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.

Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Jérôme Glisse jglisse@redhat.com Reviewed-by: Jan Kara jack@suse.cz 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 --- mm/gup.c | 91 ++++++++++++++++++++++---------------------------------- 1 file changed, 36 insertions(+), 55 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index 7646bf993b25..f764432914c4 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1978,6 +1978,25 @@ 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; + + for (nr = 0; addr != end; addr += PAGE_SIZE) + pages[nr++] = page++; + + return nr; +} + +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); +} + #ifdef CONFIG_ARCH_HAS_HUGEPD static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, unsigned long sz) @@ -2007,32 +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; }

+ *nr += refs; SetPageReferenced(head); return 1; } @@ -2079,28 +2086,19 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return __gup_device_huge_pmd(orig, pmdp, addr, end, 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; }

+ *nr += refs; SetPageReferenced(head); return 1; } @@ -2120,28 +2118,19 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return __gup_device_huge_pud(orig, pudp, addr, end, 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; }

+ *nr += refs; SetPageReferenced(head); return 1; } @@ -2157,28 +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; }

+ *nr += refs; SetPageReferenced(head); return 1; }

From: Dan Williams dan.j.williams@intel.com

After the removal of the device-public infrastructure there are only 2 ->page_free() call backs in the kernel. One of those is a device-private callback in the nouveau driver, the other is a generic wakeup needed in the DAX case. In the hopes that all ->page_free() callbacks can be migrated to common core kernel functionality, move the device-private specific actions in __put_devmap_managed_page() under the is_device_private_page() conditional, including the ->page_free() callback. For the other page types just open-code the generic wakeup.

Yes, the wakeup is only needed in the MEMORY_DEVICE_FSDAX case, but it does no harm in the MEMORY_DEVICE_DEVDAX and MEMORY_DEVICE_PCI_P2PDMA case.

Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Jérôme Glisse jglisse@redhat.com Cc: Jan Kara jack@suse.cz Cc: Ira Weiny ira.weiny@intel.com Signed-off-by: Dan Williams dan.j.williams@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- drivers/nvdimm/pmem.c | 6 ---- mm/memremap.c | 80 ++++++++++++++++++++++++------------------- 2 files changed, 44 insertions(+), 42 deletions(-)

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index ad8e4df1282b..4eae441f86c9 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -337,13 +337,7 @@ static void pmem_release_disk(void *__pmem) put_disk(pmem->disk); }

-static void pmem_pagemap_page_free(struct page *page) -{ - wake_up_var(&page->_refcount); -} - static const struct dev_pagemap_ops fsdax_pagemap_ops = { - .page_free = pmem_pagemap_page_free, .kill = pmem_pagemap_kill, .cleanup = pmem_pagemap_cleanup, }; diff --git a/mm/memremap.c b/mm/memremap.c index 03ccbdfeb697..e899fa876a62 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -27,7 +27,8 @@ static void devmap_managed_enable_put(void)

static int devmap_managed_enable_get(struct dev_pagemap *pgmap) { - if (!pgmap->ops || !pgmap->ops->page_free) { + if (pgmap->type == MEMORY_DEVICE_PRIVATE && + (!pgmap->ops || !pgmap->ops->page_free)) { WARN(1, "Missing page_free method\n"); return -EINVAL; } @@ -414,44 +415,51 @@ void __put_devmap_managed_page(struct page *page) { 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) { - /* Clear Active bit in case of parallel mark_page_accessed */ - __ClearPageActive(page); - __ClearPageWaiters(page); + /* still busy */ + if (count > 1) + return;

- mem_cgroup_uncharge(page); + /* only triggered by the dev_pagemap shutdown path */ + if (count == 0) { + __put_page(page); + return; + }

- /* - * When a device_private page is freed, the page->mapping field - * may still contain a (stale) mapping value. For example, the - * lower bits of page->mapping may still identify the page as - * an anonymous page. Ultimately, this entire field is just - * stale and wrong, and it will cause errors if not cleared. - * One example is: - * - * migrate_vma_pages() - * migrate_vma_insert_page() - * page_add_new_anon_rmap() - * __page_set_anon_rmap() - * ...checks page->mapping, via PageAnon(page) call, - * and incorrectly concludes that the page is an - * anonymous page. Therefore, it incorrectly, - * silently fails to set up the new anon rmap. - * - * For other types of ZONE_DEVICE pages, migration is either - * handled differently or not done at all, so there is no need - * to clear page->mapping. - */ - if (is_device_private_page(page)) - page->mapping = NULL; + /* notify page idle for dax */ + if (!is_device_private_page(page)) { + wake_up_var(&page->_refcount); + return; + }

- page->pgmap->ops->page_free(page); - } else if (!count) - __put_page(page); + /* Clear Active bit in case of parallel mark_page_accessed */ + __ClearPageActive(page); + __ClearPageWaiters(page); + + mem_cgroup_uncharge(page); + + /* + * When a device_private page is freed, the page->mapping field + * may still contain a (stale) mapping value. For example, the + * lower bits of page->mapping may still identify the page as an + * anonymous page. Ultimately, this entire field is just stale + * and wrong, and it will cause errors if not cleared. One + * example is: + * + * migrate_vma_pages() + * migrate_vma_insert_page() + * page_add_new_anon_rmap() + * __page_set_anon_rmap() + * ...checks page->mapping, via PageAnon(page) call, + * and incorrectly concludes that the page is an + * anonymous page. Therefore, it incorrectly, + * silently fails to set up the new anon rmap. + * + * For other types of ZONE_DEVICE pages, migration is either + * handled differently or not done at all, so there is no need + * to clear page->mapping. + */ + page->mapping = NULL; + page->pgmap->ops->page_free(page); } EXPORT_SYMBOL(__put_devmap_managed_page); #endif /* CONFIG_DEV_PAGEMAP_OPS */

1. Avoid naming conflicts: rename local static function from "pin_user_pages()" to "goldfish_pin_pages()".

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

Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Jérôme Glisse jglisse@redhat.com Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.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..ef50c264db71 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 goldfish_pin_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 = goldfish_pin_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;

Update VFIO to take advantage of the recently loosened restriction on FOLL_LONGTERM with get_user_pages_remote(). Also, now it is possible to fix a bug: the VFIO caller is logically a FOLL_LONGTERM user, but it wasn't setting FOLL_LONGTERM.

Also, remove an unnessary pair of calls that were releasing and reacquiring the mmap_sem. There is no need to avoid holding mmap_sem just in order to call page_to_pfn().

Also, now that the the DAX check ("if a VMA is DAX, don't allow long term pinning") is in the internals of get_user_pages_remote() and __gup_longterm_locked(), there's no need for it at the VFIO call site. So remove it.

Tested-by: Alex Williamson alex.williamson@redhat.com Acked-by: Alex Williamson alex.williamson@redhat.com Reviewed-by: Jason Gunthorpe jgg@mellanox.com Reviewed-by: Ira Weiny ira.weiny@intel.com Suggested-by: Jason Gunthorpe jgg@ziepe.ca Cc: Dan Williams dan.j.williams@intel.com Cc: Jerome Glisse jglisse@redhat.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- drivers/vfio/vfio_iommu_type1.c | 30 +++++------------------------- 1 file changed, 5 insertions(+), 25 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 2ada8e6cdb88..b800fc9a0251 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -322,7 +322,6 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, { struct page *page[1]; struct vm_area_struct *vma; - struct vm_area_struct *vmas[1]; unsigned int flags = 0; int ret;

@@ -330,33 +329,14 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, flags |= FOLL_WRITE;

down_read(&mm->mmap_sem); - if (mm == current->mm) { - ret = get_user_pages(vaddr, 1, flags | FOLL_LONGTERM, page, - vmas); - } else { - ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page, - vmas, NULL); - /* - * The lifetime of a vaddr_get_pfn() page pin is - * userspace-controlled. In the fs-dax case this could - * lead to indefinite stalls in filesystem operations. - * Disallow attempts to pin fs-dax pages via this - * interface. - */ - if (ret > 0 && vma_is_fsdax(vmas[0])) { - ret = -EOPNOTSUPP; - put_page(page[0]); - } - } - up_read(&mm->mmap_sem); - + ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM, + page, NULL, NULL); if (ret == 1) { *pfn = page_to_pfn(page[0]); - return 0; + ret = 0; + goto done; }

- down_read(&mm->mmap_sem); - vaddr = untagged_addr(vaddr);

vma = find_vma_intersection(mm, vaddr, vaddr + 1); @@ -366,7 +346,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, if (is_invalid_reserved_pfn(*pfn)) ret = 0; } - +done: up_read(&mm->mmap_sem); return ret; }

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

For now, these are placeholder calls, until the various call sites are converted to use the correct get_user_pages*() or pin_user_pages*() API.

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

pin_user_pages() pin_user_pages_remote() pin_user_pages_fast()

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

The underlying rules are:

* FOLL_PIN is a gup-internal flag, so the call sites should not directly set it. That behavior is enforced with assertions.

* 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 upon it.)

Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Mike Rapoport rppt@linux.ibm.com # Documentation Reviewed-by: Jérôme Glisse jglisse@redhat.com Cc: Jonathan Corbet corbet@lwn.net Cc: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- Documentation/core-api/index.rst | 1 + Documentation/core-api/pin_user_pages.rst | 233 ++++++++++++++++++++++ include/linux/mm.h | 63 ++++-- mm/gup.c | 161 +++++++++++++-- 4 files changed, 424 insertions(+), 34 deletions(-) create mode 100644 Documentation/core-api/pin_user_pages.rst

diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index ab0eae1c153a..413f7d7c8642 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -31,6 +31,7 @@ Core utilities generic-radix-tree memory-allocation mm-api + pin_user_pages gfp_mask-from-fs-io timekeeping boot-time-mm diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst new file mode 100644 index 000000000000..4f26637a5005 --- /dev/null +++ b/Documentation/core-api/pin_user_pages.rst @@ -0,0 +1,233 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================================================== +pin_user_pages() and related calls +==================================================== + +.. contents:: :local: + +Overview +======== + +This document describes the following functions: :: + + pin_user_pages + pin_user_pages_fast + pin_user_pages_remote + +Basic description of FOLL_PIN +============================= + +FOLL_PIN and FOLL_LONGTERM are flags that can be passed to the get_user_pages*() +("gup") family of functions. FOLL_PIN has significant interactions and +interdependencies with FOLL_LONGTERM, so both are covered here. + +FOLL_PIN is internal to gup, meaning that it 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_LONGTERM, on the other hand, *is* allowed to be set at the gup call sites. +This is in order to avoid creating a large number of wrapper functions to cover +all combinations of get*(), pin*(), FOLL_LONGTERM, and more. Also, the +pin_user_pages*() APIs are clearly distinct from the get_user_pages*() APIs, so +that's a natural dividing line, and a good point to make separate wrapper calls. +In other words, use pin_user_pages*() for DMA-pinned pages, and +get_user_pages*() for other cases. There are four cases described later on in +this document, to further clarify that concept. + +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 +=================================== + +For these pin_user_pages*() functions, FOLL_PIN is OR'd in with whatever gup +flags the caller provides. The caller is required to pass in a non-null struct +pages* array, and the function then pin pages by incrementing each by a special +value. For now, that value is +1, just like get_user_pages*().:: + + Function + -------- + pin_user_pages FOLL_PIN is always set internally by this function. + pin_user_pages_fast FOLL_PIN is always set internally by this function. + pin_user_pages_remote FOLL_PIN is always set internally by this function. + +For these get_user_pages*() functions, FOLL_GET might not even be specified. +Behavior is a little more complex than above. If FOLL_GET was *not* specified, +but the caller passed in a non-null struct pages* array, then the function +sets FOLL_GET for you, and proceeds to pin pages by incrementing the refcount +of each page by +1.:: + + Function + -------- + get_user_pages FOLL_GET is sometimes set internally by this function. + get_user_pages_fast FOLL_GET is sometimes set internally by this function. + get_user_pages_remote FOLL_GET is sometimes set internally by this function. + +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: 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. + +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 77a4df06c8a7..0fb9929e00af 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1048,16 +1048,14 @@ static inline void put_page(struct page *page) * put_user_page() - release a gup-pinned page * @page: pointer to page to be released * - * 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. + * Pages that were pinned via pin_user_pages*() must be released via either + * put_user_page(), or one of the put_user_pages*() routines. This is so that + * eventually such pages can be separately tracked and uniquely handled. In + * particular, interactions with RDMA and filesystems need special handling. * * 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. + * be perfectly matched up with pin*() calls. */ static inline void put_user_page(struct page *page) { @@ -1515,9 +1513,16 @@ 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 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 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, @@ -1525,6 +1530,8 @@ 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 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, @@ -2588,13 +2595,15 @@ 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(), whose usages 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 @@ -2609,11 +2618,39 @@ 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*() 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 should be set internally by the pin_user_pages*() 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 958ab0757389..4862ff982bc3 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -201,6 +201,10 @@ 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); @@ -818,7 +822,7 @@ 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 @@ -1042,7 +1046,16 @@ 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; @@ -1185,6 +1198,13 @@ 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_pages*() APIs, + * never directly by the caller, so enforce that with an assertion: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + return -EINVAL; + /* * Parts of FOLL_LONGTERM behavior are incompatible with * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on @@ -1400,6 +1420,14 @@ static long __get_user_pages_locked(struct task_struct *tsk, finish_or_fault: return i ? : -EFAULT; } + +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) +{ + return 0; +} #endif /* !CONFIG_MMU */

#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA) @@ -1654,6 +1682,13 @@ 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_pages*() 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); } @@ -2392,30 +2427,15 @@ 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;

if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | - FOLL_FORCE))) + FOLL_FORCE | FOLL_PIN))) return -EINVAL;

start = untagged_addr(start) & PAGE_MASK; @@ -2455,4 +2475,103 @@ 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_pages*() 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 + * + * For now, this is a placeholder function, until various call sites are + * converted to use the correct get_user_pages*() or pin_user_pages*() API. So, + * this is identical to get_user_pages_fast(). + * + * 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) +{ + /* + * This is a placeholder, until the pin functionality is activated. + * Until then, just behave like the corresponding get_user_pages*() + * routine. + */ + return get_user_pages_fast(start, nr_pages, gup_flags, pages); +} +EXPORT_SYMBOL_GPL(pin_user_pages_fast); + +/** + * pin_user_pages_remote() - pin pages of a remote process (task != current) + * + * For now, this is a placeholder function, until various call sites are + * converted to use the correct get_user_pages*() or pin_user_pages*() API. So, + * this is identical to get_user_pages_remote(). + * + * 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) +{ + /* + * This is a placeholder, until the pin functionality is activated. + * Until then, just behave like the corresponding get_user_pages*() + * routine. + */ + return get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, pages, + vmas, locked); +} +EXPORT_SYMBOL(pin_user_pages_remote); + +/** + * pin_user_pages() - pin user pages in memory for use by other devices + * + * For now, this is a placeholder function, until various call sites are + * converted to use the correct get_user_pages*() or pin_user_pages*() API. So, + * this is identical to get_user_pages(). + * + * 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) +{ + /* + * This is a placeholder, until the pin functionality is activated. + * Until then, just behave like the corresponding get_user_pages*() + * routine. + */ + return get_user_pages(start, nr_pages, gup_flags, pages, vmas); +} +EXPORT_SYMBOL(pin_user_pages);

Convert infiniband to use the new pin_user_pages*() calls.

Also, revert earlier changes to Infiniband ODP that had it using put_user_page(). ODP is "Case 3" in Documentation/core-api/pin_user_pages.rst, which is to say, normal get_user_pages() and put_page() is the API to use there.

The new pin_user_pages*() calls replace corresponding get_user_pages*() calls, and set the 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: Jason Gunthorpe jgg@mellanox.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- drivers/infiniband/core/umem.c | 2 +- drivers/infiniband/core/umem_odp.c | 13 ++++++------- drivers/infiniband/hw/hfi1/user_pages.c | 2 +- drivers/infiniband/hw/mthca/mthca_memfree.c | 2 +- drivers/infiniband/hw/qib/qib_user_pages.c | 2 +- drivers/infiniband/hw/qib/qib_user_sdma.c | 2 +- drivers/infiniband/hw/usnic/usnic_uiom.c | 2 +- drivers/infiniband/sw/siw/siw_mem.c | 2 +- 8 files changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 214e87aa609d..55daefaa9b88 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -266,7 +266,7 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, sg = umem->sg_head.sgl;

while (npages) { - ret = get_user_pages_fast(cur_base, + ret = pin_user_pages_fast(cur_base, min_t(unsigned long, npages, PAGE_SIZE / sizeof(struct page *)), diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index e42d44e501fd..abc3bb6578cc 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -308,9 +308,8 @@ EXPORT_SYMBOL(ib_umem_odp_release); * The function returns -EFAULT if the DMA mapping operation fails. It returns * -EAGAIN if a concurrent invalidation prevents us from updating the page. * - * The page is released via put_user_page even if the operation failed. For - * on-demand pinning, the page is released whenever it isn't stored in the - * umem. + * The page is released via put_page even if the operation failed. For on-demand + * pinning, the page is released whenever it isn't stored in the umem. */ static int ib_umem_odp_map_dma_single_page( struct ib_umem_odp *umem_odp, @@ -363,7 +362,7 @@ static int ib_umem_odp_map_dma_single_page( }

out: - put_user_page(page); + put_page(page); return ret; }

@@ -473,7 +472,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt, ret = -EFAULT; break; } - put_user_page(local_page_list[j]); + put_page(local_page_list[j]); continue; }

@@ -500,8 +499,8 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt, * ib_umem_odp_map_dma_single_page(). */ if (npages - (j + 1) > 0) - put_user_pages(&local_page_list[j+1], - npages - (j + 1)); + release_pages(&local_page_list[j+1], + npages - (j + 1)); break; } } diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c index 469acb961fbd..9a94761765c0 100644 --- a/drivers/infiniband/hw/hfi1/user_pages.c +++ b/drivers/infiniband/hw/hfi1/user_pages.c @@ -106,7 +106,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np int ret; unsigned int gup_flags = FOLL_LONGTERM | (writable ? FOLL_WRITE : 0);

- ret = get_user_pages_fast(vaddr, npages, gup_flags, pages); + ret = pin_user_pages_fast(vaddr, npages, gup_flags, pages); if (ret < 0) return ret;

diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c index edccfd6e178f..8269ab040c21 100644 --- a/drivers/infiniband/hw/mthca/mthca_memfree.c +++ b/drivers/infiniband/hw/mthca/mthca_memfree.c @@ -472,7 +472,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar, goto out; }

- ret = get_user_pages_fast(uaddr & PAGE_MASK, 1, + ret = pin_user_pages_fast(uaddr & PAGE_MASK, 1, FOLL_WRITE | FOLL_LONGTERM, pages); if (ret < 0) goto out; diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c index 6bf764e41891..7fc4b5f81fcd 100644 --- a/drivers/infiniband/hw/qib/qib_user_pages.c +++ b/drivers/infiniband/hw/qib/qib_user_pages.c @@ -108,7 +108,7 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,

down_read(&current->mm->mmap_sem); for (got = 0; got < num_pages; got += ret) { - ret = get_user_pages(start_page + got * PAGE_SIZE, + ret = pin_user_pages(start_page + got * PAGE_SIZE, num_pages - got, FOLL_LONGTERM | FOLL_WRITE | FOLL_FORCE, p + got, NULL); diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c index 05190edc2611..1a3cc2957e3a 100644 --- a/drivers/infiniband/hw/qib/qib_user_sdma.c +++ b/drivers/infiniband/hw/qib/qib_user_sdma.c @@ -670,7 +670,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd, else j = npages;

- ret = get_user_pages_fast(addr, j, FOLL_LONGTERM, pages); + ret = pin_user_pages_fast(addr, j, FOLL_LONGTERM, pages); if (ret != j) { i = 0; j = ret; diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index 62e6ffa9ad78..600896727d34 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -141,7 +141,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable, ret = 0;

while (npages) { - ret = get_user_pages(cur_base, + ret = pin_user_pages(cur_base, min_t(unsigned long, npages, PAGE_SIZE / sizeof(struct page *)), gup_flags | FOLL_LONGTERM, diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c index e99983f07663..e53b07dcfed5 100644 --- a/drivers/infiniband/sw/siw/siw_mem.c +++ b/drivers/infiniband/sw/siw/siw_mem.c @@ -426,7 +426,7 @@ struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable) while (nents) { struct page **plist = &umem->page_chunk[i].plist[got];

- rv = get_user_pages(first_page_va, nents, + rv = pin_user_pages(first_page_va, nents, foll_flags | FOLL_LONGTERM, plist, NULL); if (rv < 0)

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().

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().

Acked-by: Daniel Vetter daniel.vetter@ffwll.ch Reviewed-by: Jérôme Glisse jglisse@redhat.com Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.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);

Convert net/xdp to use the new pin_longterm_pages() call, which sets FOLL_PIN. Setting FOLL_PIN is now required for code that requires tracking of pinned pages.

In partial anticipation of this work, the net/xdp code 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 here is to change get_user_pages() to pin_user_pages().

Acked-by: Björn Töpel bjorn.topel@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- net/xdp/xdp_umem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 3049af269fbf..d071003b5e76 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -291,7 +291,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem) return -ENOMEM;

down_read(&current->mm->mmap_sem); - npgs = get_user_pages(umem->address, umem->npgs, + npgs = pin_user_pages(umem->address, umem->npgs, gup_flags | FOLL_LONGTERM, &umem->pgs[0], NULL); up_read(&current->mm->mmap_sem);

1. Change vfio from get_user_pages_remote(), to pin_user_pages_remote().

2. Because all FOLL_PIN-acquired pages must be released via put_user_page(), also convert the put_page() call over to put_user_pages_dirty_lock().

Note that this effectively changes the code's behavior in vfio_iommu_type1.c: put_pfn(): it now ultimately calls set_page_dirty_lock(), instead of set_page_dirty(). This is probably more accurate.

As Christoph Hellwig put it, "set_page_dirty() is only safe if we are dealing with a file backed page where we have reference on the inode it hangs off." [1]

[1] https://lore.kernel.org/r/20190723153640.GB720@lst.de

Tested-by: Alex Williamson alex.williamson@redhat.com Acked-by: Alex Williamson alex.williamson@redhat.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- drivers/vfio/vfio_iommu_type1.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index b800fc9a0251..18bfc2fc8e6d 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -309,9 +309,8 @@ static int put_pfn(unsigned long pfn, int prot) { if (!is_invalid_reserved_pfn(pfn)) { struct page *page = pfn_to_page(pfn); - if (prot & IOMMU_WRITE) - SetPageDirty(page); - put_page(page); + + put_user_pages_dirty_lock(&page, 1, prot & IOMMU_WRITE); return 1; } return 0; @@ -329,7 +328,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, flags |= FOLL_WRITE;

down_read(&mm->mmap_sem); - ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM, + ret = pin_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM, page, NULL, NULL); if (ret == 1) { *pfn = page_to_pfn(page[0]);

In order to provide a clearer, more symmetric API for pinning and unpinning DMA pages. This way, pin_user_pages*() calls match up with unpin_user_pages*() calls, and the API is a lot closer to being self-explanatory.

Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: John Hubbard jhubbard@nvidia.com --- Documentation/core-api/pin_user_pages.rst | 2 +- arch/powerpc/mm/book3s64/iommu_api.c | 4 +-- drivers/gpu/drm/via/via_dmablit.c | 4 +-- drivers/infiniband/core/umem.c | 2 +- drivers/infiniband/hw/hfi1/user_pages.c | 2 +- drivers/infiniband/hw/mthca/mthca_memfree.c | 6 ++-- drivers/infiniband/hw/qib/qib_user_pages.c | 2 +- drivers/infiniband/hw/qib/qib_user_sdma.c | 6 ++-- drivers/infiniband/hw/usnic/usnic_uiom.c | 2 +- drivers/infiniband/sw/siw/siw_mem.c | 2 +- drivers/media/v4l2-core/videobuf-dma-sg.c | 4 +-- drivers/platform/goldfish/goldfish_pipe.c | 4 +-- drivers/vfio/vfio_iommu_type1.c | 2 +- fs/io_uring.c | 4 +-- include/linux/mm.h | 26 ++++++++--------- mm/gup.c | 32 ++++++++++----------- mm/process_vm_access.c | 4 +-- net/xdp/xdp_umem.c | 2 +- 18 files changed, 55 insertions(+), 55 deletions(-)

diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst index 4f26637a5005..bba96428ade7 100644 --- a/Documentation/core-api/pin_user_pages.rst +++ b/Documentation/core-api/pin_user_pages.rst @@ -220,7 +220,7 @@ since the system was booted, via two new /proc/vmstat entries: :: /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 +because there is a noticeable performance drop in unpin_user_page(), when they are activated.

References diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c index fc1670a6fc3c..b965a0dfd4a2 100644 --- a/arch/powerpc/mm/book3s64/iommu_api.c +++ b/arch/powerpc/mm/book3s64/iommu_api.c @@ -168,7 +168,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,

free_exit: /* free the references taken */ - put_user_pages(mem->hpages, pinned); + unpin_user_pages(mem->hpages, pinned);

vfree(mem->hpas); kfree(mem); @@ -211,7 +211,7 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem) if (!page) continue;

- put_user_pages_dirty_lock(&page, 1, + unpin_user_pages_dirty_lock(&page, 1, mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY);

mem->hpas[i] = 0; diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c index 37c5e572993a..719d036c9384 100644 --- a/drivers/gpu/drm/via/via_dmablit.c +++ b/drivers/gpu/drm/via/via_dmablit.c @@ -188,8 +188,8 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg) kfree(vsg->desc_pages); /* fall through */ case dr_via_pages_locked: - put_user_pages_dirty_lock(vsg->pages, vsg->num_pages, - (vsg->direction == DMA_FROM_DEVICE)); + unpin_user_pages_dirty_lock(vsg->pages, vsg->num_pages, + (vsg->direction == DMA_FROM_DEVICE)); /* fall through */ case dr_via_pages_alloc: vfree(vsg->pages); diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 55daefaa9b88..a6094766b6f5 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -54,7 +54,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d

for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) { page = sg_page_iter_page(&sg_iter); - put_user_pages_dirty_lock(&page, 1, umem->writable && dirty); + unpin_user_pages_dirty_lock(&page, 1, umem->writable && dirty); }

sg_free_table(&umem->sg_head); diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c index 9a94761765c0..3b505006c0a6 100644 --- a/drivers/infiniband/hw/hfi1/user_pages.c +++ b/drivers/infiniband/hw/hfi1/user_pages.c @@ -118,7 +118,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np void hfi1_release_user_pages(struct mm_struct *mm, struct page **p, size_t npages, bool dirty) { - put_user_pages_dirty_lock(p, npages, dirty); + unpin_user_pages_dirty_lock(p, npages, dirty);

if (mm) { /* during close after signal, mm can be NULL */ atomic64_sub(npages, &mm->pinned_vm); diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c index 8269ab040c21..78a48aea3faf 100644 --- a/drivers/infiniband/hw/mthca/mthca_memfree.c +++ b/drivers/infiniband/hw/mthca/mthca_memfree.c @@ -482,7 +482,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,

ret = pci_map_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE); if (ret < 0) { - put_user_page(pages[0]); + unpin_user_page(pages[0]); goto out; }

@@ -490,7 +490,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar, mthca_uarc_virt(dev, uar, i)); if (ret) { pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE); - put_user_page(sg_page(&db_tab->page[i].mem)); + unpin_user_page(sg_page(&db_tab->page[i].mem)); goto out; }

@@ -556,7 +556,7 @@ void mthca_cleanup_user_db_tab(struct mthca_dev *dev, struct mthca_uar *uar, if (db_tab->page[i].uvirt) { mthca_UNMAP_ICM(dev, mthca_uarc_virt(dev, uar, i), 1); pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE); - put_user_page(sg_page(&db_tab->page[i].mem)); + unpin_user_page(sg_page(&db_tab->page[i].mem)); } }

diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c index 7fc4b5f81fcd..342e3172ca40 100644 --- a/drivers/infiniband/hw/qib/qib_user_pages.c +++ b/drivers/infiniband/hw/qib/qib_user_pages.c @@ -40,7 +40,7 @@ static void __qib_release_user_pages(struct page **p, size_t num_pages, int dirty) { - put_user_pages_dirty_lock(p, num_pages, dirty); + unpin_user_pages_dirty_lock(p, num_pages, dirty); }

/** diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c index 1a3cc2957e3a..a67599b5a550 100644 --- a/drivers/infiniband/hw/qib/qib_user_sdma.c +++ b/drivers/infiniband/hw/qib/qib_user_sdma.c @@ -317,7 +317,7 @@ static int qib_user_sdma_page_to_frags(const struct qib_devdata *dd, * the caller can ignore this page. */ if (put) { - put_user_page(page); + unpin_user_page(page); } else { /* coalesce case */ kunmap(page); @@ -631,7 +631,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev, kunmap(pkt->addr[i].page);

if (pkt->addr[i].put_page) - put_user_page(pkt->addr[i].page); + unpin_user_page(pkt->addr[i].page); else __free_page(pkt->addr[i].page); } else if (pkt->addr[i].kvaddr) { @@ -706,7 +706,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd, /* if error, return all pages not managed by pkt */ free_pages: while (i < j) - put_user_page(pages[i++]); + unpin_user_page(pages[i++]);

done: return ret; diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index 600896727d34..bd9f944b68fc 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -75,7 +75,7 @@ static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty) for_each_sg(chunk->page_list, sg, chunk->nents, i) { page = sg_page(sg); pa = sg_phys(sg); - put_user_pages_dirty_lock(&page, 1, dirty); + unpin_user_pages_dirty_lock(&page, 1, dirty); usnic_dbg("pa: %pa\n", &pa); } kfree(chunk); diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c index e53b07dcfed5..e2061dc0b043 100644 --- a/drivers/infiniband/sw/siw/siw_mem.c +++ b/drivers/infiniband/sw/siw/siw_mem.c @@ -63,7 +63,7 @@ struct siw_mem *siw_mem_id2obj(struct siw_device *sdev, int stag_index) static void siw_free_plist(struct siw_page_chunk *chunk, int num_pages, bool dirty) { - put_user_pages_dirty_lock(chunk->plist, num_pages, dirty); + unpin_user_pages_dirty_lock(chunk->plist, num_pages, dirty); }

void siw_umem_release(struct siw_umem *umem, bool dirty) diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c index 162a2633b1e3..13b65ed9e74c 100644 --- a/drivers/media/v4l2-core/videobuf-dma-sg.c +++ b/drivers/media/v4l2-core/videobuf-dma-sg.c @@ -349,8 +349,8 @@ int videobuf_dma_free(struct videobuf_dmabuf *dma) BUG_ON(dma->sglen);

if (dma->pages) { - put_user_pages_dirty_lock(dma->pages, dma->nr_pages, - dma->direction == DMA_FROM_DEVICE); + unpin_user_pages_dirty_lock(dma->pages, dma->nr_pages, + dma->direction == DMA_FROM_DEVICE); kfree(dma->pages); dma->pages = NULL; } diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c index 2a5901efecde..1ab207ec9c94 100644 --- a/drivers/platform/goldfish/goldfish_pipe.c +++ b/drivers/platform/goldfish/goldfish_pipe.c @@ -360,8 +360,8 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe,

*consumed_size = pipe->command_buffer->rw_params.consumed_size;

- put_user_pages_dirty_lock(pipe->pages, pages_count, - !is_write && *consumed_size > 0); + unpin_user_pages_dirty_lock(pipe->pages, pages_count, + !is_write && *consumed_size > 0);

mutex_unlock(&pipe->lock); return 0; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 18bfc2fc8e6d..a177bf2c6683 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -310,7 +310,7 @@ static int put_pfn(unsigned long pfn, int prot) if (!is_invalid_reserved_pfn(pfn)) { struct page *page = pfn_to_page(pfn);

- put_user_pages_dirty_lock(&page, 1, prot & IOMMU_WRITE); + unpin_user_pages_dirty_lock(&page, 1, prot & IOMMU_WRITE); return 1; } return 0; diff --git a/fs/io_uring.c b/fs/io_uring.c index 9639ebc21e8a..f5a378251995 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4400,7 +4400,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) struct io_mapped_ubuf *imu = &ctx->user_bufs[i];

for (j = 0; j < imu->nr_bvecs; j++) - put_user_page(imu->bvec[j].bv_page); + unpin_user_page(imu->bvec[j].bv_page);

if (ctx->account_mem) io_unaccount_mem(ctx->user, imu->nr_bvecs); @@ -4545,7 +4545,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, * release any pages we did get */ if (pret > 0) - put_user_pages(pages, pret); + unpin_user_pages(pages, pret); if (ctx->account_mem) io_unaccount_mem(ctx->user, nr_pages); kvfree(imu->bvec); diff --git a/include/linux/mm.h b/include/linux/mm.h index 0fb9929e00af..6a1a357e7d86 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1045,27 +1045,27 @@ static inline void put_page(struct page *page) }

/** - * put_user_page() - release a gup-pinned page + * unpin_user_page() - release a gup-pinned page * @page: pointer to page to be released * * Pages that were pinned via pin_user_pages*() must be released via either - * put_user_page(), or one of the put_user_pages*() routines. This is so that - * eventually such pages can be separately tracked and uniquely handled. In + * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so + * that eventually such pages can be separately tracked and uniquely handled. In * particular, interactions with RDMA and filesystems need special handling. * - * put_user_page() and put_page() are not interchangeable, despite this early - * implementation that makes them look the same. put_user_page() calls must + * unpin_user_page() and put_page() are not interchangeable, despite this early + * implementation that makes them look the same. unpin_user_page() calls must * be perfectly matched up with pin*() calls. */ -static inline void put_user_page(struct page *page) +static inline void unpin_user_page(struct page *page) { put_page(page); }

-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages, - bool make_dirty); +void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, + bool make_dirty);

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

#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS @@ -2595,7 +2595,7 @@ 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() */ +#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */

/* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each @@ -2630,7 +2630,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * 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(). + * a call to unpin_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 @@ -2638,7 +2638,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. * - * FOLL_PIN: pin_user_pages*() to acquire, and put_user_pages to release. + * FOLL_PIN: pin_user_pages*() to acquire, and unpin_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 @@ -2648,7 +2648,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * FOLL_PIN should be set internally by the pin_user_pages*() 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(). + * while pin_user_pages*() pages must be released via unpin_user_page(). * * Please see Documentation/vm/pin_user_pages.rst for more information. */ diff --git a/mm/gup.c b/mm/gup.c index 4862ff982bc3..73aedcefa4bd 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -52,7 +52,7 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) }

/** - * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages + * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages * @pages: array of pages to be maybe marked dirty, and definitely released. * @npages: number of pages in the @pages array. * @make_dirty: whether to mark the pages dirty @@ -62,19 +62,19 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) * * For each page in the @pages array, make that page (or its head page, if a * compound page) dirty, if @make_dirty is true, and if the page was previously - * listed as clean. In any case, releases all pages using put_user_page(), - * possibly via put_user_pages(), for the non-dirty case. + * listed as clean. In any case, releases all pages using unpin_user_page(), + * possibly via unpin_user_pages(), for the non-dirty case. * - * Please see the put_user_page() documentation for details. + * Please see the unpin_user_page() documentation for details. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: - * set_page_dirty_lock(), put_user_page(). + * set_page_dirty_lock(), unpin_user_page(). * */ -void put_user_pages_dirty_lock(struct page **pages, unsigned long npages, - bool make_dirty) +void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, + bool make_dirty) { unsigned long index;

@@ -85,7 +85,7 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages, */

if (!make_dirty) { - put_user_pages(pages, npages); + unpin_user_pages(pages, npages); return; }

@@ -113,21 +113,21 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages, */ if (!PageDirty(page)) set_page_dirty_lock(page); - put_user_page(page); + unpin_user_page(page); } } -EXPORT_SYMBOL(put_user_pages_dirty_lock); +EXPORT_SYMBOL(unpin_user_pages_dirty_lock);

/** - * put_user_pages() - release an array of gup-pinned pages. + * unpin_user_pages() - release an array of gup-pinned pages. * @pages: array of pages to be marked dirty and released. * @npages: number of pages in the @pages array. * - * For each page in the @pages array, release the page using put_user_page(). + * For each page in the @pages array, release the page using unpin_user_page(). * - * Please see the put_user_page() documentation for details. + * Please see the unpin_user_page() documentation for details. */ -void put_user_pages(struct page **pages, unsigned long npages) +void unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long index;

@@ -137,9 +137,9 @@ void put_user_pages(struct page **pages, unsigned long npages) * single operation to the head page should suffice. */ for (index = 0; index < npages; index++) - put_user_page(pages[index]); + unpin_user_page(pages[index]); } -EXPORT_SYMBOL(put_user_pages); +EXPORT_SYMBOL(unpin_user_pages);

#ifdef CONFIG_MMU static struct page *no_page_table(struct vm_area_struct *vma, diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index fd20ab675b85..de41e830cdac 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -126,8 +126,8 @@ static int process_vm_rw_single_vec(unsigned long addr, pa += pinned_pages * PAGE_SIZE;

/* If vm_write is set, the pages need to be made dirty: */ - put_user_pages_dirty_lock(process_pages, pinned_pages, - vm_write); + unpin_user_pages_dirty_lock(process_pages, pinned_pages, + vm_write); }

return rc; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index d071003b5e76..ac182c38f7b0 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -212,7 +212,7 @@ static int xdp_umem_map_pages(struct xdp_umem *umem)

static void xdp_umem_unpin_pages(struct xdp_umem *umem) { - put_user_pages_dirty_lock(umem->pgs, umem->npgs, true); + unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);

kfree(umem->pgs); umem->pgs = NULL;

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 unpin_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], [2], and [3].

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

[1] Some slow progress on get_user_pages() (Apr 2, 2019): https://lwn.net/Articles/784574/ [2] DMA and get_user_pages() (LPC: Dec 12, 2018): https://lwn.net/Articles/774411/ [3] The trouble with get_user_pages() (Apr 30, 2018): https://lwn.net/Articles/753027/

Suggested-by: Jan Kara jack@suse.cz Suggested-by: Jérôme Glisse jglisse@redhat.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- Documentation/core-api/pin_user_pages.rst | 2 +- include/linux/mm.h | 73 ++++- include/linux/mmzone.h | 2 + include/linux/page_ref.h | 10 + mm/gup.c | 338 +++++++++++++++++----- mm/huge_memory.c | 23 +- mm/hugetlb.c | 15 +- mm/vmstat.c | 2 + 8 files changed, 362 insertions(+), 103 deletions(-)

diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst index bba96428ade7..6d93ef203561 100644 --- a/Documentation/core-api/pin_user_pages.rst +++ b/Documentation/core-api/pin_user_pages.rst @@ -53,7 +53,7 @@ Which flags are set by each wrapper For these pin_user_pages*() functions, FOLL_PIN is OR'd in with whatever gup flags the caller provides. The caller is required to pass in a non-null struct pages* array, and the function then pin pages by incrementing each by a special -value. For now, that value is +1, just like get_user_pages*().:: +value: GUP_PIN_COUNTING_BIAS.::

Function -------- diff --git a/include/linux/mm.h b/include/linux/mm.h index 6a1a357e7d86..9666989d2b9e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1016,6 +1016,8 @@ static inline void get_page(struct page *page) page_ref_inc(page); }

+void grab_page(struct page *page, unsigned int flags); + static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); @@ -1044,29 +1046,70 @@ static inline void put_page(struct page *page) __put_page(page); }

-/** - * unpin_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 pin_user_pages() calls were + * made against the page. ("gup-pinned" is another term for the latter). + * + * With this scheme, pin_user_pages() becomes special: such pages are marked as + * distinct from normal pages. As such, the unpin_user_page() call (and its + * variants) must be used in order to release gup-pinned pages. + * + * Choice of value: * - * Pages that were pinned via pin_user_pages*() must be released via either - * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so - * that eventually such 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 pin_user_pages() and unpin_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). * - * unpin_user_page() and put_page() are not interchangeable, despite this early - * implementation that makes them look the same. unpin_user_page() calls must - * be perfectly matched up with pin*() 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 unpin_user_page(struct page *page) -{ - put_page(page); -} +#define GUP_PIN_COUNTING_BIAS (1UL << 10)

+void unpin_user_page(struct page *page); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); - void unpin_user_pages(struct page **pages, unsigned long npages);

+/** + * page_dma_pinned() - report if a page is pinned for DMA. + * + * This function checks if a page has been pinned via a call to + * pin_user_pages*(). + * + * The return value is partially fuzzy: false is not fuzzy, because it means + * "definitely not pinned for DMA", but true means "probably pinned for DMA, but + * possibly a false positive due to having at least GUP_PIN_COUNTING_BIAS worth + * of normal page references". + * + * False positives are OK, because: a) it's unlikely for a page to get that many + * refcounts, and b) all the callers of this routine are expected to be able to + * deal gracefully with a false positive. + * + * For more information, please see Documentation/vm/pin_user_pages.rst. + * + * @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. + */ +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/include/linux/mmzone.h b/include/linux/mmzone.h index 89d8ff06c9ce..a7418f7a44da 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -244,6 +244,8 @@ enum node_stat_item { NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ + NR_FOLL_PIN_REQUESTED, /* via: pin_user_page(), gup flag: FOLL_PIN */ + NR_FOLL_PIN_RETURNED, /* pages returned via unpin_user_page() */ NR_VM_NODE_STAT_ITEMS };

diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 14d14beb1f7f..b9cbe553d1e7 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -102,6 +102,16 @@ static inline void page_ref_sub(struct page *page, int nr) __page_ref_mod(page, -nr); }

+static inline int page_ref_sub_return(struct page *page, int nr) +{ + int ret = atomic_sub_return(nr, &page->_refcount); + + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + __page_ref_mod(page, -nr); + + return ret; +} + static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); diff --git a/mm/gup.c b/mm/gup.c index 687d48506f04..45fe923e28e2 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -36,6 +36,20 @@ static __always_inline long __gup_longterm_locked(struct task_struct *tsk, struct page **pages, struct vm_area_struct **vmas, unsigned int flags); + +#ifdef CONFIG_DEBUG_VM +static inline void __update_proc_vmstat(struct page *page, + enum node_stat_item item, int count) +{ + mod_node_page_state(page_pgdat(page), item, count); +} +#else +static inline void __update_proc_vmstat(struct page *page, + enum node_stat_item item, int count) +{ +} +#endif + /* * Return the compound head page with ref appropriately incremented, * or NULL if that failed. @@ -51,6 +65,138 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) return head; }

+/** + * try_pin_compound_head() - mark a compound page as being used by + * pin_user_pages*(). + * + * This is the FOLL_PIN counterpart to try_get_compound_head(). + * + * @page: pointer to page to be marked + * @Return: the compound head page, with ref appropriately incremented, + * or NULL upon failure. + */ +__must_check struct page *try_pin_compound_head(struct page *page, int refs) +{ + struct page *head = try_get_compound_head(page, + GUP_PIN_COUNTING_BIAS * refs); + if (!head) + return NULL; + + __update_proc_vmstat(page, NR_FOLL_PIN_REQUESTED, refs); + return head; +} + +/* + * try_grab_compound_head() - attempt to elevate a page's refcount, by a + * flags-dependent amount. + * + * This has a default assumption of "use FOLL_GET behavior, if FOLL_PIN is not + * set". + * + * "grab" names in this file mean, "look at flags to decide with to use FOLL_PIN + * or FOLL_GET behavior, when incrementing the page's refcount. + */ +static struct page *try_grab_compound_head(struct page *page, int refs, + unsigned int flags) +{ + if (flags & FOLL_PIN) + return try_pin_compound_head(page, refs); + + return try_get_compound_head(page, refs); +} + +/** + * grab_page() - elevate a page's refcount by a flag-dependent amount + * + * This might not do anything at all, depending on the flags argument. + * + * "grab" names in this file mean, "look at flags to decide with to use FOLL_PIN + * or FOLL_GET behavior, when incrementing the page's refcount. + * + * @page: pointer to page to be grabbed + * @flags: gup flags: these are the FOLL_* flag values. + * + * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same + * time. (That's true throughout the get_user_pages*() and pin_user_pages*() + * APIs.) Cases: + * + * FOLL_GET: page's refcount will be incremented by 1. + * FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS. + */ +void grab_page(struct page *page, unsigned int flags) +{ + if (flags & FOLL_GET) + get_page(page); + else if (flags & FOLL_PIN) { + get_page(page); + WARN_ON_ONCE(flags & FOLL_GET); + /* + * Use get_page(), above, to do the refcount error + * checking. Then just add in the remaining references: + */ + page_ref_add(page, GUP_PIN_COUNTING_BIAS - 1); + __update_proc_vmstat(page, NR_FOLL_PIN_REQUESTED, 1); + } +} + +#ifdef CONFIG_DEV_PAGEMAP_OPS +static bool __unpin_devmap_managed_user_page(struct page *page) +{ + bool is_devmap = page_is_devmap_managed(page); + + if (is_devmap) { + int count = page_ref_sub_return(page, GUP_PIN_COUNTING_BIAS); + + __update_proc_vmstat(page, NR_FOLL_PIN_RETURNED, 1); + /* + * devmap page refcounts are 1-based, rather than 0-based: if + * refcount is 1, then the page is free and the refcount is + * stable because nobody holds a reference on the page. + */ + if (count == 1) + free_devmap_managed_page(page); + else if (!count) + __put_page(page); + } + + return is_devmap; +} +#else +static bool __unpin_devmap_managed_user_page(struct page *page) +{ + return false; +} +#endif /* CONFIG_DEV_PAGEMAP_OPS */ + +/** + * unpin_user_page() - release a dma-pinned page + * @page: pointer to page to be released + * + * Pages that were pinned via pin_user_pages*() must be released via either + * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so + * that such pages can be separately tracked and uniquely handled. In + * particular, interactions with RDMA and filesystems need special handling. + */ +void unpin_user_page(struct page *page) +{ + page = compound_head(page); + + /* + * For devmap managed pages we need to catch refcount transition from + * GUP_PIN_COUNTING_BIAS to 1, when refcount reach one it means the + * page is free and we need to inform the device driver through + * callback. See include/linux/memremap.h and HMM for details. + */ + if (__unpin_devmap_managed_user_page(page)) + return; + + if (page_ref_sub_and_test(page, GUP_PIN_COUNTING_BIAS)) + __put_page(page); + + __update_proc_vmstat(page, NR_FOLL_PIN_RETURNED, 1); +} +EXPORT_SYMBOL(unpin_user_page); + /** * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages * @pages: array of pages to be maybe marked dirty, and definitely released. @@ -237,10 +383,11 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, }

page = vm_normal_page(vma, address, pte); - if (!page && pte_devmap(pte) && (flags & FOLL_GET)) { + if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* - * Only return device mapping pages in the FOLL_GET case since - * they are only valid while holding the pgmap reference. + * Only return device mapping pages in the FOLL_GET or FOLL_PIN + * case since they are only valid while holding the pgmap + * reference. */ *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); if (*pgmap) @@ -278,11 +425,23 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, goto retry; }

- if (flags & FOLL_GET) { + if (flags & (FOLL_PIN | FOLL_GET)) { + /* + * Allow try_get_page() to take care of error handling, for + * both cases: FOLL_GET or FOLL_PIN: + */ if (unlikely(!try_get_page(page))) { page = ERR_PTR(-ENOMEM); goto out; } + + if (flags & FOLL_PIN) { + WARN_ON_ONCE(flags & FOLL_GET); + + /* We got a +1 refcount from try_get_page(), above. */ + page_ref_add(page, GUP_PIN_COUNTING_BIAS - 1); + __update_proc_vmstat(page, NR_FOLL_PIN_REQUESTED, 1); + } } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && @@ -544,8 +703,8 @@ static struct page *follow_page_mask(struct vm_area_struct *vma, /* make this handle hugepd */ page = follow_huge_addr(mm, address, flags & FOLL_WRITE); if (!IS_ERR(page)) { - BUG_ON(flags & FOLL_GET); - return page; + WARN_ON_ONCE(flags & (FOLL_GET | FOLL_PIN)); + return NULL; }

pgd = pgd_offset(mm, address); @@ -1131,6 +1290,36 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, return pages_done; }

+static 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) +{ + /* + * Parts of FOLL_LONGTERM behavior are incompatible with + * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on + * vmas. However, this only comes up if locked is set, and there are + * callers that do request FOLL_LONGTERM, but do not set locked. So, + * allow what we can. + */ + if (gup_flags & FOLL_LONGTERM) { + if (WARN_ON_ONCE(locked)) + return -EINVAL; + /* + * This will check the vmas (even if our vmas arg is NULL) + * and return -ENOTSUPP if DAX isn't allowed in this case: + */ + return __gup_longterm_locked(tsk, mm, start, nr_pages, pages, + vmas, gup_flags | FOLL_TOUCH | + FOLL_REMOTE); + } + + return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, + locked, + gup_flags | FOLL_TOUCH | FOLL_REMOTE); +} + /* * get_user_pages_remote() - pin user pages in memory * @tsk: the task_struct to use for page fault accounting, or @@ -1205,28 +1394,8 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) return -EINVAL;

- /* - * Parts of FOLL_LONGTERM behavior are incompatible with - * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on - * vmas. However, this only comes up if locked is set, and there are - * callers that do request FOLL_LONGTERM, but do not set locked. So, - * allow what we can. - */ - if (gup_flags & FOLL_LONGTERM) { - if (WARN_ON_ONCE(locked)) - return -EINVAL; - /* - * This will check the vmas (even if our vmas arg is NULL) - * and return -ENOTSUPP if DAX isn't allowed in this case: - */ - return __gup_longterm_locked(tsk, mm, start, nr_pages, pages, - vmas, gup_flags | FOLL_TOUCH | - FOLL_REMOTE); - } - - return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, - locked, - gup_flags | FOLL_TOUCH | FOLL_REMOTE); + return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, + pages, vmas, locked); } EXPORT_SYMBOL(get_user_pages_remote);

@@ -1421,10 +1590,11 @@ static long __get_user_pages_locked(struct task_struct *tsk, return i ? : -EFAULT; }

-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) +static 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) { return 0; } @@ -1864,13 +2034,17 @@ static inline pte_t gup_get_pte(pte_t *ptep) #endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */

static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, + unsigned int flags, struct page **pages) { while ((*nr) - nr_start) { struct page *page = pages[--(*nr)];

ClearPageReferenced(page); - put_page(page); + if (flags & FOLL_PIN) + unpin_user_page(page); + else + put_page(page); } }

@@ -1903,7 +2077,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,

pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, pages); + undo_dev_pagemap(nr, nr_start, flags, pages); goto pte_unmap; } } else if (pte_special(pte)) @@ -1912,7 +2086,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte);

- head = try_get_compound_head(page, 1); + head = try_grab_compound_head(page, 1, flags); if (!head) goto pte_unmap;

@@ -1968,12 +2142,12 @@ 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); + grab_page(page, flags); (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); @@ -1995,7 +2169,7 @@ static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0;

if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { - undo_dev_pagemap(nr, nr_start, pages); + undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; @@ -2013,7 +2187,7 @@ static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0;

if (unlikely(pud_val(orig) != pud_val(*pudp))) { - undo_dev_pagemap(nr, nr_start, pages); + undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; @@ -2047,8 +2221,11 @@ static int record_subpages(struct page *page, unsigned long addr, return nr; }

-static void put_compound_head(struct page *page, int refs) +static void put_compound_head(struct page *page, int refs, unsigned int flags) { + if (flags & FOLL_PIN) + refs *= GUP_PIN_COUNTING_BIAS; + /* Do a get_page() first, in case refs == page->_refcount */ get_page(page); page_ref_sub(page, refs); @@ -2088,12 +2265,12 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, page = head + ((addr & (sz-1)) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr);

- head = try_get_compound_head(head, refs); + head = try_grab_compound_head(head, refs, flags); if (!head) return 0;

if (unlikely(pte_val(pte) != pte_val(*ptep))) { - put_compound_head(head, refs); + put_compound_head(head, refs, flags); return 0; }

@@ -2148,12 +2325,12 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr);

- head = try_get_compound_head(pmd_page(orig), refs); + head = try_grab_compound_head(pmd_page(orig), refs, flags); if (!head) return 0;

if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { - put_compound_head(head, refs); + put_compound_head(head, refs, flags); return 0; }

@@ -2182,12 +2359,12 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr);

- head = try_get_compound_head(pud_page(orig), refs); + head = try_grab_compound_head(pud_page(orig), refs, flags); if (!head) return 0;

if (unlikely(pud_val(orig) != pud_val(*pudp))) { - put_compound_head(head, refs); + put_compound_head(head, refs, flags); return 0; }

@@ -2211,12 +2388,12 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); refs = record_subpages(page, addr, end, pages + *nr);

- head = try_get_compound_head(pgd_page(orig), refs); + head = try_grab_compound_head(pgd_page(orig), refs, flags); if (!head) return 0;

if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { - put_compound_head(head, refs); + put_compound_head(head, refs, flags); return 0; }

@@ -2517,9 +2694,12 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast); /** * pin_user_pages_fast() - pin user pages in memory without taking locks * - * For now, this is a placeholder function, until various call sites are - * converted to use the correct get_user_pages*() or pin_user_pages*() API. So, - * this is identical to get_user_pages_fast(). + * 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 unpin_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). @@ -2527,21 +2707,24 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { - /* - * This is a placeholder, until the pin functionality is activated. - * Until then, just behave like the corresponding get_user_pages*() - * routine. - */ - return get_user_pages_fast(start, nr_pages, gup_flags, 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_user_pages_remote() - pin pages of a remote process (task != current) * - * For now, this is a placeholder function, until various call sites are - * converted to use the correct get_user_pages*() or pin_user_pages*() API. So, - * this is identical to get_user_pages_remote(). + * 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 unpin_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). @@ -2551,22 +2734,24 @@ long pin_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) { - /* - * This is a placeholder, until the pin functionality is activated. - * Until then, just behave like the corresponding get_user_pages*() - * routine. - */ - return get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, pages, - vmas, locked); + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, + pages, vmas, locked); } EXPORT_SYMBOL(pin_user_pages_remote);

/** * pin_user_pages() - pin user pages in memory for use by other devices * - * For now, this is a placeholder function, until various call sites are - * converted to use the correct get_user_pages*() or pin_user_pages*() API. So, - * this is identical to get_user_pages(). + * 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 unpin_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). @@ -2575,11 +2760,12 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas) { - /* - * This is a placeholder, until the pin functionality is activated. - * Until then, just behave like the corresponding get_user_pages*() - * routine. - */ - return get_user_pages(start, nr_pages, gup_flags, pages, 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); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 41a0fbddc96b..4e04a6aee8a6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -945,6 +945,11 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, */ WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");

+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == + (FOLL_PIN | FOLL_GET))) + return NULL; + if (flags & FOLL_WRITE && !pmd_write(*pmd)) return NULL;

@@ -960,7 +965,7 @@ struct page *follow_devmap_pmd(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);

pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; @@ -968,7 +973,7 @@ 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); + grab_page(page, flags);

return page; } @@ -1088,6 +1093,11 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, if (flags & FOLL_WRITE && !pud_write(*pud)) return NULL;

+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == + (FOLL_PIN | FOLL_GET))) + return NULL; + if (pud_present(*pud) && pud_devmap(*pud)) /* pass */; else @@ -1099,8 +1109,10 @@ 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. + * + * At least one of FOLL_GET | FOLL_PIN must be set, so assert that here: */ - if (!(flags & FOLL_GET)) + if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST);

pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; @@ -1108,7 +1120,7 @@ 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); + grab_page(page, flags);

return page; } @@ -1522,8 +1534,7 @@ 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); + grab_page(page, flags);

out: return page; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ac65bb5e38ac..84844ec4ac8b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4356,7 +4356,7 @@ 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]); + grab_page(pages[i], flags); }

if (vmas) @@ -4916,6 +4916,12 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, struct page *page = NULL; spinlock_t *ptl; pte_t pte; + + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == + (FOLL_PIN | FOLL_GET))) + return NULL; + retry: ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); @@ -4928,8 +4934,7 @@ 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); + grab_page(page, flags); } else { if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); @@ -4950,7 +4955,7 @@ struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags) { - if (flags & FOLL_GET) + if (flags & (FOLL_GET | FOLL_PIN)) return NULL;

return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); @@ -4959,7 +4964,7 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address, struct page * __weak follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags) { - if (flags & FOLL_GET) + if (flags & (FOLL_GET | FOLL_PIN)) return NULL;

return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT); diff --git a/mm/vmstat.c b/mm/vmstat.c index 78d53378db99..b56808bae1b4 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1168,6 +1168,8 @@ const char * const vmstat_text[] = { "nr_dirtied", "nr_written", "nr_kernel_misc_reclaimable", + "nr_foll_pin_requested", + "nr_foll_pin_returned",

/* enum writeback_stat_item counters */ "nr_dirty_threshold",

It's good to have basic unit test coverage of the new FOLL_PIN behavior. Fortunately, the gup_benchmark unit test is extremely fast (a few milliseconds), so adding it the the run_vmtests suite is going to cause no noticeable change in running time.

So, add two new invocations to run_vmtests:

1) Run gup_benchmark with normal get_user_pages().

2) Run gup_benchmark with pin_user_pages(). This is much like the first call, except that it sets FOLL_PIN.

Running these two in quick succession also provide a visual comparison of the running times, which is convenient.

The new invocations are fairly early in the run_vmtests script, because with test suites, it's usually preferable to put the shorter, faster tests first, all other things being equal.

Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- tools/testing/selftests/vm/run_vmtests | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+)

diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index a692ea828317..df6a6bf3f238 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -112,6 +112,28 @@ echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" echo " hugetlb regression testing."

+echo "--------------------------------------------" +echo "running 'gup_benchmark -U' (normal/slow gup)" +echo "--------------------------------------------" +./gup_benchmark -U +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + +echo "------------------------------------------" +echo "running gup_benchmark -b (pin_user_pages)" +echo "------------------------------------------" +./gup_benchmark -b +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "-------------------" echo "running userfaultfd" echo "-------------------"