[PATCH v2 hmm 1/9] mm/hmm: remove pgmap checking for devmap pages

[Jason Gunthorpe]

From: Jason Gunthorpe <jgg at mellanox.com>

The checking boils down to some racy check if the pagemap is still
available or not. Instead of checking this, rely entirely on the
notifiers, if a pagemap is destroyed then all pages that belong to it must
be removed from the tables and the notifiers triggered.

Reviewed-by: Ralph Campbell <rcampbell at nvidia.com>
Reviewed-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Jason Gunthorpe <jgg at mellanox.com>
---
 mm/hmm.c | 50 ++------------------------------------------------
 1 file changed, 2 insertions(+), 48 deletions(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index a491d9aaafe45d..3a2610e0713329 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -28,7 +28,6 @@
 
 struct hmm_vma_walk {
 	struct hmm_range	*range;
-	struct dev_pagemap	*pgmap;
 	unsigned long		last;
 	unsigned int		flags;
 };
@@ -196,19 +195,8 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
 		return hmm_vma_fault(addr, end, fault, write_fault, walk);
 
 	pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) {
-		if (pmd_devmap(pmd)) {
-			hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
-					      hmm_vma_walk->pgmap);
-			if (unlikely(!hmm_vma_walk->pgmap))
-				return -EBUSY;
-		}
+	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
 		pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
-	}
-	if (hmm_vma_walk->pgmap) {
-		put_dev_pagemap(hmm_vma_walk->pgmap);
-		hmm_vma_walk->pgmap = NULL;
-	}
 	hmm_vma_walk->last = end;
 	return 0;
 }
@@ -300,15 +288,6 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 	if (fault || write_fault)
 		goto fault;
 
-	if (pte_devmap(pte)) {
-		hmm_vma_walk->pgmap = get_dev_pagemap(pte_pfn(pte),
-					      hmm_vma_walk->pgmap);
-		if (unlikely(!hmm_vma_walk->pgmap)) {
-			pte_unmap(ptep);
-			return -EBUSY;
-		}
-	}
-
 	/*
 	 * Since each architecture defines a struct page for the zero page, just
 	 * fall through and treat it like a normal page.
@@ -328,10 +307,6 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 	return 0;
 
 fault:
-	if (hmm_vma_walk->pgmap) {
-		put_dev_pagemap(hmm_vma_walk->pgmap);
-		hmm_vma_walk->pgmap = NULL;
-	}
 	pte_unmap(ptep);
 	/* Fault any virtual address we were asked to fault */
 	return hmm_vma_fault(addr, end, fault, write_fault, walk);
@@ -418,16 +393,6 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
 			return r;
 		}
 	}
-	if (hmm_vma_walk->pgmap) {
-		/*
-		 * We do put_dev_pagemap() here and not in hmm_vma_handle_pte()
-		 * so that we can leverage get_dev_pagemap() optimization which
-		 * will not re-take a reference on a pgmap if we already have
-		 * one.
-		 */
-		put_dev_pagemap(hmm_vma_walk->pgmap);
-		hmm_vma_walk->pgmap = NULL;
-	}
 	pte_unmap(ptep - 1);
 
 	hmm_vma_walk->last = addr;
@@ -491,20 +456,9 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 		}
 
 		pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-		for (i = 0; i < npages; ++i, ++pfn) {
-			hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
-					      hmm_vma_walk->pgmap);
-			if (unlikely(!hmm_vma_walk->pgmap)) {
-				ret = -EBUSY;
-				goto out_unlock;
-			}
+		for (i = 0; i < npages; ++i, ++pfn)
 			pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
 				  cpu_flags;
-		}
-		if (hmm_vma_walk->pgmap) {
-			put_dev_pagemap(hmm_vma_walk->pgmap);
-			hmm_vma_walk->pgmap = NULL;
-		}
 		hmm_vma_walk->last = end;
 		goto out_unlock;
 	}
-- 
2.25.2