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/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst
index 4e3e9362afeb10e642e732dea04f1850da9069fa..9924f2caa0184c18670cad0894635ac417d48194 100644 (file)
--- a/Documentation/vm/hmm.rst
+++ b/Documentation/vm/hmm.rst
@@ -161,7 +161,7 @@ device must complete the update before the driver callback returns.
 When the device driver wants to populate a range of virtual addresses, it can
 use::
 
-  long hmm_range_fault(struct hmm_range *range);
+  int hmm_range_fault(struct hmm_range *range);
 
 It will trigger a page fault on missing or read-only entries if write access is
 requested (see below). Page faults use the generic mm page fault code path just

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 6309ff72bd78765f45baa9772058becc52dbf12e..7eb745b8acce0f0da3842033a7d8c760092157a7 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -852,12 +852,12 @@ retry:
        down_read(&mm->mmap_sem);
        r = hmm_range_fault(range);
        up_read(&mm->mmap_sem);
-       if (unlikely(r <= 0)) {
+       if (unlikely(r)) {
                /*
                 * FIXME: This timeout should encompass the retry from
                 * mmu_interval_read_retry() as well.
                 */
-               if ((r == 0 || r == -EBUSY) && !time_after(jiffies, timeout))
+               if (r == -EBUSY && !time_after(jiffies, timeout))
                        goto retry;
                goto out_free_pfns;
        }

diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 645fedd77e21b4fea8fe6ee9da7eb15da371c6db..c68e9317cf07407a748119096f160920f9f744f1 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -536,7 +536,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
                .pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT,
        };
        struct mm_struct *mm = notifier->notifier.mm;
-       long ret;
+       int ret;
 
        while (true) {
                if (time_after(jiffies, timeout))
@@ -548,8 +548,8 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
                down_read(&mm->mmap_sem);
                ret = hmm_range_fault(&range);
                up_read(&mm->mmap_sem);
-               if (ret <= 0) {
-                       if (ret == 0 || ret == -EBUSY)
+               if (ret) {
+                       if (ret == -EBUSY)
                                continue;
                        return ret;
                }

diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 7475051100c7825675f499ad5ac93a8706a3f633..0df27dd03d53d76575c9877f2a1aa0cf17d1bf6d 100644 (file)
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -120,7 +120,7 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang
 /*
  * Please see Documentation/vm/hmm.rst for how to use the range API.
  */
-long hmm_range_fault(struct hmm_range *range);
+int hmm_range_fault(struct hmm_range *range);
 
 /*
  * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range

diff --git a/mm/hmm.c b/mm/hmm.c
index 280585833adfc1b35eddd11c0ee28d15b0ef60ad..f06bcac948a79bf80871935f36e96388f823e46f 100644 (file)
--- 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 @@ again:
                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);