On Sun, Nov 03, 2019 at 01:17:56PM -0800, John Hubbard wrote:

A subsequent patch requires access to gup flags, so pass the flags argument through to the __gup_device_* functions.

Also placate checkpatch.pl by shortening a nearby line.

Reviewed-by: Ira Weiny ira.weiny@intel.com Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com

Reviewed-by: Jérôme Glisse jglisse@redhat.com

---

mm/gup.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index 8f236a335ae9..85caf76b3012 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1890,7 +1890,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) static int __gup_device_huge(unsigned long pfn, unsigned long addr,

• unsigned long end, struct page **pages, int *nr)
  

• 	     unsigned long end, unsigned int flags,
  

• 	     struct page **pages, int *nr)
  

{ int nr_start = *nr; struct dev_pagemap *pgmap = NULL; @@ -1916,13 +1917,14 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, } static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,

• unsigned long end, struct page **pages, int *nr)
  

• 		 unsigned long end, unsigned int flags,
  

• 		 struct page **pages, int *nr)
  

{ unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);

• if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))

• if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) return 0;

if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { @@ -1933,13 +1935,14 @@ static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, } static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,

• unsigned long end, struct page **pages, int *nr)
  

• 		 unsigned long end, unsigned int flags,
  

• 		 struct page **pages, int *nr)
  

{ unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);

• if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))

• if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) return 0;

if (unlikely(pud_val(orig) != pud_val(*pudp))) { @@ -1950,14 +1953,16 @@ static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, } #else static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,

• unsigned long end, struct page **pages, int *nr)
  

• 		 unsigned long end, unsigned int flags,
  

• 		 struct page **pages, int *nr)
  

{ BUILD_BUG(); return 0; } static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,

• unsigned long end, struct page **pages, int *nr)
  

• 		 unsigned long end, unsigned int flags,
  

• 		 struct page **pages, int *nr)
  

{ BUILD_BUG(); return 0; @@ -2062,7 +2067,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0;

• return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
  

• return __gup_device_huge_pmd(orig, pmdp, addr, end, flags,
  

• 			     pages, nr);
  

  }

refs = 0; @@ -2092,7 +2098,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, } static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,

• unsigned long end, unsigned int flags, struct page **pages, int *nr)
  

• 	unsigned long end, unsigned int flags,
  

• 	struct page **pages, int *nr)
  

{ struct page *head, *page; int refs; @@ -2103,7 +2110,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, if (pud_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0;

• return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
  

• return __gup_device_huge_pud(orig, pudp, addr, end, flags,
  

• 			     pages, nr);
  

  }

refs = 0; -- 2.23.0

On Sun, Nov 03, 2019 at 01:17:57PM -0800, John Hubbard wrote:

There are four locations in gup.c that have a fair amount of code duplication. This means that changing one requires making the same changes in four places, not to mention reading the same code four times, and wondering if there are subtle differences.

Factor out the common code into static functions, thus reducing the overall line count and the code's complexity.

Also, take the opportunity to slightly improve the efficiency of the error cases, by doing a mass subtraction of the refcount, surrounded by get_page()/put_page().

Also, further simplify (slightly), by waiting until the the successful end of each routine, to increment *nr.

Cc: Ira Weiny ira.weiny@intel.com Cc: Christoph Hellwig hch@lst.de Cc: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com Signed-off-by: John Hubbard jhubbard@nvidia.com

Good cleanup.

Reviewed-by: Jérôme Glisse jglisse@redhat.com

---

mm/gup.c | 104 ++++++++++++++++++++++++------------------------------- 1 file changed, 45 insertions(+), 59 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index 85caf76b3012..199da99e8ffc 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1969,6 +1969,34 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr, } #endif +static int __record_subpages(struct page *page, unsigned long addr,

• 	     unsigned long end, struct page **pages, int nr)
  

+{

• int nr_recorded_pages = 0;
• do {

• pages[nr] = page;
  

• nr++;
  

• page++;
  

• nr_recorded_pages++;
  

• } while (addr += PAGE_SIZE, addr != end);
• return nr_recorded_pages;

+}

+static void put_compound_head(struct page *page, int refs) +{

• /* Do a get_page() first, in case refs == page->_refcount */
• get_page(page);
• page_ref_sub(page, refs);
• put_page(page);

+}

+static void __huge_pt_done(struct page *head, int nr_recorded_pages, int *nr) +{

• *nr += nr_recorded_pages;
• SetPageReferenced(head);

+}

#ifdef CONFIG_ARCH_HAS_HUGEPD static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, unsigned long sz) @@ -1998,33 +2026,20 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, /* hugepages are never "special" */ VM_BUG_ON(!pfn_valid(pte_pfn(pte)));

• refs = 0; head = pte_page(pte);
• page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
• do {

• VM_BUG_ON(compound_head(page) != head);
  

• pages[*nr] = page;
  

• (*nr)++;
  

• page++;
  

• refs++;
  

• } while (addr += PAGE_SIZE, addr != end);

• refs = __record_subpages(page, addr, end, pages, *nr);

head = try_get_compound_head(head, refs);

• if (!head) {

• *nr -= refs;
  

• if (!head) return 0;

• }

if (unlikely(pte_val(pte) != pte_val(*ptep))) {

• /* Could be optimized better */
  

• *nr -= refs;
  

• while (refs--)
  

• 	put_page(head);
  

• put_compound_head(head, refs);
  

  return 0; }

• SetPageReferenced(head);

• __huge_pt_done(head, refs, nr); return 1;

} @@ -2071,29 +2086,19 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, pages, nr); }

• refs = 0; page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
• do {

• pages[*nr] = page;
  

• (*nr)++;
  

• page++;
  

• refs++;
  

• } while (addr += PAGE_SIZE, addr != end);

• refs = __record_subpages(page, addr, end, pages, *nr);

head = try_get_compound_head(pmd_page(orig), refs);

• if (!head) {

• *nr -= refs;
  

• if (!head) return 0;

• }

if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {

• *nr -= refs;
  

• while (refs--)
  

• 	put_page(head);
  

• put_compound_head(head, refs);
  

  return 0; }

• SetPageReferenced(head);

• __huge_pt_done(head, refs, nr); return 1;

} @@ -2114,29 +2119,19 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, pages, nr); }

• refs = 0; page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
• do {

• pages[*nr] = page;
  

• (*nr)++;
  

• page++;
  

• refs++;
  

• } while (addr += PAGE_SIZE, addr != end);

• refs = __record_subpages(page, addr, end, pages, *nr);

head = try_get_compound_head(pud_page(orig), refs);

• if (!head) {

• *nr -= refs;
  

• if (!head) return 0;

• }

if (unlikely(pud_val(orig) != pud_val(*pudp))) {

• *nr -= refs;
  

• while (refs--)
  

• 	put_page(head);
  

• put_compound_head(head, refs);
  

  return 0; }

• SetPageReferenced(head);

• __huge_pt_done(head, refs, nr); return 1;

} @@ -2151,29 +2146,20 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0; BUILD_BUG_ON(pgd_devmap(orig));

• refs = 0;

• page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);

• do {

• pages[*nr] = page;
  

• (*nr)++;
  

• page++;
  

• refs++;
  

• } while (addr += PAGE_SIZE, addr != end);

• refs = __record_subpages(page, addr, end, pages, *nr);

head = try_get_compound_head(pgd_page(orig), refs);

• if (!head) {

• *nr -= refs;
  

• if (!head) return 0;

• }

if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {

• *nr -= refs;
  

• while (refs--)
  

• 	put_page(head);
  

• put_compound_head(head, refs);
  

  return 0; }

• SetPageReferenced(head);

• __huge_pt_done(head, refs, nr); return 1;

} -- 2.23.0

On Sun, Nov 03, 2019 at 01:17:58PM -0800, John Hubbard wrote:

1. Avoid naming conflicts: rename local static function from

"pin_user_pages()" to "pin_goldfish_pages()".

An upcoming patch will introduce a global pin_user_pages() function.

Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com

Reviewed-by: Jérôme Glisse jglisse@redhat.com

---

drivers/platform/goldfish/goldfish_pipe.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c index cef0133aa47a..7ed2a21a0bac 100644 --- a/drivers/platform/goldfish/goldfish_pipe.c +++ b/drivers/platform/goldfish/goldfish_pipe.c @@ -257,12 +257,12 @@ static int goldfish_pipe_error_convert(int status) } } -static int pin_user_pages(unsigned long first_page,

• 	  unsigned long last_page,
  

• 	  unsigned int last_page_size,
  

• 	  int is_write,
  

• 	  struct page *pages[MAX_BUFFERS_PER_COMMAND],
  

• 	  unsigned int *iter_last_page_size)
  

+static int pin_goldfish_pages(unsigned long first_page,

• 	      unsigned long last_page,
  

• 	      unsigned int last_page_size,
  

• 	      int is_write,
  

• 	      struct page *pages[MAX_BUFFERS_PER_COMMAND],
  

• 	      unsigned int *iter_last_page_size)
  

{ int ret; int requested_pages = ((last_page - first_page) >> PAGE_SHIFT) + 1; @@ -354,9 +354,9 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe, if (mutex_lock_interruptible(&pipe->lock)) return -ERESTARTSYS;

• pages_count = pin_user_pages(first_page, last_page,

• 		     last_page_size, is_write,
  

• 		     pipe->pages, &iter_last_page_size);
  

• pages_count = pin_goldfish_pages(first_page, last_page,

• 			 last_page_size, is_write,
  

• 			 pipe->pages, &iter_last_page_size);
  

  if (pages_count < 0) { mutex_unlock(&pipe->lock); return pages_count;

-- 2.23.0

On 11/3/19 10:17 PM, John Hubbard wrote:

After DMA is complete, and the device and CPU caches are synchronized, it's still required to mark the CPU pages as dirty, if the data was coming from the device. However, this driver was just issuing a bare put_page() call, without any set_page_dirty*() call.

Fix the problem, by calling set_page_dirty_lock() if the CPU pages were potentially receiving data from the device.

Cc: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: John Hubbard jhubbard@nvidia.com

Acked-by: Hans Verkuil hverkuil-cisco@xs4all.nl

Looks good, thanks!

Hans

---

drivers/media/v4l2-core/videobuf-dma-sg.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c index 66a6c6c236a7..28262190c3ab 100644 --- a/drivers/media/v4l2-core/videobuf-dma-sg.c +++ b/drivers/media/v4l2-core/videobuf-dma-sg.c @@ -349,8 +349,11 @@ int videobuf_dma_free(struct videobuf_dmabuf *dma) BUG_ON(dma->sglen); if (dma->pages) {

• for (i = 0; i < dma->nr_pages; i++)
  

• for (i = 0; i < dma->nr_pages; i++) {
  

• 	if (dma->direction == DMA_FROM_DEVICE)
  

• 		set_page_dirty_lock(dma->pages[i]);
  put_page(dma->pages[i]);
  

• }
  

  kfree(dma->pages); dma->pages = NULL; }

On 11/4/19 9:33 AM, Jerome Glisse wrote: ...

Few nitpick belows, nonetheless:

Reviewed-by: Jérôme Glisse jglisse@redhat.com [...]

...

+CASE 3: ODP +----------- +(Mellanox/Infiniband On Demand Paging: the hardware supports +replayable page faulting). There are GUP references to pages serving as DMA +buffers. For ODP, MMU notifiers are used to synchronize with page_mkclean() +and munmap(). Therefore, normal GUP calls are sufficient, so neither flag +needs to be set.

I would not include ODP or anything like it here, they do not use GUP anymore and i believe it is more confusing here. I would how- ever include some text in this documentation explaining that hard- ware that support page fault is superior as it does not incur any of the issues described here.

OK, agreed, here's a new write up that I'll put in v3:

CASE 3: ODP ----------- Advanced, but non-CPU (DMA) hardware that supports replayable page faults. Here, a well-written driver doesn't normally need to pin pages at all. However, if the driver does choose to do so, it can register MMU notifiers for the range, and will be called back upon invalidation. Either way (avoiding page pinning, or using MMU notifiers to unpin upon request), there is proper synchronization with both filesystem and mm (page_mkclean(), munmap(), etc).

Therefore, neither flag needs to be set.

It's worth mentioning here that pinning pages should not be the first design choice. If page fault capable hardware is available, then the software should be written so that it does not pin pages. This allows mm and filesystems to operate more efficiently and reliably.

[...]

...

diff --git a/mm/gup.c b/mm/gup.c index 199da99e8ffc..1aea48427879 100644 --- a/mm/gup.c +++ b/mm/gup.c

[...]

...

@@ -1014,7 +1018,16 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, BUG_ON(*locked != 1); }

• if (pages)

• /*

• * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
  

• * is to set FOLL_GET if the caller wants pages[] filled in (but has
  

• * carelessly failed to specify FOLL_GET), so keep doing that, but only
  

• * for FOLL_GET, not for the newer FOLL_PIN.
  

• *
  

• * FOLL_PIN always expects pages to be non-null, but no need to assert
  

• * that here, as any failures will be obvious enough.
  

• */
  

• if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET;

Did you look at user that have pages and not FOLL_GET set ? I believe it would be better to first fix them to end up with FOLL_GET set and then error out if pages is != NULL but nor FOLL_GET or FOLL_PIN is set.

I was perhaps overly cautious, and didn't go there. However, it's probably doable, given that there was already the following in __get_user_pages():

VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));

...which will have conditioned people and code to set FOLL_GET together with pages. So I agree that the time is right.

In order to make bisecting future failures simpler, I can insert a patch right before this one, that changes the FOLL_GET setting into an assert, like this:

diff --git a/mm/gup.c b/mm/gup.c index 8f236a335ae9..be338961e80d 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1014,8 +1014,8 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, BUG_ON(*locked != 1); }

- if (pages) - flags |= FOLL_GET; + if (pages && WARN_ON_ONCE(!(gup_flags & FOLL_GET))) + return -EINVAL;

pages_done = 0; lock_dropped = false;

...and then add in FOLL_PIN, with this patch.

...

pages_done = 0;

...

@@ -2373,24 +2402,9 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages, return ret; } -/**

• • get_user_pages_fast() - pin user pages in memory
• • @start: starting user address
• • @nr_pages: number of pages from start to pin
• • @gup_flags: flags modifying pin behaviour
• • @pages: array that receives pointers to the pages pinned.

• • Should be at least nr_pages long.
    

• • Attempt to pin user pages in memory without taking mm->mmap_sem.
• • If not successful, it will fall back to taking the lock and
• • calling get_user_pages().
• • Returns number of pages pinned. This may be fewer than the number
• • requested. If nr_pages is 0 or negative, returns 0. If no pages
• • were pinned, returns -errno.
• */

-int get_user_pages_fast(unsigned long start, int nr_pages,

• 	unsigned int gup_flags, struct page **pages)
  

+static int internal_get_user_pages_fast(unsigned long start, int nr_pages,

• 			unsigned int gup_flags,
  

• 			struct page **pages)
  

Usualy function are rename to _old_func_name ie add _ in front. So here it would become _get_user_pages_fast but i know some people don't like that as sometimes we endup with ___function_overloaded :)

Exactly: the __get_user_pages* names were already used for *non*-internal routines, so I attempted to pick the next best naming prefix.

...

{ unsigned long addr, len, end; int nr = 0, ret = 0;

...

@@ -2435,4 +2449,215 @@ int get_user_pages_fast(unsigned long start, int nr_pages,

[...]

...

+/**

• • pin_user_pages_remote() - pin pages for (typically) use by Direct IO, and
• • return the pages to the user.

Not a fan of (typically) maybe: pin_user_pages_remote() - pin pages of a remote process (task != current)

I think here the remote part if more important that DIO. Remote is use by other thing that DIO.

Yes, good point. I'll use your wording:

* pin_user_pages_remote() - pin pages of a remote process (task != current)

...

• • Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See
• • get_user_pages_remote() for documentation on the function arguments, because
• • the arguments here are identical.
• • FOLL_PIN means that the pages must be released via put_user_page(). Please
• • see Documentation/vm/pin_user_pages.rst for details.
• • This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
• • is NOT intended for Case 2 (RDMA: long-term pins).
• */

+long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,

• 	   unsigned long start, unsigned long nr_pages,
  

• 	   unsigned int gup_flags, struct page **pages,
  

• 	   struct vm_area_struct **vmas, int *locked)
  

+{

• /* FOLL_GET and FOLL_PIN are mutually exclusive. */
• if (WARN_ON_ONCE(gup_flags & FOLL_GET))

• return -EINVAL;
  

• gup_flags |= FOLL_TOUCH | FOLL_REMOTE | FOLL_PIN;
• return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,

• 		       locked, gup_flags);
  

+} +EXPORT_SYMBOL(pin_user_pages_remote);

+/**

• • pin_longterm_pages_remote() - pin pages for (typically) use by Direct IO, and
• • return the pages to the user.

I think you copy pasted this from pin_user_pages_remote() :)

I admit to nothing, with respect to copy-paste! :)

This one can simply be:

* pin_longterm_pages_remote() - pin pages of a remote process (task != current)

...

• • Nearly the same as get_user_pages_remote(), but note that FOLL_TOUCH is not
• • set, and FOLL_PIN and FOLL_LONGTERM are set. See get_user_pages_remote() for
• • documentation on the function arguments, because the arguments here are
• • identical.
• • FOLL_PIN means that the pages must be released via put_user_page(). Please
• • see Documentation/vm/pin_user_pages.rst for further details.
• • FOLL_LONGTERM means that the pages are being pinned for "long term" use,
• • typically by a non-CPU device, and we cannot be sure that waiting for a
• • pinned page to become unpin will be effective.
• • This is intended for Case 2 (RDMA: long-term pins) in
• • Documentation/vm/pin_user_pages.rst.
• */

+long pin_longterm_pages_remote(struct task_struct *tsk, struct mm_struct *mm,

• 	       unsigned long start, unsigned long nr_pages,
  

• 	       unsigned int gup_flags, struct page **pages,
  

• 	       struct vm_area_struct **vmas, int *locked)
  

+{

• /* FOLL_GET and FOLL_PIN are mutually exclusive. */
• if (WARN_ON_ONCE(gup_flags & FOLL_GET))

• return -EINVAL;
  

• /*

• * FIXME: as noted in the get_user_pages_remote() implementation, it
  

• * is not yet possible to safely set FOLL_LONGTERM here. FOLL_LONGTERM
  

• * needs to be set, but for now the best we can do is a "TODO" item.
  

• */
  

• gup_flags |= FOLL_REMOTE | FOLL_PIN;

Wouldn't it be better to not add pin_longterm_pages_remote() until it can be properly implemented ?

Well, the problem is that I need each call site that requires FOLL_PIN to use a proper wrapper. It's the FOLL_PIN that is the focus here, because there is a hard, bright rule, which is: if and only if a caller sets FOLL_PIN, then the dma-page tracking happens, and put_user_page() must be called.

So this leaves me with only two reasonable choices:

a) Convert the call site as above: pin_longterm_pages_remote(), which sets FOLL_PIN (the key point!), and leaves the FOLL_LONGTERM situation exactly as it has been so far. When the FOLL_LONGTERM situation is fixed, the call site *might* not need any changes to adopt the working gup.c code.

b) Convert the call site to pin_user_pages_remote(), which also sets FOLL_PIN, and also leaves the FOLL_LONGTERM situation exactly as before. There would also be a comment at the call site, to the effect of, "this is the wrong call to make: it really requires FOLL_LONGTERM behavior".

When the FOLL_LONGTERM situation is fixed, the call site will need to be changed to pin_longterm_pages_remote().

So you can probably see why I picked (a).

thanks,

John Hubbard NVIDIA

On 11/4/19 11:18 AM, Jerome Glisse wrote:

On Mon, Nov 04, 2019 at 11:04:38AM -0800, John Hubbard wrote:

...

On 11/4/19 9:33 AM, Jerome Glisse wrote: ...

...

Few nitpick belows, nonetheless:

Reviewed-by: Jérôme Glisse jglisse@redhat.com [...]

...

+CASE 3: ODP +----------- +(Mellanox/Infiniband On Demand Paging: the hardware supports +replayable page faulting). There are GUP references to pages serving as DMA +buffers. For ODP, MMU notifiers are used to synchronize with page_mkclean() +and munmap(). Therefore, normal GUP calls are sufficient, so neither flag +needs to be set.

I would not include ODP or anything like it here, they do not use GUP anymore and i believe it is more confusing here. I would how- ever include some text in this documentation explaining that hard- ware that support page fault is superior as it does not incur any of the issues described here.

OK, agreed, here's a new write up that I'll put in v3:

CASE 3: ODP

ODP is RDMA, maybe Hardware with page fault support instead

...

Advanced, but non-CPU (DMA) hardware that supports replayable page faults.

OK, so:

"RDMA hardware with page faulting support."

for the first sentence.

...

Here, a well-written driver doesn't normally need to pin pages at all. However, if the driver does choose to do so, it can register MMU notifiers for the range, and will be called back upon invalidation. Either way (avoiding page pinning, or using MMU notifiers to unpin upon request), there is proper synchronization with both filesystem and mm (page_mkclean(), munmap(), etc).

Therefore, neither flag needs to be set.

In fact GUP should never be use with those.

Yes. The next paragraph says that, but maybe not strong enough.

...

It's worth mentioning here that pinning pages should not be the first design choice. If page fault capable hardware is available, then the software should be written so that it does not pin pages. This allows mm and filesystems to operate more efficiently and reliably.

Here's what we have after the above changes:

CASE 3: ODP ----------- RDMA hardware with page faulting support. Here, a well-written driver doesn't normally need to pin pages at all. However, if the driver does choose to do so, it can register MMU notifiers for the range, and will be called back upon invalidation. Either way (avoiding page pinning, or using MMU notifiers to unpin upon request), there is proper synchronization with both filesystem and mm (page_mkclean(), munmap(), etc).

Therefore, neither flag needs to be set.

In this case, ideally, neither get_user_pages() nor pin_user_pages() should be called. Instead, the software should be written so that it does not pin pages. This allows mm and filesystems to operate more efficiently and reliably.

...

...

[...]

...

@@ -1014,7 +1018,16 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, BUG_ON(*locked != 1); }

• if (pages)

• /*

• * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
  

• * is to set FOLL_GET if the caller wants pages[] filled in (but has
  

• * carelessly failed to specify FOLL_GET), so keep doing that, but only
  

• * for FOLL_GET, not for the newer FOLL_PIN.
  

• *
  

• * FOLL_PIN always expects pages to be non-null, but no need to assert
  

• * that here, as any failures will be obvious enough.
  

• */
  

• if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET;

Did you look at user that have pages and not FOLL_GET set ? I believe it would be better to first fix them to end up with FOLL_GET set and then error out if pages is != NULL but nor FOLL_GET or FOLL_PIN is set.

I was perhaps overly cautious, and didn't go there. However, it's probably doable, given that there was already the following in __get_user_pages():

VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));

...which will have conditioned people and code to set FOLL_GET together with pages. So I agree that the time is right.

In order to make bisecting future failures simpler, I can insert a patch right before this one, that changes the FOLL_GET setting into an assert, like this:

diff --git a/mm/gup.c b/mm/gup.c index 8f236a335ae9..be338961e80d 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1014,8 +1014,8 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, BUG_ON(*locked != 1); }

•   if (pages)
  

•           flags |= FOLL_GET;
  

•   if (pages && WARN_ON_ONCE(!(gup_flags & FOLL_GET)))
  

•           return -EINVAL;
  

pages_done = 0; lock_dropped = false;

...and then add in FOLL_PIN, with this patch.

looks good but double check that it should not happens, i will try to check on my side too.

Yes, I'll look.

...

...

...

...

• */
  

• gup_flags |= FOLL_REMOTE | FOLL_PIN;

Wouldn't it be better to not add pin_longterm_pages_remote() until it can be properly implemented ?

Well, the problem is that I need each call site that requires FOLL_PIN to use a proper wrapper. It's the FOLL_PIN that is the focus here, because there is a hard, bright rule, which is: if and only if a caller sets FOLL_PIN, then the dma-page tracking happens, and put_user_page() must be called.

So this leaves me with only two reasonable choices:

a) Convert the call site as above: pin_longterm_pages_remote(), which sets FOLL_PIN (the key point!), and leaves the FOLL_LONGTERM situation exactly as it has been so far. When the FOLL_LONGTERM situation is fixed, the call site *might* not need any changes to adopt the working gup.c code.

b) Convert the call site to pin_user_pages_remote(), which also sets FOLL_PIN, and also leaves the FOLL_LONGTERM situation exactly as before. There would also be a comment at the call site, to the effect of, "this is the wrong call to make: it really requires FOLL_LONGTERM behavior".

When the FOLL_LONGTERM situation is fixed, the call site will need to be changed to pin_longterm_pages_remote().

So you can probably see why I picked (a).

But right now nobody has FOLL_LONGTERM and FOLL_REMOTE. So you should never have the need for pin_longterm_pages_remote(). My fear is that longterm has implication and it would be better to not drop this implication by adding a wrapper that does not do what the name says.

So do not introduce pin_longterm_pages_remote() until its first user happens. This is option c)

Almost forgot, though: there is already another user: Infiniband:

drivers/infiniband/core/umem_odp.c:646: npages = pin_longterm_pages_remote(owning_process, owning_mm,

thanks,

John Hubbard NVIDIA

On Sun, Nov 03, 2019 at 01:18:00PM -0800, John Hubbard wrote:

Introduce pin_user_pages*() variations of get_user_pages*() calls, and also pin_longterm_pages*() variations.

These variants all set FOLL_PIN, which is also introduced, and thoroughly documented.

The pin_longterm*() variants also set FOLL_LONGTERM, in addition to FOLL_PIN:

pin_user_pages()
pin_user_pages_remote()
pin_user_pages_fast()

pin_longterm_pages()
pin_longterm_pages_remote()
pin_longterm_pages_fast()

All pages that are pinned via the above calls, must be unpinned via put_user_page().

The underlying rules are:

• These are gup-internal flags, so the call sites should not directly

set FOLL_PIN nor FOLL_LONGTERM. That behavior is enforced with assertions, for the new FOLL_PIN flag. However, for the pre-existing FOLL_LONGTERM flag, which has some call sites that still directly set FOLL_LONGTERM, there is no assertion yet.

• Call sites that want to indicate that they are going to do DirectIO ("DIO") or something with similar characteristics, should call a get_user_pages()-like wrapper call that sets FOLL_PIN. These wrappers will: * Start with "pin_user_pages" instead of "get_user_pages". That makes it easy to find and audit the call sites. * Set FOLL_PIN

• For pages that are received via FOLL_PIN, those pages must be returned via put_user_page().

Thanks to Jan Kara and Vlastimil Babka for explaining the 4 cases in this documentation. (I've reworded it and expanded on it slightly.)

Cc: Jonathan Corbet corbet@lwn.net Cc: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com

---

Documentation/vm/index.rst | 1 + Documentation/vm/pin_user_pages.rst | 212 ++++++++++++++++++++++

I think it belongs to Documentation/core-api.

include/linux/mm.h | 62 ++++++- mm/gup.c | 265 +++++++++++++++++++++++++--- 4 files changed, 514 insertions(+), 26 deletions(-) create mode 100644 Documentation/vm/pin_user_pages.rst

diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst index e8d943b21cf9..7194efa3554a 100644 --- a/Documentation/vm/index.rst +++ b/Documentation/vm/index.rst @@ -44,6 +44,7 @@ descriptions of data structures and algorithms. page_migration page_frags page_owner

• pin_user_pages remap_file_pages slub split_page_table_lock

diff --git a/Documentation/vm/pin_user_pages.rst b/Documentation/vm/pin_user_pages.rst new file mode 100644 index 000000000000..3910f49ca98c --- /dev/null +++ b/Documentation/vm/pin_user_pages.rst @@ -0,0 +1,212 @@ +.. SPDX-License-Identifier: GPL-2.0

+==================================================== +pin_user_pages() and related calls +====================================================

I know this is too much to ask, but having pin_user_pages() a part of more general GUP description would be really great :)

+.. contents:: :local:

+Overview +========

+This document describes the following functions: ::

• pin_user_pages
• pin_user_pages_fast
• pin_user_pages_remote
• pin_longterm_pages
• pin_longterm_pages_fast
• pin_longterm_pages_remote

+Basic description of FOLL_PIN +=============================

+A new flag for get_user_pages ("gup") has been added: FOLL_PIN. FOLL_PIN has

Consider reading this after, say, half a year ;-)

+significant interactions and interdependencies with FOLL_LONGTERM, so both are +covered here.

+Both FOLL_PIN and FOLL_LONGTERM are "internal" to gup, meaning that neither +FOLL_PIN nor FOLL_LONGTERM should not appear at the gup call sites. This allows +the associated wrapper functions (pin_user_pages and others) to set the correct +combination of these flags, and to check for problems as well.

+FOLL_PIN and FOLL_GET are mutually exclusive for a given gup call. However, +multiple threads and call sites are free to pin the same struct pages, via both +FOLL_PIN and FOLL_GET. It's just the call site that needs to choose one or the +other, not the struct page(s).

+The FOLL_PIN implementation is nearly the same as FOLL_GET, except that FOLL_PIN +uses a different reference counting technique.

+FOLL_PIN is a prerequisite to FOLL_LONGTGERM. Another way of saying that is, +FOLL_LONGTERM is a specific case, more restrictive case of FOLL_PIN.

+Which flags are set by each wrapper +===================================

+Only FOLL_PIN and FOLL_LONGTERM are covered here. These flags are added to +whatever flags the caller provides::

• Function gup flags (FOLL_PIN or FOLL_LONGTERM only)

• ---

• pin_user_pages FOLL_PIN
• pin_user_pages_fast FOLL_PIN
• pin_user_pages_remote FOLL_PIN
• pin_longterm_pages FOLL_PIN | FOLL_LONGTERM
• pin_longterm_pages_fast FOLL_PIN | FOLL_LONGTERM
• pin_longterm_pages_remote FOLL_PIN | FOLL_LONGTERM

+Tracking dma-pinned pages +=========================

+Some of the key design constraints, and solutions, for tracking dma-pinned +pages:

+* An actual reference count, per struct page, is required. This is because

• multiple processes may pin and unpin a page.

+* False positives (reporting that a page is dma-pinned, when in fact it is not)

• are acceptable, but false negatives are not.

+* struct page may not be increased in size for this, and all fields are already

• used.

+* Given the above, we can overload the page->_refcount field by using, sort of,

• the upper bits in that field for a dma-pinned count. "Sort of", means that,
• rather than dividing page->_refcount into bit fields, we simple add a medium-
• large value (GUP_PIN_COUNTING_BIAS, initially chosen to be 1024: 10 bits) to
• page->_refcount. This provides fuzzy behavior: if a page has get_page() called
• on it 1024 times, then it will appear to have a single dma-pinned count.
• And again, that's acceptable.

+This also leads to limitations: there are only 31-10==21 bits available for a +counter that increments 10 bits at a time.

+TODO: for 1GB and larger huge pages, this is cutting it close. That's because +when pin_user_pages() follows such pages, it increments the head page by "1" +(where "1" used to mean "+1" for get_user_pages(), but now means "+1024" for +pin_user_pages()) for each tail page. So if you have a 1GB huge page:

+* There are 256K (18 bits) worth of 4 KB tail pages. +* There are 21 bits available to count up via GUP_PIN_COUNTING_BIAS (that is,

• 10 bits at a time)

+* There are 21 - 18 == 3 bits available to count. Except that there aren't,

• because you need to allow for a few normal get_page() calls on the head page,
• as well. Fortunately, the approach of using addition, rather than "hard"
• bitfields, within page->_refcount, allows for sharing these bits gracefully.
• But we're still looking at about 8 references.

+This, however, is a missing feature more than anything else, because it's easily +solved by addressing an obvious inefficiency in the original get_user_pages() +approach of retrieving pages: stop treating all the pages as if they were +PAGE_SIZE. Retrieve huge pages as huge pages. The callers need to be aware of +this, so some work is required. Once that's in place, this limitation mostly +disappears from view, because there will be ample refcounting range available.

+* Callers must specifically request "dma-pinned tracking of pages". In other

• words, just calling get_user_pages() will not suffice; a new set of functions,
• pin_user_page() and related, must be used.

+FOLL_PIN, FOLL_GET, FOLL_LONGTERM: when to use which flags +==========================================================

+Thanks to Jan Kara, Vlastimil Babka and several other -mm people, for describing +these categories:

+CASE 1: Direct IO (DIO) +----------------------- +There are GUP references to pages that are serving +as DIO buffers. These buffers are needed for a relatively short time (so they +are not "long term"). No special synchronization with page_mkclean() or +munmap() is provided. Therefore, flags to set at the call site are: ::

• FOLL_PIN

+...but rather than setting FOLL_PIN directly, call sites should use one of +the pin_user_pages*() routines that set FOLL_PIN.

+CASE 2: RDMA +------------ +There are GUP references to pages that are serving as DMA +buffers. These buffers are needed for a long time ("long term"). No special +synchronization with page_mkclean() or munmap() is provided. Therefore, flags +to set at the call site are: ::

• FOLL_PIN | FOLL_LONGTERM

+NOTE: Some pages, such as DAX pages, cannot be pinned with longterm pins. That's +because DAX pages do not have a separate page cache, and so "pinning" implies +locking down file system blocks, which is not (yet) supported in that way.

+CASE 3: ODP +----------- +(Mellanox/Infiniband On Demand Paging: the hardware supports +replayable page faulting). There are GUP references to pages serving as DMA +buffers. For ODP, MMU notifiers are used to synchronize with page_mkclean() +and munmap(). Therefore, normal GUP calls are sufficient, so neither flag +needs to be set.

+CASE 4: Pinning for struct page manipulation only +------------------------------------------------- +Here, normal GUP calls are sufficient, so neither flag needs to be set.

+page_dma_pinned(): the whole point of pinning +=============================================

+The whole point of marking pages as "DMA-pinned" or "gup-pinned" is to be able +to query, "is this page DMA-pinned?" That allows code such as page_mkclean() +(and file system writeback code in general) to make informed decisions about +what to do when a page cannot be unmapped due to such pins.

+What to do in those cases is the subject of a years-long series of discussions +and debates (see the References at the end of this document). It's a TODO item +here: fill in the details once that's worked out. Meanwhile, it's safe to say +that having this available: ::

•    static inline bool page_dma_pinned(struct page *page)
  

+...is a prerequisite to solving the long-running gup+DMA problem.

+Another way of thinking about FOLL_GET, FOLL_PIN, and FOLL_LONGTERM +===================================================================

+Another way of thinking about these flags is as a progression of restrictions: +FOLL_GET is for struct page manipulation, without affecting the data that the +struct page refers to. FOLL_PIN is a *replacement* for FOLL_GET, and is for +short term pins on pages whose data *will* get accessed. As such, FOLL_PIN is +a "more severe" form of pinning. And finally, FOLL_LONGTERM is an even more +restrictive case that has FOLL_PIN as a prerequisite: this is for pages that +will be pinned longterm, and whose data will be accessed.

+Unit testing +============ +This file::

• tools/testing/selftests/vm/gup_benchmark.c

+has the following new calls to exercise the new pin*() wrapper functions:

+* PIN_FAST_BENCHMARK (./gup_benchmark -a) +* PIN_LONGTERM_BENCHMARK (./gup_benchmark -a) +* PIN_BENCHMARK (./gup_benchmark -a)

+You can monitor how many total dma-pinned pages have been acquired and released +since the system was booted, via two new /proc/vmstat entries: ::

• /proc/vmstat/nr_foll_pin_requested
• /proc/vmstat/nr_foll_pin_requested

+Those are both going to show zero, unless CONFIG_DEBUG_VM is set. This is +because there is a noticeable performance drop in put_user_page(), when they +are activated.

+References +==========

+* `Some slow progress on get_user_pages() (Apr 2, 2019) https://lwn.net/Articles/784574/`_ +* `DMA and get_user_pages() (LPC: Dec 12, 2018) https://lwn.net/Articles/774411/`_ +* `The trouble with get_user_pages() (Apr 30, 2018) https://lwn.net/Articles/753027/`_

+John Hubbard, October, 2019 diff --git a/include/linux/mm.h b/include/linux/mm.h index cc292273e6ba..cdfb6fedb271 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1526,9 +1526,23 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); +long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,

• 	   unsigned long start, unsigned long nr_pages,
  

• 	   unsigned int gup_flags, struct page **pages,
  

• 	   struct vm_area_struct **vmas, int *locked);
  

+long pin_longterm_pages_remote(struct task_struct *tsk, struct mm_struct *mm,

• 	       unsigned long start, unsigned long nr_pages,
  

• 	       unsigned int gup_flags, struct page **pages,
  

• 	       struct vm_area_struct **vmas, int *locked);
  

long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); +long pin_user_pages(unsigned long start, unsigned long nr_pages,

•     unsigned int gup_flags, struct page **pages,
  

•     struct vm_area_struct **vmas);
  

+long pin_longterm_pages(unsigned long start, unsigned long nr_pages,

• 	unsigned int gup_flags, struct page **pages,
  

• 	struct vm_area_struct **vmas);
  

long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, @@ -1536,6 +1550,10 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); +int pin_user_pages_fast(unsigned long start, int nr_pages,

• 	unsigned int gup_flags, struct page **pages);
  

+int pin_longterm_pages_fast(unsigned long start, int nr_pages,

• 	    unsigned int gup_flags, struct page **pages);
  

int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, @@ -2594,13 +2612,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ +#define FOLL_PIN 0x40000 /* pages must be released via put_user_page() */ /*

• • NOTE on FOLL_LONGTERM:

• • FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
• • other. Here is what they mean, and how to use them:
  • FOLL_LONGTERM indicates that the page will be held for an indefinite time

• • period _often_ under userspace control. This is contrasted with
• • iov_iter_get_pages() where usages which are transient.

• • period _often_ under userspace control. This is in contrast to
• • iov_iter_get_pages(), where usages which are transient.
  • FIXME: For pages which are part of a filesystem, mappings are subject to the
  • lifetime enforced by the filesystem and we need guarantees that longterm

@@ -2615,11 +2635,41 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,

• Currently only get_user_pages() and get_user_pages_fast() support this flag
• and calls to get_user_pages_[un]locked are specifically not allowed. This
• is due to an incompatibility with the FS DAX check and

• • FAULT_FLAG_ALLOW_RETRY

• • FAULT_FLAG_ALLOW_RETRY.

• • In the CMA case: longterm pins in a CMA region would unnecessarily fragment
• • that region. And so CMA attempts to migrate the page before pinning when

• • In the CMA case: long term pins in a CMA region would unnecessarily fragment
• • that region. And so, CMA attempts to migrate the page before pinning, when
  • FOLL_LONGTERM is specified.
• • FOLL_PIN indicates that a special kind of tracking (not just page->_refcount,
• • but an additional pin counting system) will be invoked. This is intended for
• • anything that gets a page reference and then touches page data (for example,
• • Direct IO). This lets the filesystem know that some non-file-system entity is
• • potentially changing the pages' data. In contrast to FOLL_GET (whose pages
• • are released via put_page()), FOLL_PIN pages must be released, ultimately, by
• • a call to put_user_page().
• • FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different
• • and separate refcounting mechanisms, however, and that means that each has
• • its own acquire and release mechanisms:

• • FOLL_GET: get_user_pages*() to acquire, and put_page() to release.
    

• • FOLL_PIN: pin_user_pages*() or pin_longterm_pages*() to acquire, and
    

• •           put_user_pages to release.
    

• • FOLL_PIN and FOLL_GET are mutually exclusive for a given function call.
• • (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based
• • calls applied to them, and that's perfectly OK. This is a constraint on the
• • callers, not on the pages.)
• • FOLL_PIN and FOLL_LONGTERM should be set internally by the pin_user_page*()
• • and pin_longterm_*() APIs, never directly by the caller. That's in order to
• • help avoid mismatches when releasing pages: get_user_pages*() pages must be
• • released via put_page(), while pin_user_pages*() pages must be released via
• • put_user_page().
• • Please see Documentation/vm/pin_user_pages.rst for more information.
  */

static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) diff --git a/mm/gup.c b/mm/gup.c index 199da99e8ffc..1aea48427879 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -179,6 +179,10 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, spinlock_t *ptl; pte_t *ptep, pte;

• /* FOLL_GET and FOLL_PIN are mutually exclusive. */
• if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==

• 	 (FOLL_PIN | FOLL_GET)))
  

• return ERR_PTR(-EINVAL);
  

retry: if (unlikely(pmd_bad(*pmd))) return no_page_table(vma, flags); @@ -790,7 +794,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, start = untagged_addr(start);

• VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));

• VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));

/* * If FOLL_FORCE is set then do not force a full fault as the hinting @@ -1014,7 +1018,16 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, BUG_ON(*locked != 1); }

• if (pages)

• /*

• * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
  

• * is to set FOLL_GET if the caller wants pages[] filled in (but has
  

• * carelessly failed to specify FOLL_GET), so keep doing that, but only
  

• * for FOLL_GET, not for the newer FOLL_PIN.
  

• *
  

• * FOLL_PIN always expects pages to be non-null, but no need to assert
  

• * that here, as any failures will be obvious enough.
  

• */
  

• if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET;

pages_done = 0; @@ -1151,6 +1164,14 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) {

• /*

• * FOLL_PIN must only be set internally by the pin_user_page*() and
  

• * pin_longterm_*() APIs, never directly by the caller, so enforce that
  

• * with an assertion:
  

• */
  

• if (WARN_ON_ONCE(gup_flags & FOLL_PIN))

• return -EINVAL;
  

• /*
  • FIXME: Current FOLL_LONGTERM behavior is incompatible with
  • FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on

@@ -1608,6 +1629,14 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas) {

• /*

• * FOLL_PIN must only be set internally by the pin_user_page*() and
  

• * pin_longterm_*() APIs, never directly by the caller, so enforce that
  

• * with an assertion:
  

• */
  

• if (WARN_ON_ONCE(gup_flags & FOLL_PIN))

• return -EINVAL;
  

• return __gup_longterm_locked(current, current->mm, start, nr_pages, pages, vmas, gup_flags | FOLL_TOUCH);

} @@ -2373,24 +2402,9 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages, return ret; } -/**

• • get_user_pages_fast() - pin user pages in memory
• • @start: starting user address
• • @nr_pages: number of pages from start to pin
• • @gup_flags: flags modifying pin behaviour
• • @pages: array that receives pointers to the pages pinned.

• • Should be at least nr_pages long.
    

• • Attempt to pin user pages in memory without taking mm->mmap_sem.
• • If not successful, it will fall back to taking the lock and
• • calling get_user_pages().
• • Returns number of pages pinned. This may be fewer than the number
• • requested. If nr_pages is 0 or negative, returns 0. If no pages
• • were pinned, returns -errno.
• */

-int get_user_pages_fast(unsigned long start, int nr_pages,

• 	unsigned int gup_flags, struct page **pages)
  

+static int internal_get_user_pages_fast(unsigned long start, int nr_pages,

• 			unsigned int gup_flags,
  

• 			struct page **pages)
  

{ unsigned long addr, len, end; int nr = 0, ret = 0; @@ -2435,4 +2449,215 @@ int get_user_pages_fast(unsigned long start, int nr_pages, return ret; }

+/**

• • get_user_pages_fast() - pin user pages in memory
• • @start: starting user address
• • @nr_pages: number of pages from start to pin
• • @gup_flags: flags modifying pin behaviour
• • @pages: array that receives pointers to the pages pinned.

• • Should be at least nr_pages long.
    

• • Attempt to pin user pages in memory without taking mm->mmap_sem.
• • If not successful, it will fall back to taking the lock and
• • calling get_user_pages().
• • Returns number of pages pinned. This may be fewer than the number requested.
• • If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns
• • -errno.
• */

+int get_user_pages_fast(unsigned long start, int nr_pages,

• 	unsigned int gup_flags, struct page **pages)
  

+{

• /*

• * FOLL_PIN must only be set internally by the pin_user_page*() and
  

• * pin_longterm_*() APIs, never directly by the caller, so enforce that:
  

• */
  

• if (WARN_ON_ONCE(gup_flags & FOLL_PIN))

• return -EINVAL;
  

• return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);

+} EXPORT_SYMBOL_GPL(get_user_pages_fast);

+/**

• • pin_user_pages_fast() - pin user pages in memory without taking locks
• • Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See
• • get_user_pages_fast() for documentation on the function arguments, because
• • the arguments here are identical.
• • FOLL_PIN means that the pages must be released via put_user_page(). Please
• • see Documentation/vm/pin_user_pages.rst for further details.
• • This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
• • is NOT intended for Case 2 (RDMA: long-term pins).
• */

+int pin_user_pages_fast(unsigned long start, int nr_pages,

• 	unsigned int gup_flags, struct page **pages)
  

+{

• /* FOLL_GET and FOLL_PIN are mutually exclusive. */
• if (WARN_ON_ONCE(gup_flags & FOLL_GET))

• return -EINVAL;
  

• gup_flags |= FOLL_PIN;
• return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);

+} +EXPORT_SYMBOL_GPL(pin_user_pages_fast);

+/**

• • pin_longterm_pages_fast() - pin user pages in memory without taking locks
• • Nearly the same as get_user_pages_fast(), except that FOLL_PIN and
• • FOLL_LONGTERM are set. See get_user_pages_fast() for documentation on the
• • function arguments, because the arguments here are identical.
• • FOLL_PIN means that the pages must be released via put_user_page(). Please
• • see Documentation/vm/pin_user_pages.rst for further details.
• • FOLL_LONGTERM means that the pages are being pinned for "long term" use,
• • typically by a non-CPU device, and we cannot be sure that waiting for a
• • pinned page to become unpin will be effective.
• • This is intended for Case 2 (RDMA: long-term pins) of the FOLL_PIN
• • documentation.
• */

+int pin_longterm_pages_fast(unsigned long start, int nr_pages,

• 	    unsigned int gup_flags, struct page **pages)
  

+{

• /* FOLL_GET and FOLL_PIN are mutually exclusive. */
• if (WARN_ON_ONCE(gup_flags & FOLL_GET))

• return -EINVAL;
  

• gup_flags |= (FOLL_PIN | FOLL_LONGTERM);
• return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);

+} +EXPORT_SYMBOL_GPL(pin_longterm_pages_fast);

+/**

• • pin_user_pages_remote() - pin pages for (typically) use by Direct IO, and
• • return the pages to the user.
• • Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See
• • get_user_pages_remote() for documentation on the function arguments, because
• • the arguments here are identical.
• • FOLL_PIN means that the pages must be released via put_user_page(). Please
• • see Documentation/vm/pin_user_pages.rst for details.
• • This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
• • is NOT intended for Case 2 (RDMA: long-term pins).
• */

+long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,

• 	   unsigned long start, unsigned long nr_pages,
  

• 	   unsigned int gup_flags, struct page **pages,
  

• 	   struct vm_area_struct **vmas, int *locked)
  

+{

• /* FOLL_GET and FOLL_PIN are mutually exclusive. */
• if (WARN_ON_ONCE(gup_flags & FOLL_GET))

• return -EINVAL;
  

• gup_flags |= FOLL_TOUCH | FOLL_REMOTE | FOLL_PIN;
• return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,

• 		       locked, gup_flags);
  

+} +EXPORT_SYMBOL(pin_user_pages_remote);

+/**

• • pin_longterm_pages_remote() - pin pages for (typically) use by Direct IO, and
• • return the pages to the user.
• • Nearly the same as get_user_pages_remote(), but note that FOLL_TOUCH is not
• • set, and FOLL_PIN and FOLL_LONGTERM are set. See get_user_pages_remote() for
• • documentation on the function arguments, because the arguments here are
• • identical.
• • FOLL_PIN means that the pages must be released via put_user_page(). Please
• • see Documentation/vm/pin_user_pages.rst for further details.
• • FOLL_LONGTERM means that the pages are being pinned for "long term" use,
• • typically by a non-CPU device, and we cannot be sure that waiting for a
• • pinned page to become unpin will be effective.
• • This is intended for Case 2 (RDMA: long-term pins) in
• • Documentation/vm/pin_user_pages.rst.
• */

+long pin_longterm_pages_remote(struct task_struct *tsk, struct mm_struct *mm,

• 	       unsigned long start, unsigned long nr_pages,
  

• 	       unsigned int gup_flags, struct page **pages,
  

• 	       struct vm_area_struct **vmas, int *locked)
  

+{

• /* FOLL_GET and FOLL_PIN are mutually exclusive. */
• if (WARN_ON_ONCE(gup_flags & FOLL_GET))

• return -EINVAL;
  

• /*

• * FIXME: as noted in the get_user_pages_remote() implementation, it
  

• * is not yet possible to safely set FOLL_LONGTERM here. FOLL_LONGTERM
  

• * needs to be set, but for now the best we can do is a "TODO" item.
  

• */
  

• gup_flags |= FOLL_REMOTE | FOLL_PIN;
• return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,

• 		       locked, gup_flags);
  

+} +EXPORT_SYMBOL(pin_longterm_pages_remote);

+/**

• • pin_user_pages() - pin user pages in memory for use by other devices
• • Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and
• • FOLL_PIN is set.
• • FOLL_PIN means that the pages must be released via put_user_page(). Please
• • see Documentation/vm/pin_user_pages.rst for details.
• • This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
• • is NOT intended for Case 2 (RDMA: long-term pins).
• */

+long pin_user_pages(unsigned long start, unsigned long nr_pages,

•     unsigned int gup_flags, struct page **pages,
  

•     struct vm_area_struct **vmas)
  

+{

• /* FOLL_GET and FOLL_PIN are mutually exclusive. */
• if (WARN_ON_ONCE(gup_flags & FOLL_GET))

• return -EINVAL;
  

• gup_flags |= FOLL_PIN;
• return __gup_longterm_locked(current, current->mm, start, nr_pages,

• 		     pages, vmas, gup_flags);
  

+} +EXPORT_SYMBOL(pin_user_pages);

+/**

• • pin_longterm_pages() - pin user pages in memory for long-term use (RDMA,
• • typically)
• • Nearly the same as get_user_pages(), except that FOLL_PIN and FOLL_LONGTERM
• • are set. See get_user_pages_fast() for documentation on the function
• • arguments, because the arguments here are identical.
• • FOLL_PIN means that the pages must be released via put_user_page(). Please
• • see Documentation/vm/pin_user_pages.rst for further details.
• • FOLL_LONGTERM means that the pages are being pinned for "long term" use,
• • typically by a non-CPU device, and we cannot be sure that waiting for a
• • pinned page to become unpin will be effective.
• • This is intended for Case 2 (RDMA: long-term pins) in
• • Documentation/vm/pin_user_pages.rst.
• */

+long pin_longterm_pages(unsigned long start, unsigned long nr_pages,

• 	unsigned int gup_flags, struct page **pages,
  

• 	struct vm_area_struct **vmas)
  

+{

• /* FOLL_GET and FOLL_PIN are mutually exclusive. */
• if (WARN_ON_ONCE(gup_flags & FOLL_GET))

• return -EINVAL;
  

• gup_flags |= FOLL_PIN | FOLL_LONGTERM;
• return __gup_longterm_locked(current, current->mm, start, nr_pages,

• 		     pages, vmas, gup_flags);
  

+}

+EXPORT_SYMBOL(pin_longterm_pages);

2.23.0

On Sun, Nov 03, 2019 at 01:18:02PM -0800, John Hubbard wrote:

Convert infiniband to use the new wrapper calls, and stop explicitly setting FOLL_LONGTERM at the call sites.

The new pin_longterm_*() calls replace get_user_pages*() calls, and set both FOLL_LONGTERM and a new FOLL_PIN flag. The FOLL_PIN flag requires that the caller must return the pages via put_user_page*() calls, but infiniband was already doing that as part of an earlier commit.

Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com drivers/infiniband/core/umem.c | 5 ++--- drivers/infiniband/core/umem_odp.c | 10 +++++----- drivers/infiniband/hw/hfi1/user_pages.c | 4 ++-- drivers/infiniband/hw/mthca/mthca_memfree.c | 3 +-- drivers/infiniband/hw/qib/qib_user_pages.c | 8 ++++---- drivers/infiniband/hw/qib/qib_user_sdma.c | 2 +- drivers/infiniband/hw/usnic/usnic_uiom.c | 9 ++++----- drivers/infiniband/sw/siw/siw_mem.c | 5 ++--- 8 files changed, 21 insertions(+), 25 deletions(-)

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 24244a2f68cc..c5a78d3e674b 100644 +++ b/drivers/infiniband/core/umem.c @@ -272,11 +272,10 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, while (npages) { down_read(&mm->mmap_sem);

• ret = get_user_pages(cur_base,
  

• ret = pin_longterm_pages(cur_base,
  	     min_t(unsigned long, npages,
  		   PAGE_SIZE / sizeof (struct page *)),
  

• 		     gup_flags | FOLL_LONGTERM,
  

• 		     page_list, NULL);
  

• 		     gup_flags, page_list, NULL);
  

FWIW, this one should be converted to fast as well, I think we finally got rid of all the blockers for that?

Jason

On Mon, Nov 04, 2019 at 12:48:13PM -0800, John Hubbard wrote:

On 11/4/19 12:33 PM, Jason Gunthorpe wrote: ...

...

...

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 24244a2f68cc..c5a78d3e674b 100644 +++ b/drivers/infiniband/core/umem.c @@ -272,11 +272,10 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, while (npages) { down_read(&mm->mmap_sem);

• ret = get_user_pages(cur_base,
  

• ret = pin_longterm_pages(cur_base,
  	     min_t(unsigned long, npages,
  		   PAGE_SIZE / sizeof (struct page *)),
  

• 		     gup_flags | FOLL_LONGTERM,
  

• 		     page_list, NULL);
  

• 		     gup_flags, page_list, NULL);
  

FWIW, this one should be converted to fast as well, I think we finally got rid of all the blockers for that?

I'm not aware of any blockers on the gup.c end, anyway. The only broken thing we have there is "gup remote + FOLL_LONGTERM". But we can do "gup fast + LONGTERM".

I mean the use of the mmap_sem here is finally in a way where we can just delete the mmap_sem and use _fast

ie, AFAIK there is no need for the mmap_sem to be held during ib_umem_add_sg_table()

This should probably be a standalone patch however

Jason

On Mon, Nov 04, 2019 at 02:03:43PM -0800, John Hubbard wrote:

On 11/4/19 12:57 PM, Jason Gunthorpe wrote:

...

On Mon, Nov 04, 2019 at 12:48:13PM -0800, John Hubbard wrote:

...

On 11/4/19 12:33 PM, Jason Gunthorpe wrote: ...

...

...

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 24244a2f68cc..c5a78d3e674b 100644 +++ b/drivers/infiniband/core/umem.c @@ -272,11 +272,10 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, while (npages) { down_read(&mm->mmap_sem);

• ret = get_user_pages(cur_base,
  

• ret = pin_longterm_pages(cur_base,
  	     min_t(unsigned long, npages,
  		   PAGE_SIZE / sizeof (struct page *)),
  

• 		     gup_flags | FOLL_LONGTERM,
  

• 		     page_list, NULL);
  

• 		     gup_flags, page_list, NULL);
  

FWIW, this one should be converted to fast as well, I think we finally got rid of all the blockers for that?

I'm not aware of any blockers on the gup.c end, anyway. The only broken thing we have there is "gup remote + FOLL_LONGTERM". But we can do "gup fast + LONGTERM".

I mean the use of the mmap_sem here is finally in a way where we can just delete the mmap_sem and use _fast ie, AFAIK there is no need for the mmap_sem to be held during ib_umem_add_sg_table()

This should probably be a standalone patch however

Yes. Oh, actually I guess the patch flow should be: change to get_user_pages_fast() and remove the mmap_sem calls, as one patch. And then change to pin_longterm_pages_fast() as the next patch. Otherwise, the internal fallback from _fast to slow gup would attempt to take the mmap_sem (again) in the same thread, which is not good. :)

Or just defer the change until after this series. Either way is fine, let me know if you prefer one over the other.

The patch itself is trivial, but runtime testing to gain confidence that it's solid is much harder. Is there a stress test you would recommend for that? (I'm not promising I can quickly run it yet--my local IB setup is still nascent at best.)

If you make a patch we can probably get it tested, it is something we should do I keep forgetting about.

Jason

On 11/4/19 9:44 AM, Jerome Glisse wrote:

On Sun, Nov 03, 2019 at 01:18:04PM -0800, John Hubbard wrote:

...

Convert drm/via to use the new pin_user_pages_fast() call, which sets FOLL_PIN. Setting FOLL_PIN is now required for code that requires tracking of pinned pages, and therefore for any code that calls put_user_page().

Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com

Please be more explicit that via_dmablit.c is already using put_user_page() as i am expecting that any conversion to pin_user_pages*() must be pair with a put_user_page(). I find above commit message bit unclear from that POV.

OK. This one, and the fs/io_uring (patch 9) and net/xdp (patch 10) were all cases that had put_user_page() pre-existing. I will add something like the following to each commit description, for v3:

In partial anticipation of this work, the drm/via driver was already calling put_user_page() instead of put_page(). Therefore, in order to convert from the get_user_pages()/put_page() model, to the pin_user_pages()/put_user_page() model, the only change required is to change get_user_pages() to pin_user_pages().

thanks,

John Hubbard NVIDIA

Reviewed-by: Jérôme Glisse jglisse@redhat.com

...

---

drivers/gpu/drm/via/via_dmablit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c index 3db000aacd26..37c5e572993a 100644 --- a/drivers/gpu/drm/via/via_dmablit.c +++ b/drivers/gpu/drm/via/via_dmablit.c @@ -239,7 +239,7 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg, drm_via_dmablit_t *xfer) vsg->pages = vzalloc(array_size(sizeof(struct page *), vsg->num_pages)); if (NULL == vsg->pages) return -ENOMEM;

• ret = get_user_pages_fast((unsigned long)xfer->mem_addr,

• ret = pin_user_pages_fast((unsigned long)xfer->mem_addr, vsg->num_pages, vsg->direction == DMA_FROM_DEVICE ? FOLL_WRITE : 0, vsg->pages);

-- 2.23.0

On Sun, Nov 03, 2019 at 01:18:07PM -0800, John Hubbard wrote:

Add tracking of pages that were pinned via FOLL_PIN.

As mentioned in the FOLL_PIN documentation, callers who effectively set FOLL_PIN are required to ultimately free such pages via put_user_page(). The effect is similar to FOLL_GET, and may be thought of as "FOLL_GET for DIO and/or RDMA use".

Pages that have been pinned via FOLL_PIN are identifiable via a new function call:

bool page_dma_pinned(struct page *page);

What to do in response to encountering such a page, is left to later patchsets. There is discussion about this in [1].

This also changes a BUG_ON(), to a WARN_ON(), in follow_page_mask().

This also has a couple of trivial, non-functional change fixes to try_get_compound_head(). That function got moved to the top of the file.

Maybe split that as a separate trivial patch.

This includes the following fix from Ira Weiny:

DAX requires detection of a page crossing to a ref count of 1. Fix this for GUP pages by introducing put_devmap_managed_user_page() which accounts for GUP_PIN_COUNTING_BIAS now used by GUP.

Please do the put_devmap_managed_page() changes in a separate patch, it would be a lot easier to follow, also on that front see comments below.

[1] https://lwn.net/Articles/784574/ "Some slow progress on get_user_pages()"

Suggested-by: Jan Kara jack@suse.cz Suggested-by: Jérôme Glisse jglisse@redhat.com Signed-off-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com

---

include/linux/mm.h | 80 +++++++++++---- include/linux/mmzone.h | 2 + include/linux/page_ref.h | 10 ++ mm/gup.c | 213 +++++++++++++++++++++++++++++++-------- mm/huge_memory.c | 32 +++++- mm/hugetlb.c | 28 ++++- mm/memremap.c | 4 +- mm/vmstat.c | 2 + 8 files changed, 300 insertions(+), 71 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h index cdfb6fedb271..03b3600843b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -972,9 +972,10 @@ static inline bool is_zone_device_page(const struct page *page) #endif #ifdef CONFIG_DEV_PAGEMAP_OPS -void __put_devmap_managed_page(struct page *page); +void __put_devmap_managed_page(struct page *page, int count); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -static inline bool put_devmap_managed_page(struct page *page)

+static inline bool page_is_devmap_managed(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; @@ -983,7 +984,6 @@ static inline bool put_devmap_managed_page(struct page *page) switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_FS_DAX:

• __put_devmap_managed_page(page);
  

  return true; default: break;

@@ -991,6 +991,19 @@ static inline bool put_devmap_managed_page(struct page *page) return false; } +static inline bool put_devmap_managed_page(struct page *page) +{

• bool is_devmap = page_is_devmap_managed(page);
• if (is_devmap) {

• int count = page_ref_dec_return(page);
  

• __put_devmap_managed_page(page, count);
  

• }
• return is_devmap;

+}

I think the __put_devmap_managed_page() should be rename to free_devmap_managed_page() and that the count != 1 case move to this inline function ie:

static inline bool put_devmap_managed_page(struct page *page) { bool is_devmap = page_is_devmap_managed(page);

if (is_devmap) { int count = page_ref_dec_return(page);

/* * If refcount is 1 then page is freed and refcount is stable as nobody * holds a reference on the page. */ if (count == 1) free_devmap_managed_page(page, count); else if (!count) __put_page(page); }

return is_devmap; }

#else /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool put_devmap_managed_page(struct page *page) { @@ -1038,6 +1051,8 @@ static inline __must_check bool try_get_page(struct page *page) return true; } +__must_check bool user_page_ref_inc(struct page *page);

What about having it as an inline here as it is pretty small.

static inline void put_page(struct page *page) { page = compound_head(page); @@ -1055,31 +1070,56 @@ static inline void put_page(struct page *page) __put_page(page); } -/**

• • put_user_page() - release a gup-pinned page
• • @page: pointer to page to be released

+/*

• • GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload
• • the page's refcount so that two separate items are tracked: the original page
• • reference count, and also a new count of how many get_user_pages() calls were
• • made against the page. ("gup-pinned" is another term for the latter).
• • With this scheme, get_user_pages() becomes special: such pages are marked
• • as distinct from normal pages. As such, the new put_user_page() call (and
• • its variants) must be used in order to release gup-pinned pages.
• • Choice of value:

• • Pages that were pinned via get_user_pages*() must be released via
• • either put_user_page(), or one of the put_user_pages*() routines
• • below. This is so that eventually, pages that are pinned via
• • get_user_pages*() can be separately tracked and uniquely handled. In
• • particular, interactions with RDMA and filesystems need special
• • handling.

• • By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference
• • counts with respect to get_user_pages() and put_user_page() becomes simpler,
• • due to the fact that adding an even power of two to the page refcount has
• • the effect of using only the upper N bits, for the code that counts up using
• • the bias value. This means that the lower bits are left for the exclusive
• • use of the original code that increments and decrements by one (or at least,
• • by much smaller values than the bias value).

• • put_user_page() and put_page() are not interchangeable, despite this early
• • implementation that makes them look the same. put_user_page() calls must
• • be perfectly matched up with get_user_page() calls.

• • Of course, once the lower bits overflow into the upper bits (and this is
• • OK, because subtraction recovers the original values), then visual inspection
• • no longer suffices to directly view the separate counts. However, for normal
• • applications that don't have huge page reference counts, this won't be an
• • issue.
• • Locking: the lockless algorithm described in page_cache_get_speculative()
• • and page_cache_gup_pin_speculative() provides safe operation for
• • get_user_pages and page_mkclean and other calls that race to set up page
• • table entries.
  */

-static inline void put_user_page(struct page *page) -{

• put_page(page);

-} +#define GUP_PIN_COUNTING_BIAS (1UL << 10) +void put_user_page(struct page *page); void put_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty);

void put_user_pages(struct page **pages, unsigned long npages); +/**

• • page_dma_pinned() - report if a page is pinned by a call to pin_user_pages*()
• • or pin_longterm_pages*()
• • @page: pointer to page to be queried.
• • @Return: True, if it is likely that the page has been "dma-pinned".

• • False, if the page is definitely not dma-pinned.
    

• */

Maybe add a small comment about wrap around :)

+static inline bool page_dma_pinned(struct page *page) +{

• return (page_ref_count(compound_head(page))) >= GUP_PIN_COUNTING_BIAS;

+}

#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif

[...]

diff --git a/mm/gup.c b/mm/gup.c index 1aea48427879..c9727e65fad3 100644 --- a/mm/gup.c +++ b/mm/gup.c

[...]

@@ -1930,12 +2028,20 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) {

• 	undo_dev_pagemap(nr, nr_start, pages);
  

• 	undo_dev_pagemap(nr, nr_start, flags, pages);
  return 0;
  

  } SetPageReferenced(page); pages[*nr] = page;

• get_page(page);
  

• if (flags & FOLL_PIN) {
  

• 	if (unlikely(!user_page_ref_inc(page))) {
  

• 		undo_dev_pagemap(nr, nr_start, flags, pages);
  

• 		return 0;
  

• 	}
  

Maybe add a comment about a case that should never happens ie user_page_ref_inc() fails after the second iteration of the loop as it would be broken and a bug to call undo_dev_pagemap() after the first iteration of that loop.

Also i believe that this should never happens as if first iteration succeed than __page_cache_add_speculative() will succeed for all the iterations.

Note that the pgmap case above follows that too ie the call to get_dev_pagemap() can only fail on first iteration of the loop, well i assume you can never have a huge device page that span different pgmap ie different devices (which is a reasonable assumption). So maybe this code needs fixing ie :

pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) return 0;

• } else
  

• 	get_page(page);
  

• (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end);

[...]

@@ -2409,7 +2540,7 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, unsigned long addr, len, end; int nr = 0, ret = 0;

• if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM)))

• if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_PIN)))

Maybe add a comments to explain, something like:

/* * The only flags allowed here are: FOLL_WRITE, FOLL_LONGTERM, FOLL_PIN * * Note that get_user_pages_fast() imply FOLL_GET flag by default but * callers can over-ride this default to pin case by setting FOLL_PIN. */

return -EINVAL;

start = untagged_addr(start) & PAGE_MASK; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 13cc93785006..66bf4c8b88f1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c

[...]

@@ -968,7 +973,12 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn);

• get_page(page);

• if (flags & FOLL_GET)

• get_page(page);
  

• else if (flags & FOLL_PIN)

• if (unlikely(!user_page_ref_inc(page)))
  

• 	page = ERR_PTR(-ENOMEM);
  

While i agree that user_page_ref_inc() (ie page_cache_add_speculative()) should never fails here as we are holding the pmd lock and thus no one can unmap the pmd and free the page it points to. I believe you should return -EFAULT like for the pgmap and not -ENOMEM as the pgmap should not fail either for the same reason. Thus it would be better to have consistent error. Maybe also add a comments explaining that it should not fail here.

return page; }

[...]

@@ -1100,7 +1115,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, * device mapped pages can only be returned if the * caller will manage the page reference count. */

• if (!(flags & FOLL_GET))

• if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST);

Maybe add a comment that FOLL_GET or FOLL_PIN must be set.

pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; @@ -1108,7 +1123,12 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn);

• get_page(page);

• if (flags & FOLL_GET)

• get_page(page);
  

• else if (flags & FOLL_PIN)

• if (unlikely(!user_page_ref_inc(page)))
  

• 	page = ERR_PTR(-ENOMEM);
  

Same as for follow_devmap_pmd() see above.

return page; } @@ -1522,8 +1542,12 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, skip_mlock: page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);

• if (flags & FOLL_GET) get_page(page);
• else if (flags & FOLL_PIN)

• if (unlikely(!user_page_ref_inc(page)))
  

• 	page = NULL;
  

This should not fail either as we are holding the pmd lock maybe add a comment. Dunno if we want a WARN() or something to catch this degenerate case, or dump the page.

out: return page; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b45a95363a84..da335b1cd798 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4462,7 +4462,17 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset);

• 	get_page(pages[i]);
  

• 	if (flags & FOLL_GET)
  

• 		get_page(pages[i]);
  

• 	else if (flags & FOLL_PIN)
  

• 		if (unlikely(!user_page_ref_inc(pages[i]))) {
  

• 			spin_unlock(ptl);
  

• 			remainder = 0;
  

• 			err = -ENOMEM;
  

• 			WARN_ON_ONCE(1);
  

• 			break;
  

• 		}
  

  }

user_page_ref_inc() should not fail here either because we hold the ptl, so the WAR_ON_ONCE() is right but maybe add a comment.

if (vmas)

[...]

@@ -5034,8 +5050,14 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, pte = huge_ptep_get((pte_t *)pmd); if (pte_present(pte)) { page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);

• if (flags & FOLL_GET) get_page(page);

• else if (flags & FOLL_PIN)
  

• 	if (unlikely(!user_page_ref_inc(page))) {
  

• 		page = NULL;
  

• 		goto out;
  

• 	}
  

This should not fail either (again holding pmd lock), dunno if we want a warn or something to catch this degenerate case.

} else { if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl);

[...]

On Mon, Nov 04, 2019 at 02:49:18PM -0800, John Hubbard wrote:

On 11/4/19 10:52 AM, Jerome Glisse wrote:

...

On Sun, Nov 03, 2019 at 01:18:07PM -0800, John Hubbard wrote:

...

Add tracking of pages that were pinned via FOLL_PIN.

As mentioned in the FOLL_PIN documentation, callers who effectively set FOLL_PIN are required to ultimately free such pages via put_user_page(). The effect is similar to FOLL_GET, and may be thought of as "FOLL_GET for DIO and/or RDMA use".

Pages that have been pinned via FOLL_PIN are identifiable via a new function call:

bool page_dma_pinned(struct page *page);

What to do in response to encountering such a page, is left to later patchsets. There is discussion about this in [1].

This also changes a BUG_ON(), to a WARN_ON(), in follow_page_mask().

This also has a couple of trivial, non-functional change fixes to try_get_compound_head(). That function got moved to the top of the file.

Maybe split that as a separate trivial patch.

Will do.

...

...

This includes the following fix from Ira Weiny:

DAX requires detection of a page crossing to a ref count of 1. Fix this for GUP pages by introducing put_devmap_managed_user_page() which accounts for GUP_PIN_COUNTING_BIAS now used by GUP.

Please do the put_devmap_managed_page() changes in a separate patch, it would be a lot easier to follow, also on that front see comments below.

Oh! OK. It makes sense when you say it out loud. :)

...

...

...

+static inline bool put_devmap_managed_page(struct page *page) +{

• bool is_devmap = page_is_devmap_managed(page);
• if (is_devmap) {

• int count = page_ref_dec_return(page);
  

• __put_devmap_managed_page(page, count);
  

• }
• return is_devmap;

+}

I think the __put_devmap_managed_page() should be rename to free_devmap_managed_page() and that the count != 1 case move to this inline function ie:

static inline bool put_devmap_managed_page(struct page *page) { bool is_devmap = page_is_devmap_managed(page);

if (is_devmap) { int count = page_ref_dec_return(page);

/*
 * If refcount is 1 then page is freed and refcount is stable as nobody
 * holds a reference on the page.
 */
if (count == 1)
	free_devmap_managed_page(page, count);
else if (!count)
	__put_page(page);

}

return is_devmap; }

Thanks, that does look cleaner and easier to read.

...

...

#else /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool put_devmap_managed_page(struct page *page) { @@ -1038,6 +1051,8 @@ static inline __must_check bool try_get_page(struct page *page) return true; } +__must_check bool user_page_ref_inc(struct page *page);

What about having it as an inline here as it is pretty small.

You mean move it to a static inline function in mm.h? It's worse than it looks, though: *everything* that it calls is also a static function, local to gup.c. So I'd have to expose both try_get_compound_head() and __update_proc_vmstat(). And that also means calling mod_node_page_state() from mm.h, and it goes south right about there. :)

Ok fair enough

...

...

...

+/**

• • page_dma_pinned() - report if a page is pinned by a call to pin_user_pages*()
• • or pin_longterm_pages*()
• • @page: pointer to page to be queried.
• • @Return: True, if it is likely that the page has been "dma-pinned".

• • False, if the page is definitely not dma-pinned.
    

• */

Maybe add a small comment about wrap around :)

I don't *think* the count can wrap around, due to the checks in user_page_ref_inc().

But it's true that the documentation is a little light here...What did you have in mind?

About false positive case (and how unlikely they are) and that wrap around is properly handle. Maybe just a pointer to the documentation so that people know they can go look there for details. I know my brain tend to forget where to look for things so i like to be constantly reminded hey the doc is Documentations/foobar :)

...

[...]

...

@@ -1930,12 +2028,20 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) {

• 	undo_dev_pagemap(nr, nr_start, pages);
  

• 	undo_dev_pagemap(nr, nr_start, flags, pages);
  return 0;
  

  } SetPageReferenced(page); pages[*nr] = page;

• get_page(page);
  

• if (flags & FOLL_PIN) {
  

• 	if (unlikely(!user_page_ref_inc(page))) {
  

• 		undo_dev_pagemap(nr, nr_start, flags, pages);
  

• 		return 0;
  

• 	}
  

Maybe add a comment about a case that should never happens ie user_page_ref_inc() fails after the second iteration of the loop as it would be broken and a bug to call undo_dev_pagemap() after the first iteration of that loop.

Also i believe that this should never happens as if first iteration succeed than __page_cache_add_speculative() will succeed for all the iterations.

Note that the pgmap case above follows that too ie the call to get_dev_pagemap() can only fail on first iteration of the loop, well i assume you can never have a huge device page that span different pgmap ie different devices (which is a reasonable assumption). So maybe this code needs fixing ie :

pgmap = get_dev_pagemap(pfn, pgmap);
if (unlikely(!pgmap))
	return 0;

OK, yes that does make sense. And I think a comment is adequate, no need to check for bugs during every tail page iteration. So how about this, as a preliminary patch:

Actualy i thought about it and i think that there is pgmap per section and thus maybe one device can have multiple pgmap and that would be an issue for page bigger than section size (ie bigger than 128MB iirc). I will go double check that, but maybe Dan can chime in.

In any case my comment above is correct for the page ref increment, if the first one succeed than others will too or otherwise it means someone is doing too many put_page()/ put_user_page() which is _bad_ :)

diff --git a/mm/gup.c b/mm/gup.c index 8f236a335ae9..a4a81e125832 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1892,17 +1892,18 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, static int __gup_device_huge(unsigned long pfn, unsigned long addr, unsigned long end, struct page **pages, int *nr) {

•   int nr_start = *nr;
  

•   struct dev_pagemap *pgmap = NULL;
  

•   /*
  

•    * Huge pages should never cross dev_pagemap boundaries. Therefore, use
  

•    * this same pgmap for the entire huge page.
  

•    */
  

•   struct dev_pagemap *pgmap = get_dev_pagemap(pfn, NULL);
  

•   if (unlikely(!pgmap))
  

•           return 0;
  

do { struct page *page = pfn_to_page(pfn);

•           pgmap = get_dev_pagemap(pfn, pgmap);
  

•           if (unlikely(!pgmap)) {
  

•                   undo_dev_pagemap(nr, nr_start, pages);
  

•                   return 0;
  

•           }
            SetPageReferenced(page);
            pages[*nr] = page;
            get_page(page);
  
  
  
  
  

...

...

• } else
  

• 	get_page(page);
  

• (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end);

[...]

...

@@ -2409,7 +2540,7 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, unsigned long addr, len, end; int nr = 0, ret = 0;

• if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM)))

• if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_PIN)))

Maybe add a comments to explain, something like:

/*

• The only flags allowed here are: FOLL_WRITE, FOLL_LONGTERM, FOLL_PIN
• Note that get_user_pages_fast() imply FOLL_GET flag by default but
• callers can over-ride this default to pin case by setting FOLL_PIN.

*/

Good idea. Here's the draft now:

/*

• The only flags allowed here are: FOLL_WRITE, FOLL_LONGTERM, FOLL_PIN.
• Note that get_user_pages_fast() implies FOLL_GET flag by default, but
• callers can override this default by setting FOLL_PIN instead of
• FOLL_GET.

*/ if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_PIN))) return -EINVAL;

Looks good to me.

...

Cheers, Jérôme