 
 	if (!md->pages)
 		goto out;