From: Dan Williams <dan.j.williams@intel.com>
To: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Linux MM <linux-mm@kvack.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Ralph Campbell <rcampbell@nvidia.com>,
John Hubbard <jhubbard@nvidia.com>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>
Subject: Re: [PATCH 09/10] mm/hmm: allow to mirror vma of a file on a DAX backed filesystem
Date: Tue, 29 Jan 2019 10:41:23 -0800 [thread overview]
Message-ID: <CAPcyv4gNtDQf0mHwhZ8g3nX6ShsjA1tx2KLU_ZzTH1Z1AeA_CA@mail.gmail.com> (raw)
In-Reply-To: <20190129165428.3931-10-jglisse@redhat.com>
On Tue, Jan 29, 2019 at 8:54 AM <jglisse@redhat.com> wrote:
>
> From: Jérôme Glisse <jglisse@redhat.com>
>
> This add 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.
>
The reason not to support it would be if it gets in the way of future
DAX development. How does this interact with MAP_SYNC? I'm also
concerned if this complicates DAX reflink support. In general I'd
rather prioritize fixing the places where DAX is broken today before
adding more cross-subsystem entanglements. The unit tests for
filesystems (xfstests) are readily accessible. How would I go about
regression testing DAX + HMM interactions?
> Note that unlike GUP code we do not take page reference hence when we
> back-off we have nothing to undo.
>
> Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Dan Williams <dan.j.williams@intel.com>
> Cc: Ralph Campbell <rcampbell@nvidia.com>
> Cc: John Hubbard <jhubbard@nvidia.com>
> ---
> mm/hmm.c | 133 ++++++++++++++++++++++++++++++++++++++++++++++---------
> 1 file changed, 112 insertions(+), 21 deletions(-)
>
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 8b87e1813313..1a444885404e 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -334,6 +334,7 @@ EXPORT_SYMBOL(hmm_mirror_unregister);
>
> struct hmm_vma_walk {
> struct hmm_range *range;
> + struct dev_pagemap *pgmap;
> unsigned long last;
> bool fault;
> bool block;
> @@ -508,6 +509,15 @@ static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
> 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,
> @@ -529,8 +539,19 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk,
> 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;
> }
> @@ -617,10 +638,24 @@ 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))
> + 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);
> @@ -708,12 +743,84 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
> 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)
> @@ -786,14 +893,6 @@ static void hmm_pfns_clear(struct hmm_range *range,
> *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
> @@ -911,12 +1010,6 @@ long hmm_range_snapshot(struct hmm_range *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);
>
> @@ -940,6 +1033,7 @@ long hmm_range_snapshot(struct hmm_range *range)
> }
>
> range->vma = vma;
> + hmm_vma_walk.pgmap = NULL;
> hmm_vma_walk.last = start;
> hmm_vma_walk.fault = false;
> hmm_vma_walk.range = range;
> @@ -951,6 +1045,7 @@ long hmm_range_snapshot(struct hmm_range *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;
> @@ -1018,12 +1113,6 @@ long hmm_range_fault(struct hmm_range *range, bool block)
> 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);
>
> @@ -1047,6 +1136,7 @@ long hmm_range_fault(struct hmm_range *range, bool block)
> }
>
> range->vma = vma;
> + hmm_vma_walk.pgmap = NULL;
> hmm_vma_walk.last = start;
> hmm_vma_walk.fault = true;
> hmm_vma_walk.block = block;
> @@ -1059,6 +1149,7 @@ long hmm_range_fault(struct hmm_range *range, bool block)
> 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;
> --
> 2.17.2
>
next prev parent reply other threads:[~2019-01-29 18:41 UTC|newest]
Thread overview: 98+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-29 16:54 [PATCH 00/10] HMM updates for 5.1 jglisse
2019-01-29 16:54 ` [PATCH 01/10] mm/hmm: use reference counting for HMM struct jglisse
2019-02-20 23:47 ` John Hubbard
2019-02-20 23:59 ` Jerome Glisse
2019-02-21 0:06 ` John Hubbard
2019-02-21 0:15 ` Jerome Glisse
2019-02-21 0:32 ` John Hubbard
2019-02-21 0:37 ` Jerome Glisse
2019-02-21 0:42 ` John Hubbard
2019-01-29 16:54 ` [PATCH 02/10] mm/hmm: do not erase snapshot when a range is invalidated jglisse
2019-02-20 23:58 ` John Hubbard
2019-01-29 16:54 ` [PATCH 03/10] mm/hmm: improve and rename hmm_vma_get_pfns() to hmm_range_snapshot() jglisse
2019-02-21 0:25 ` John Hubbard
2019-02-21 0:28 ` Jerome Glisse
2019-01-29 16:54 ` [PATCH 04/10] mm/hmm: improve and rename hmm_vma_fault() to hmm_range_fault() jglisse
2019-01-29 16:54 ` [PATCH 05/10] mm/hmm: improve driver API to work and wait over a range jglisse
2019-01-29 16:54 ` [PATCH 06/10] mm/hmm: add default fault flags to avoid the need to pre-fill pfns arrays jglisse
2019-01-29 16:54 ` [PATCH 07/10] mm/hmm: add an helper function that fault pages and map them to a device jglisse
2019-03-18 20:21 ` Dan Williams
2019-03-18 20:41 ` Jerome Glisse
2019-03-18 21:30 ` Dan Williams
2019-03-18 22:15 ` Jerome Glisse
2019-03-19 3:29 ` Dan Williams
2019-03-19 13:30 ` Jerome Glisse
2019-03-19 8:44 ` Ira Weiny
2019-03-19 17:10 ` Jerome Glisse
2019-03-19 14:10 ` Ira Weiny
2019-01-29 16:54 ` [PATCH 08/10] mm/hmm: support hugetlbfs (snap shoting, faulting and DMA mapping) jglisse
2019-01-29 16:54 ` [PATCH 09/10] mm/hmm: allow to mirror vma of a file on a DAX backed filesystem jglisse
2019-01-29 18:41 ` Dan Williams [this message]
2019-01-29 19:31 ` Jerome Glisse
2019-01-29 20:51 ` Dan Williams
2019-01-29 21:21 ` Jerome Glisse
2019-01-30 2:32 ` Dan Williams
2019-01-30 3:03 ` Jerome Glisse
2019-01-30 17:25 ` Dan Williams
2019-01-30 18:36 ` Jerome Glisse
2019-01-31 3:28 ` Dan Williams
2019-01-31 4:16 ` Jerome Glisse
2019-01-31 5:44 ` Dan Williams
2019-03-05 22:16 ` Andrew Morton
2019-03-06 4:20 ` Dan Williams
2019-03-06 15:51 ` Jerome Glisse
2019-03-06 15:57 ` Dan Williams
2019-03-06 16:03 ` Jerome Glisse
2019-03-06 16:06 ` Dan Williams
2019-03-07 17:46 ` Andrew Morton
2019-03-07 18:56 ` Jerome Glisse
2019-03-12 3:13 ` Dan Williams
2019-03-12 15:25 ` Jerome Glisse
2019-03-12 16:06 ` Dan Williams
2019-03-12 19:06 ` Jerome Glisse
2019-03-12 19:30 ` Dan Williams
2019-03-12 20:34 ` Dave Chinner
2019-03-13 1:06 ` Dan Williams
2019-03-12 21:52 ` Andrew Morton
2019-03-13 0:10 ` Jerome Glisse
2019-03-13 0:46 ` Dan Williams
2019-03-13 1:00 ` Jerome Glisse
2019-03-13 16:06 ` Andrew Morton
2019-03-13 18:39 ` Jerome Glisse
2019-03-06 15:49 ` Jerome Glisse
2019-03-06 22:18 ` Andrew Morton
2019-03-07 0:36 ` Jerome Glisse
2019-01-29 16:54 ` [PATCH 10/10] mm/hmm: add helpers for driver to safely take the mmap_sem jglisse
2019-02-20 21:59 ` John Hubbard
2019-02-20 22:19 ` Jerome Glisse
2019-02-20 22:40 ` John Hubbard
2019-02-20 23:09 ` Jerome Glisse
2019-02-20 23:17 ` [PATCH 00/10] HMM updates for 5.1 John Hubbard
2019-02-20 23:36 ` Jerome Glisse
2019-02-22 23:31 ` Ralph Campbell
2019-03-13 1:27 ` Jerome Glisse
2019-03-13 16:10 ` Andrew Morton
2019-03-13 18:01 ` Jason Gunthorpe
2019-03-13 18:33 ` Jerome Glisse
2019-03-18 17:00 ` Kuehling, Felix
2019-03-18 17:04 ` Jerome Glisse
2019-03-18 18:30 ` Dan Williams
2019-03-18 18:54 ` Jerome Glisse
2019-03-18 19:18 ` Dan Williams
2019-03-18 19:28 ` Jerome Glisse
2019-03-18 19:36 ` Dan Williams
2019-03-19 16:40 ` Andrew Morton
2019-03-19 16:58 ` Jerome Glisse
2019-03-19 17:12 ` Andrew Morton
2019-03-19 17:18 ` Jerome Glisse
2019-03-19 17:33 ` Dan Williams
2019-03-19 17:45 ` Jerome Glisse
2019-03-19 18:42 ` Dan Williams
2019-03-19 19:05 ` Jerome Glisse
2019-03-19 19:13 ` Dan Williams
2019-03-19 14:18 ` Ira Weiny
2019-03-19 22:24 ` Jerome Glisse
2019-03-19 19:18 ` Jerome Glisse
2019-03-19 20:25 ` Jerome Glisse
2019-03-19 21:51 ` Stephen Rothwell
2019-03-19 18:51 ` Deucher, Alexander
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAPcyv4gNtDQf0mHwhZ8g3nX6ShsjA1tx2KLU_ZzTH1Z1AeA_CA@mail.gmail.com \
--to=dan.j.williams@intel.com \
--cc=akpm@linux-foundation.org \
--cc=jglisse@redhat.com \
--cc=jhubbard@nvidia.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=rcampbell@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox