The patch titled
Subject: mm/hmm: allow to mirror vma of a file on a DAX backed filesystem
has been added to the -mm tree. Its filename is
mm-hmm-allow-to-mirror-vma-of-a-file-on-a-dax-backed-filesystem-v3.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hmm-allow-to-mirror-vma-of-a-file-on-a-dax-backed-filesystem-v3.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hmm-allow-to-mirror-vma-of-a-file-on-a-dax-backed-filesystem-v3.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Jérôme Glisse <jglisse@xxxxxxxxxx>
Subject: mm/hmm: allow to mirror vma of a file on a DAX backed filesystem
HMM mirror is a device driver helpers to mirror range of virtual address.
It means that the process jobs running on the device can access the same
virtual address as the CPU threads of that process. This patch adds
support for mirroring mapping of file that are on a DAX block device (ie
range of virtual address that is an mmap of a file in a filesystem on a
DAX block device). There is no reason to not support such case when
mirroring virtual address on a device.
Note that unlike GUP code we do not take page reference hence when we
back-off we have nothing to undo.
Link: http://lkml.kernel.org/r/20190403193318.16478-10-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: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Balbir Singh <bsingharora@xxxxxxxxx>
Cc: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Cc: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Souptick Joarder <jrdr.linux@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/hmm.c | 138 ++++++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 117 insertions(+), 21 deletions(-)
--- a/mm/hmm.c~mm-hmm-allow-to-mirror-vma-of-a-file-on-a-dax-backed-filesystem-v3
+++ a/mm/hmm.c
@@ -329,6 +329,7 @@ EXPORT_SYMBOL(hmm_mirror_unregister);
struct hmm_vma_walk {
struct hmm_range *range;
+ struct dev_pagemap *pgmap;
unsigned long last;
bool fault;
bool block;
@@ -503,6 +504,15 @@ 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,
@@ -524,8 +534,19 @@ 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;
}
@@ -612,10 +633,24 @@ 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);
@@ -703,12 +738,89 @@ again:
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;
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;
+ 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(walk->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)
@@ -781,14 +893,6 @@ 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
@@ -906,12 +1010,6 @@ 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);
@@ -935,6 +1033,7 @@ 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;
@@ -946,6 +1045,7 @@ 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;
@@ -1011,12 +1111,6 @@ 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)) {
if (huge_page_shift(hstate_vma(vma)) !=
range->page_shift &&
@@ -1039,6 +1133,7 @@ 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;
@@ -1051,6 +1146,7 @@ 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-select-mmu-notifier-when-selecting-hmm-v2.patch
mm-hmm-use-reference-counting-for-hmm-struct-v3.patch
mm-hmm-do-not-erase-snapshot-when-a-range-is-invalidated.patch
mm-hmm-improve-and-rename-hmm_vma_get_pfns-to-hmm_range_snapshot-v2.patch
mm-hmm-improve-and-rename-hmm_vma_fault-to-hmm_range_fault-v3.patch
mm-hmm-improve-driver-api-to-work-and-wait-over-a-range-v3.patch
mm-hmm-add-default-fault-flags-to-avoid-the-need-to-pre-fill-pfns-arrays-v2.patch
mm-hmm-mirror-hugetlbfs-snapshoting-faulting-and-dma-mapping-v3.patch
mm-hmm-allow-to-mirror-vma-of-a-file-on-a-dax-backed-filesystem-v3.patch
mm-hmm-add-helpers-to-test-if-mm-is-still-alive-or-not.patch
mm-hmm-add-an-helper-function-that-fault-pages-and-map-them-to-a-device-v3.patch
mm-hmm-convert-various-hmm_pfn_-to-device_entry-which-is-a-better-name.patch
