mm/hmm: make hmm_range_fault return 0 or -1
hmm_vma_walk->last is supposed to be updated after every write to the
pfns, so that it can be returned by hmm_range_fault(). However, this is
not done consistently. Fortunately nothing checks the return code of
hmm_range_fault() for anything other than error.
More importantly last must be set before returning -EBUSY as it is used to
prevent reading an output pfn as an input flags when the loop restarts.
For clarity and simplicity make hmm_range_fault() return 0 or -ERRNO. Only
set last when returning -EBUSY.
Link: https://lore.kernel.org/r/2-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
diff --git a/mm/hmm.c b/mm/hmm.c
index 2805858..f06bcac 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -174,7 +174,6 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
}
if (required_fault)
return hmm_vma_fault(addr, end, required_fault, walk);
- hmm_vma_walk->last = addr;
return hmm_pfns_fill(addr, end, range, HMM_PFN_NONE);
}
@@ -207,7 +206,6 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
- hmm_vma_walk->last = end;
return 0;
}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -386,13 +384,10 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, pfns);
if (r) {
/* hmm_vma_handle_pte() did pte_unmap() */
- hmm_vma_walk->last = addr;
return r;
}
}
pte_unmap(ptep - 1);
-
- hmm_vma_walk->last = addr;
return 0;
}
@@ -455,7 +450,6 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
for (i = 0; i < npages; ++i, ++pfn)
pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
- hmm_vma_walk->last = end;
goto out_unlock;
}
@@ -500,7 +494,6 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
- hmm_vma_walk->last = end;
spin_unlock(ptl);
return 0;
}
@@ -537,7 +530,6 @@ static int hmm_vma_walk_test(unsigned long start, unsigned long end,
return -EFAULT;
hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
- hmm_vma_walk->last = end;
/* Skip this vma and continue processing the next vma. */
return 1;
@@ -555,9 +547,7 @@ static const struct mm_walk_ops hmm_walk_ops = {
* hmm_range_fault - try to fault some address in a virtual address range
* @range: argument structure
*
- * Return: the number of valid pages in range->pfns[] (from range start
- * address), which may be zero. On error one of the following status codes
- * can be returned:
+ * Returns 0 on success or one of the following error codes:
*
* -EINVAL: Invalid arguments or mm or virtual address is in an invalid vma
* (e.g., device file vma).
@@ -572,7 +562,7 @@ static const struct mm_walk_ops hmm_walk_ops = {
* This is similar to get_user_pages(), except that it can read the page tables
* without mutating them (ie causing faults).
*/
-long hmm_range_fault(struct hmm_range *range)
+int hmm_range_fault(struct hmm_range *range)
{
struct hmm_vma_walk hmm_vma_walk = {
.range = range,
@@ -590,10 +580,13 @@ long hmm_range_fault(struct hmm_range *range)
return -EBUSY;
ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
&hmm_walk_ops, &hmm_vma_walk);
+ /*
+ * When -EBUSY is returned the loop restarts with
+ * hmm_vma_walk.last set to an address that has not been stored
+ * in pfns. All entries < last in the pfn array are set to their
+ * output, and all >= are still at their input values.
+ */
} while (ret == -EBUSY);
-
- if (ret)
- return ret;
- return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
+ return ret;
}
EXPORT_SYMBOL(hmm_range_fault);