The patch titled
Subject: mm/hmm: allow to mirror vma of a file on a DAX backed filesystem
has been removed from the -mm tree. Its filename was
mm-hmm-allow-to-mirror-vma-of-a-file-on-a-dax-backed-filesystem.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: Jérôme Glisse <jglisse@xxxxxxxxxx>
Subject: mm/hmm: allow to mirror vma of a file on a DAX backed filesystem
HMM mirroring allow device to mirror process address onto device.
There is no reason for that mirroring to not work if the virtual
address are the result of an mmap of a file on DAX enabled file-
system.
This adds support to mirror vma which is an mmap of a file which is on a
filesystem that using a DAX block device. There is no reason not to
support that case.
Note that unlike GUP code we do not take page reference hence when we
back-off we have nothing to undo.
There are 3 reasons for this:
1) Convert ODP to use HMM underneath so that we share code between
infiniband ODP and GPU drivers. ODP do support DAX today so i can
not convert ODP to HMM without also supporting DAX in HMM otherwise
i would regress the ODP features.
2) I expect people will be running GPGPU on computer with file that
use DAX and they will want to use HMM there too, in fact from user-
space point of view wether the file is DAX or not should only change
one thing ie for DAX file you will never be able to use GPU memory.
3) I want to convert as many user of GUP to HMM (already posted
several patchset to GPU mailing list for that and i intend to post a
v2 of those latter on). Using HMM avoids GUP and it will avoid the
GUP pin as here we abide by mmu notifier hence we do not want to
inhibit any of the filesystem regular operation. Some of those GPU
driver do allow GUP on DAX file. So again I cannot regress them.
Link: http://lkml.kernel.org/r/20190129165428.3931-10-jglisse@xxxxxxxxxx
Signed-off-by: Jérôme Glisse <jglisse@xxxxxxxxxx>
Reviewed-by: Ralph Campbell <rcampbell@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Christian König <christian.koenig@xxxxxxx>
Cc: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
Cc: Ben Skeggs <bskeggs@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
--- a/mm/hmm.c~mm-hmm-allow-to-mirror-vma-of-a-file-on-a-dax-backed-filesystem
+++ a/mm/hmm.c
@@ -335,6 +335,7 @@ EXPORT_SYMBOL(hmm_mirror_unregister);
struct hmm_vma_walk {
struct hmm_range *range;
+ struct dev_pagemap *pgmap;
unsigned long last;
bool fault;
bool block;
@@ -509,6 +510,15 @@ static inline uint64_t pmd_to_hmm_pfn_fl
range->flags[HMM_PFN_VALID];
}
+static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud)
+{
+ if (!pud_present(pud))
+ return 0;
+ return pud_write(pud) ? range->flags[HMM_PFN_VALID] |
+ range->flags[HMM_PFN_WRITE] :
+ range->flags[HMM_PFN_VALID];
+}
+
static int hmm_vma_handle_pmd(struct mm_walk *walk,
unsigned long addr,
unsigned long end,
@@ -530,8 +540,19 @@ static int hmm_vma_handle_pmd(struct mm_
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
pfn = pmd_pfn(pmd) + pte_index(addr);
- for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
+ 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;
+ }
pfns[i] = hmm_pfn_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;
}
@@ -618,10 +639,24 @@ static int hmm_vma_handle_pte(struct mm_
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))
+ return -EBUSY;
+ } else if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pte_special(pte)) {
+ *pfn = range->values[HMM_PFN_SPECIAL];
+ return -EFAULT;
+ }
+
*pfn = hmm_pfn_from_pfn(range, pte_pfn(pte)) | cpu_flags;
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_walk_hole_(addr, end, fault, write_fault, walk);
@@ -709,12 +744,84 @@ again:
return r;
}
}
+ if (hmm_vma_walk->pgmap) {
+ put_dev_pagemap(hmm_vma_walk->pgmap);
+ hmm_vma_walk->pgmap = NULL;
+ }
pte_unmap(ptep - 1);
hmm_vma_walk->last = addr;
return 0;
}
+static int hmm_vma_walk_pud(pud_t *pudp,
+ 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;
+ struct vm_area_struct *vma = walk->vma;
+ unsigned long addr = start, next;
+ pmd_t *pmdp;
+ pud_t pud;
+ int ret;
+
+again:
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ return hmm_vma_walk_hole(start, end, walk);
+
+ if (pud_huge(pud) && pud_devmap(pud)) {
+ unsigned long i, npages, pfn;
+ uint64_t *pfns, cpu_flags;
+ bool fault, write_fault;
+
+ if (!pud_present(pud))
+ return hmm_vma_walk_hole(start, end, walk);
+
+ i = (addr - range->start) >> PAGE_SHIFT;
+ npages = (end - addr) >> PAGE_SHIFT;
+ pfns = &range->pfns[i];
+
+ cpu_flags = pud_to_hmm_pfn_flags(range, pud);
+ hmm_range_need_fault(hmm_vma_walk, pfns, npages,
+ cpu_flags, &fault, &write_fault);
+ if (fault || write_fault)
+ return hmm_vma_walk_hole_(addr, end, fault,
+ write_fault, walk);
+
+ 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))
+ return -EBUSY;
+ pfns[i] = hmm_pfn_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;
+ }
+
+ split_huge_pud(vma, pudp, addr);
+ if (pud_none(*pudp))
+ goto again;
+
+ pmdp = pmd_offset(pudp, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ ret = hmm_vma_walk_pmd(pmdp, addr, next, walk);
+ if (ret)
+ return ret;
+ } while (pmdp++, addr = next, addr != end);
+
+ return 0;
+}
+
static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
unsigned long start, unsigned long end,
struct mm_walk *walk)
@@ -787,14 +894,6 @@ static void hmm_pfns_clear(struct hmm_ra
*pfns = range->values[HMM_PFN_NONE];
}
-static void hmm_pfns_special(struct hmm_range *range)
-{
- unsigned long addr = range->start, i = 0;
-
- for (; addr < range->end; addr += PAGE_SIZE, i++)
- range->pfns[i] = range->values[HMM_PFN_SPECIAL];
-}
-
/*
* hmm_range_register() - start tracking change to CPU page table over a range
* @range: range
@@ -912,12 +1011,6 @@ long hmm_range_snapshot(struct hmm_range
if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
- /* FIXME support dax */
- if (vma_is_dax(vma)) {
- hmm_pfns_special(range);
- return -EINVAL;
- }
-
if (is_vm_hugetlb_page(vma)) {
struct hstate *h = hstate_vma(vma);
@@ -941,6 +1034,7 @@ long hmm_range_snapshot(struct hmm_range
}
range->vma = vma;
+ hmm_vma_walk.pgmap = NULL;
hmm_vma_walk.last = start;
hmm_vma_walk.fault = false;
hmm_vma_walk.range = range;
@@ -952,6 +1046,7 @@ long hmm_range_snapshot(struct hmm_range
mm_walk.pte_entry = NULL;
mm_walk.test_walk = NULL;
mm_walk.hugetlb_entry = NULL;
+ mm_walk.pud_entry = hmm_vma_walk_pud;
mm_walk.pmd_entry = hmm_vma_walk_pmd;
mm_walk.pte_hole = hmm_vma_walk_hole;
mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry;
@@ -1019,12 +1114,6 @@ long hmm_range_fault(struct hmm_range *r
if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
- /* FIXME support dax */
- if (vma_is_dax(vma)) {
- hmm_pfns_special(range);
- return -EINVAL;
- }
-
if (is_vm_hugetlb_page(vma)) {
struct hstate *h = hstate_vma(vma);
@@ -1048,6 +1137,7 @@ long hmm_range_fault(struct hmm_range *r
}
range->vma = vma;
+ hmm_vma_walk.pgmap = NULL;
hmm_vma_walk.last = start;
hmm_vma_walk.fault = true;
hmm_vma_walk.block = block;
@@ -1060,6 +1150,7 @@ long hmm_range_fault(struct hmm_range *r
mm_walk.pte_entry = NULL;
mm_walk.test_walk = NULL;
mm_walk.hugetlb_entry = NULL;
+ mm_walk.pud_entry = hmm_vma_walk_pud;
mm_walk.pmd_entry = hmm_vma_walk_pmd;
mm_walk.pte_hole = hmm_vma_walk_hole;
mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry;
_
Patches currently in -mm which might be from jglisse@xxxxxxxxxx are
mm-hmm-add-helpers-for-driver-to-safely-take-the-mmap_sem.patch
