An upcoming patch uses try_get_compound_head() more widely, so move it to the top of gup.c.

Also fix a tiny spelling error and a checkpatch.pl warning.

Signed-off-by: John Hubbard jhubbard@nvidia.com --- mm/gup.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index 199da99e8ffc..933524de6249 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -29,6 +29,21 @@ struct follow_page_context { unsigned int page_mask; };

+/* + * Return the compound head page with ref appropriately incremented, + * or NULL if that failed. + */ +static inline struct page *try_get_compound_head(struct page *page, int refs) +{ + struct page *head = compound_head(page); + + if (WARN_ON_ONCE(page_ref_count(head) < 0)) + return NULL; + if (unlikely(!page_cache_add_speculative(head, refs))) + return NULL; + return head; +} + /** * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages * @pages: array of pages to be maybe marked dirty, and definitely released. @@ -1793,20 +1808,6 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, } }

-/* - * Return the compund head page with ref appropriately incremented, - * or NULL if that failed. - */ -static inline struct page *try_get_compound_head(struct page *page, int refs) -{ - struct page *head = compound_head(page); - if (WARN_ON_ONCE(page_ref_count(head) < 0)) - return NULL; - if (unlikely(!page_cache_add_speculative(head, refs))) - return NULL; - return head; -} - #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr)

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

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

Reviewed-by: 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..7ed2a21a0bac 100644 --- a/drivers/platform/goldfish/goldfish_pipe.c +++ b/drivers/platform/goldfish/goldfish_pipe.c @@ -257,12 +257,12 @@ static int goldfish_pipe_error_convert(int status) } }

-static int pin_user_pages(unsigned long first_page, - unsigned long last_page, - unsigned int last_page_size, - int is_write, - struct page *pages[MAX_BUFFERS_PER_COMMAND], - unsigned int *iter_last_page_size) +static int pin_goldfish_pages(unsigned long first_page, + unsigned long last_page, + unsigned int last_page_size, + int is_write, + struct page *pages[MAX_BUFFERS_PER_COMMAND], + unsigned int *iter_last_page_size) { int ret; int requested_pages = ((last_page - first_page) >> PAGE_SHIFT) + 1; @@ -354,9 +354,9 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe, if (mutex_lock_interruptible(&pipe->lock)) return -ERESTARTSYS;

- pages_count = pin_user_pages(first_page, last_page, - last_page_size, is_write, - pipe->pages, &iter_last_page_size); + pages_count = pin_goldfish_pages(first_page, last_page, + last_page_size, is_write, + pipe->pages, &iter_last_page_size); if (pages_count < 0) { mutex_unlock(&pipe->lock); return pages_count;

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

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

Acked-by: Hans Verkuil hverkuil-cisco@xs4all.nl Cc: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: John Hubbard jhubbard@nvidia.com --- drivers/media/v4l2-core/videobuf-dma-sg.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

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

if (dma->pages) { - for (i = 0; i < dma->nr_pages; i++) + for (i = 0; i < dma->nr_pages; i++) { + if (dma->direction == DMA_FROM_DEVICE) + set_page_dirty_lock(dma->pages[i]); put_page(dma->pages[i]); + } kfree(dma->pages); dma->pages = NULL; }

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

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

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

pin_user_pages() pin_user_pages_remote() pin_user_pages_fast()

pin_longterm_pages() pin_longterm_pages_remote() pin_longterm_pages_fast()

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

The underlying rules are:

* These are gup-internal flags, so the call sites should not directly set FOLL_PIN nor FOLL_LONGTERM. That behavior is enforced with assertions, for the new FOLL_PIN flag. However, for the pre-existing FOLL_LONGTERM flag, which has some call sites that still directly set FOLL_LONGTERM, there is no assertion yet.

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

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

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

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 | 218 +++++++++++++++++ include/linux/mm.h | 75 +++++- mm/gup.c | 275 ++++++++++++++++++++-- 4 files changed, 535 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..ce819e709435 --- /dev/null +++ b/Documentation/core-api/pin_user_pages.rst @@ -0,0 +1,218 @@ +.. 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 + + pin_longterm_pages + pin_longterm_pages_fast + pin_longterm_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. + +Both FOLL_PIN and FOLL_LONGTERM are internal to gup, meaning that neither +FOLL_PIN nor FOLL_LONGTERM should not appear at the gup call sites. This allows +the associated wrapper functions (pin_user_pages() and others) to set the +correct combination of these flags, and to check for problems as well. + +FOLL_PIN and FOLL_GET are mutually exclusive for a given gup call. However, +multiple threads and call sites are free to pin the same struct pages, via both +FOLL_PIN and FOLL_GET. It's just the call site that needs to choose one or the +other, not the struct page(s). + +The FOLL_PIN implementation is nearly the same as FOLL_GET, except that FOLL_PIN +uses a different reference counting technique. + +FOLL_PIN is a prerequisite to FOLL_LONGTGERM. Another way of saying that is, +FOLL_LONGTERM is a specific case, more restrictive case of FOLL_PIN. + +Which flags are set by each wrapper +=================================== + +Only FOLL_PIN and FOLL_LONGTERM are covered here. These flags are added to +whatever flags the caller provides:: + + Function gup flags (FOLL_PIN or FOLL_LONGTERM only) + -------- ------------------------------------------ + pin_user_pages FOLL_PIN + pin_user_pages_fast FOLL_PIN + pin_user_pages_remote FOLL_PIN + + pin_longterm_pages FOLL_PIN | FOLL_LONGTERM + pin_longterm_pages_fast FOLL_PIN | FOLL_LONGTERM + pin_longterm_pages_remote FOLL_PIN | FOLL_LONGTERM + +Tracking dma-pinned pages +========================= + +Some of the key design constraints, and solutions, for tracking dma-pinned +pages: + +* An actual reference count, per struct page, is required. This is because + multiple processes may pin and unpin a page. + +* False positives (reporting that a page is dma-pinned, when in fact it is not) + are acceptable, but false negatives are not. + +* struct page may not be increased in size for this, and all fields are already + used. + +* Given the above, we can overload the page->_refcount field by using, sort of, + the upper bits in that field for a dma-pinned count. "Sort of", means that, + rather than dividing page->_refcount into bit fields, we simple add a medium- + large value (GUP_PIN_COUNTING_BIAS, initially chosen to be 1024: 10 bits) to + page->_refcount. This provides fuzzy behavior: if a page has get_page() called + on it 1024 times, then it will appear to have a single dma-pinned count. + And again, that's acceptable. + +This also leads to limitations: there are only 31-10==21 bits available for a +counter that increments 10 bits at a time. + +TODO: for 1GB and larger huge pages, this is cutting it close. That's because +when pin_user_pages() follows such pages, it increments the head page by "1" +(where "1" used to mean "+1" for get_user_pages(), but now means "+1024" for +pin_user_pages()) for each tail page. So if you have a 1GB huge page: + +* There are 256K (18 bits) worth of 4 KB tail pages. +* There are 21 bits available to count up via GUP_PIN_COUNTING_BIAS (that is, + 10 bits at a time) +* There are 21 - 18 == 3 bits available to count. Except that there aren't, + because you need to allow for a few normal get_page() calls on the head page, + as well. Fortunately, the approach of using addition, rather than "hard" + bitfields, within page->_refcount, allows for sharing these bits gracefully. + But we're still looking at about 8 references. + +This, however, is a missing feature more than anything else, because it's easily +solved by addressing an obvious inefficiency in the original get_user_pages() +approach of retrieving pages: stop treating all the pages as if they were +PAGE_SIZE. Retrieve huge pages as huge pages. The callers need to be aware of +this, so some work is required. Once that's in place, this limitation mostly +disappears from view, because there will be ample refcounting range available. + +* Callers must specifically request "dma-pinned tracking of pages". In other + words, just calling get_user_pages() will not suffice; a new set of functions, + pin_user_page() and related, must be used. + +FOLL_PIN, FOLL_GET, FOLL_LONGTERM: when to use which flags +========================================================== + +Thanks to Jan Kara, Vlastimil Babka and several other -mm people, for describing +these categories: + +CASE 1: Direct IO (DIO) +----------------------- +There are GUP references to pages that are serving +as DIO buffers. These buffers are needed for a relatively short time (so they +are not "long term"). No special synchronization with page_mkclean() or +munmap() is provided. Therefore, flags to set at the call site are: :: + + FOLL_PIN + +...but rather than setting FOLL_PIN directly, call sites should use one of +the pin_user_pages*() routines that set FOLL_PIN. + +CASE 2: RDMA +------------ +There are GUP references to pages that are serving as DMA +buffers. These buffers are needed for a long time ("long term"). No special +synchronization with page_mkclean() or munmap() is provided. Therefore, flags +to set at the call site are: :: + + FOLL_PIN | FOLL_LONGTERM + +NOTE: Some pages, such as DAX pages, cannot be pinned with longterm pins. That's +because DAX pages do not have a separate page cache, and so "pinning" implies +locking down file system blocks, which is not (yet) supported in that way. + +CASE 3: 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 96228376139c..c351e1b0b4b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1075,16 +1075,15 @@ 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 either pin_user_pages*() or pin_longterm_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) { @@ -1542,9 +1541,23 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); +long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked); +long pin_longterm_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); +long pin_user_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas); +long pin_longterm_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, @@ -1552,6 +1565,10 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,

int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); +int pin_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); +int pin_longterm_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages);

int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, @@ -2610,13 +2627,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ +#define FOLL_PIN 0x40000 /* pages must be released via put_user_page() */

/* - * NOTE on FOLL_LONGTERM: + * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each + * other. Here is what they mean, and how to use them: * * FOLL_LONGTERM indicates that the page will be held for an indefinite time - * period _often_ under userspace control. This is contrasted with - * iov_iter_get_pages() where usages which are transient. + * period _often_ under userspace control. This is in contrast to + * iov_iter_get_pages(), where usages which are transient. * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm @@ -2631,11 +2650,41 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * Currently only get_user_pages() and get_user_pages_fast() support this flag * and calls to get_user_pages_[un]locked are specifically not allowed. This * is due to an incompatibility with the FS DAX check and - * FAULT_FLAG_ALLOW_RETRY + * FAULT_FLAG_ALLOW_RETRY. * - * In the CMA case: longterm pins in a CMA region would unnecessarily fragment - * that region. And so CMA attempts to migrate the page before pinning when + * In the CMA case: long term pins in a CMA region would unnecessarily fragment + * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. + * + * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, + * but an additional pin counting system) will be invoked. This is intended for + * anything that gets a page reference and then touches page data (for example, + * Direct IO). This lets the filesystem know that some non-file-system entity is + * potentially changing the pages' data. In contrast to FOLL_GET (whose pages + * are released via put_page()), FOLL_PIN pages must be released, ultimately, by + * a call to put_user_page(). + * + * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different + * and separate refcounting mechanisms, however, and that means that each has + * its own acquire and release mechanisms: + * + * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. + * + * FOLL_PIN: pin_user_pages*() or pin_longterm_pages*() to acquire, and + * put_user_pages to release. + * + * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. + * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based + * calls applied to them, and that's perfectly OK. This is a constraint on the + * callers, not on the pages.) + * + * FOLL_PIN and FOLL_LONGTERM should be set internally by the pin_user_page*() + * and pin_longterm_*() APIs, never directly by the caller. That's in order to + * help avoid mismatches when releasing pages: get_user_pages*() pages must be + * released via put_page(), while pin_user_pages*() pages must be released via + * put_user_page(). + * + * Please see Documentation/vm/pin_user_pages.rst for more information. */

static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) diff --git a/mm/gup.c b/mm/gup.c index 83702b2e86c8..4409e84dff51 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); @@ -812,7 +816,7 @@ 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 @@ -1036,7 +1040,16 @@ 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; @@ -1173,6 +1186,14 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) { + /* + * FOLL_PIN must only be set internally by the pin_user_page*() and + * pin_longterm_*() APIs, never directly by the caller, so enforce that + * with an assertion: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + return -EINVAL; + /* * Parts of FOLL_LONGTERM behavior are incompatible with * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on @@ -1640,6 +1661,14 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas) { + /* + * FOLL_PIN must only be set internally by the pin_user_page*() and + * pin_longterm_*() APIs, never directly by the caller, so enforce that + * with an assertion: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + return -EINVAL; + return __gup_longterm_locked(current, current->mm, start, nr_pages, pages, vmas, gup_flags | FOLL_TOUCH); } @@ -2391,29 +2420,14 @@ 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))) + if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_PIN))) return -EINVAL;

start = untagged_addr(start) & PAGE_MASK; @@ -2453,4 +2467,223 @@ int get_user_pages_fast(unsigned long start, int nr_pages,

return ret; } + +/** + * get_user_pages_fast() - pin user pages in memory + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @gup_flags: flags modifying pin behaviour + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. + * + * Attempt to pin user pages in memory without taking mm->mmap_sem. + * If not successful, it will fall back to taking the lock and + * calling get_user_pages(). + * + * Returns number of pages pinned. This may be fewer than the number requested. + * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns + * -errno. + */ +int get_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + /* + * FOLL_PIN must only be set internally by the pin_user_page*() and + * pin_longterm_*() APIs, never directly by the caller, so enforce that: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + return -EINVAL; + + return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); +} EXPORT_SYMBOL_GPL(get_user_pages_fast); + +/** + * pin_user_pages_fast() - pin user pages in memory without taking locks + * + * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See + * get_user_pages_fast() for documentation on the function arguments, because + * the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for further details. + * + * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It + * is NOT intended for Case 2 (RDMA: long-term pins). + */ +int pin_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); +} +EXPORT_SYMBOL_GPL(pin_user_pages_fast); + +/** + * pin_longterm_pages_fast() - pin user pages in memory without taking locks + * + * Nearly the same as get_user_pages_fast(), except that FOLL_PIN and + * FOLL_LONGTERM are set. See get_user_pages_fast() for documentation on the + * function arguments, because the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for further details. + * + * FOLL_LONGTERM means that the pages are being pinned for "long term" use, + * typically by a non-CPU device, and we cannot be sure that waiting for a + * pinned page to become unpin will be effective. + * + * This is intended for Case 2 (RDMA: long-term pins) of the FOLL_PIN + * documentation. + */ +int pin_longterm_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= (FOLL_PIN | FOLL_LONGTERM); + return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); +} +EXPORT_SYMBOL_GPL(pin_longterm_pages_fast); + +/** + * pin_user_pages_remote() - pin pages of a remote process (task != current) + * + * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See + * get_user_pages_remote() for documentation on the function arguments, because + * the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for details. + * + * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It + * is NOT intended for Case 2 (RDMA: long-term pins). + */ +long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_TOUCH | FOLL_REMOTE | FOLL_PIN; + + return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, + locked, gup_flags); +} +EXPORT_SYMBOL(pin_user_pages_remote); + +/** + * pin_longterm_pages_remote() - pin pages of a remote process (task != current) + * + * Nearly the same as get_user_pages_remote(), but note that FOLL_TOUCH is not + * set, and FOLL_PIN and FOLL_LONGTERM are set. See get_user_pages_remote() for + * documentation on the function arguments, because the arguments here are + * identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for further details. + * + * FOLL_LONGTERM means that the pages are being pinned for "long term" use, + * typically by a non-CPU device, and we cannot be sure that waiting for a + * pinned page to become unpin will be effective. + * + * This is intended for Case 2 (RDMA: long-term pins) in + * Documentation/vm/pin_user_pages.rst. + */ +long pin_longterm_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + /* + * 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 (WARN_ON_ONCE(locked)) + return -EINVAL; + + gup_flags |= FOLL_LONGTERM | FOLL_REMOTE | FOLL_PIN; + + /* + * 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); +} +EXPORT_SYMBOL(pin_longterm_pages_remote); + +/** + * pin_user_pages() - pin user pages in memory for use by other devices + * + * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and + * FOLL_PIN is set. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for details. + * + * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It + * is NOT intended for Case 2 (RDMA: long-term pins). + */ +long pin_user_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return __gup_longterm_locked(current, current->mm, start, nr_pages, + pages, vmas, gup_flags); +} +EXPORT_SYMBOL(pin_user_pages); + +/** + * pin_longterm_pages() - pin user pages in memory for long-term use (RDMA, + * typically) + * + * Nearly the same as get_user_pages(), except that FOLL_PIN and FOLL_LONGTERM + * are set. See get_user_pages_fast() for documentation on the function + * arguments, because the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for further details. + * + * FOLL_LONGTERM means that the pages are being pinned for "long term" use, + * typically by a non-CPU device, and we cannot be sure that waiting for a + * pinned page to become unpin will be effective. + * + * This is intended for Case 2 (RDMA: long-term pins) in + * Documentation/vm/pin_user_pages.rst. + */ +long pin_longterm_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN | FOLL_LONGTERM; + return __gup_longterm_locked(current, current->mm, start, nr_pages, + pages, vmas, gup_flags); +} +EXPORT_SYMBOL(pin_longterm_pages);

1. Call the new global pin_user_pages_fast(), from pin_goldfish_pages().

2. As required by pin_user_pages(), release these pages via put_user_page(). In this case, do so via put_user_pages_dirty_lock().

That has the side effect of calling 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]

Another side effect is that the release code is simplified because the page[] loop is now in gup.c instead of here, so just delete the local release_user_pages() entirely, and call put_user_pages_dirty_lock() directly, instead.

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

Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- drivers/platform/goldfish/goldfish_pipe.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-)

diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c index 7ed2a21a0bac..635a8bc1b480 100644 --- a/drivers/platform/goldfish/goldfish_pipe.c +++ b/drivers/platform/goldfish/goldfish_pipe.c @@ -274,7 +274,7 @@ static int pin_goldfish_pages(unsigned long first_page, *iter_last_page_size = last_page_size; }

- ret = get_user_pages_fast(first_page, requested_pages, + ret = pin_user_pages_fast(first_page, requested_pages, !is_write ? FOLL_WRITE : 0, pages); if (ret <= 0) @@ -285,18 +285,6 @@ static int pin_goldfish_pages(unsigned long first_page, return ret; }

-static void release_user_pages(struct page **pages, int pages_count, - int is_write, s32 consumed_size) -{ - int i; - - for (i = 0; i < pages_count; i++) { - if (!is_write && consumed_size > 0) - set_page_dirty(pages[i]); - put_page(pages[i]); - } -} - /* Populate the call parameters, merging adjacent pages together */ static void populate_rw_params(struct page **pages, int pages_count, @@ -372,7 +360,8 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe,

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

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

mutex_unlock(&pipe->lock); return 0;

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

Also, release the pages via put_user_page*().

Also, rename "pages" to "pinned_pages", as this makes for easier reading of process_vm_rw_single_vec().

Reviewed-by: Jérôme Glisse jglisse@redhat.com Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- mm/process_vm_access.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 357aa7bef6c0..fd20ab675b85 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -42,12 +42,11 @@ static int process_vm_rw_pages(struct page **pages, if (copy > len) copy = len;

- if (vm_write) { + if (vm_write) copied = copy_page_from_iter(page, offset, copy, iter); - set_page_dirty_lock(page); - } else { + else copied = copy_page_to_iter(page, offset, copy, iter); - } + len -= copied; if (copied < copy && iov_iter_count(iter)) return -EFAULT; @@ -96,7 +95,7 @@ static int process_vm_rw_single_vec(unsigned long addr, flags |= FOLL_WRITE;

while (!rc && nr_pages && iov_iter_count(iter)) { - int pages = min(nr_pages, max_pages_per_loop); + int pinned_pages = min(nr_pages, max_pages_per_loop); int locked = 1; size_t bytes;

@@ -106,14 +105,15 @@ static int process_vm_rw_single_vec(unsigned long addr, * current/current->mm */ down_read(&mm->mmap_sem); - pages = get_user_pages_remote(task, mm, pa, pages, flags, - process_pages, NULL, &locked); + pinned_pages = pin_user_pages_remote(task, mm, pa, pinned_pages, + flags, process_pages, + NULL, &locked); if (locked) up_read(&mm->mmap_sem); - if (pages <= 0) + if (pinned_pages <= 0) return -EFAULT;

- bytes = pages * PAGE_SIZE - start_offset; + bytes = pinned_pages * PAGE_SIZE - start_offset; if (bytes > len) bytes = len;

@@ -122,10 +122,12 @@ static int process_vm_rw_single_vec(unsigned long addr, vm_write); len -= bytes; start_offset = 0; - nr_pages -= pages; - pa += pages * PAGE_SIZE; - while (pages) - put_page(process_pages[--pages]); + nr_pages -= pinned_pages; + 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); }

return rc;

Convert fs/io_uring to use the new pin_user_pages() 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 io_uring 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_longterm_pages().

Reviewed-by: Ira Weiny ira.weiny@intel.com Reviewed-by: Jens Axboe axboe@kernel.dk Signed-off-by: John Hubbard jhubbard@nvidia.com --- fs/io_uring.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c index f9a38998f2fc..0f307f2c7cac 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3433,9 +3433,8 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,

ret = 0; down_read(&current->mm->mmap_sem); - pret = get_user_pages(ubuf, nr_pages, - FOLL_WRITE | FOLL_LONGTERM, - pages, vmas); + pret = pin_longterm_pages(ubuf, nr_pages, FOLL_WRITE, pages, + vmas); if (pret == nr_pages) { /* don't support file backed memory */ for (j = 0; j < nr_pages; j++) {

Add tracking of pages that were pinned via FOLL_PIN.

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

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

bool page_dma_pinned(struct page *page);

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

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

Suggested-by: Jan Kara jack@suse.cz Suggested-by: Jérôme Glisse jglisse@redhat.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- include/linux/mm.h | 74 +++++++++++---- include/linux/mmzone.h | 2 + include/linux/page_ref.h | 10 +++ mm/gup.c | 189 +++++++++++++++++++++++++++++++++------ mm/huge_memory.c | 54 ++++++++++- mm/hugetlb.c | 39 +++++++- mm/vmstat.c | 2 + 7 files changed, 321 insertions(+), 49 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h index c351e1b0b4b7..19b3fa68a4da 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1054,6 +1054,8 @@ static inline __must_check bool try_get_page(struct page *page) return true; }

+__must_check bool user_page_ref_inc(struct page *page); + static inline void put_page(struct page *page) { page = compound_head(page); @@ -1071,30 +1073,70 @@ static inline void put_page(struct page *page) __put_page(page); }

-/** - * put_user_page() - release a gup-pinned page - * @page: pointer to page to be released +/* + * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload + * the page's refcount so that two separate items are tracked: the original page + * reference count, and also a new count of how many get_user_pages() calls were + * made against the page. ("gup-pinned" is another term for the latter). + * + * With this scheme, get_user_pages() becomes special: such pages are marked + * as distinct from normal pages. As such, the new put_user_page() call (and + * its variants) must be used in order to release gup-pinned pages. + * + * Choice of value: * - * Pages that were pinned via either pin_user_pages*() or pin_longterm_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. + * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference + * counts with respect to get_user_pages() and put_user_page() becomes simpler, + * due to the fact that adding an even power of two to the page refcount has + * the effect of using only the upper N bits, for the code that counts up using + * the bias value. This means that the lower bits are left for the exclusive + * use of the original code that increments and decrements by one (or at least, + * by much smaller values than the bias value). * - * put_user_page() and put_page() are not interchangeable, despite this early - * implementation that makes them look the same. put_user_page() calls must - * be perfectly matched up with 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 put_user_page(struct page *page) -{ - put_page(page); -} +#define GUP_PIN_COUNTING_BIAS (1UL << 10)

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

+/** + * page_dma_pinned() - report if a page is pinned for DMA. + * + * This function checks if a page has been pinned via a call to + * pin_user_pages*() or pin_longterm_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 bda20282746b..0485cba38d23 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 put_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 4409e84dff51..82e7e4ce5027 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -51,6 +51,94 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) return head; }

+#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 + +/** + * user_page_ref_inc() - mark a page as being used by get_user_pages(FOLL_PIN). + * + * @page: pointer to page to be marked + * @Return: true for success, false for failure + */ +__must_check bool user_page_ref_inc(struct page *page) +{ + page = try_get_compound_head(page, GUP_PIN_COUNTING_BIAS); + if (!page) + return false; + + __update_proc_vmstat(page, NR_FOLL_PIN_REQUESTED, 1); + return true; +} + +#ifdef CONFIG_DEV_PAGEMAP_OPS +static bool __put_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 __put_devmap_managed_user_page(struct page *page) +{ + return false; +} +#endif /* CONFIG_DEV_PAGEMAP_OPS */ + +/** + * put_user_page() - release a dma-pinned page + * @page: pointer to page to be released + * + * Pages that were pinned via either pin_user_pages*() or pin_longterm_pages*() + * must be released via either put_user_page(), or one of the put_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 put_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 (__put_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(put_user_page); + /** * put_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 +325,11 @@ 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) @@ -283,6 +372,11 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, page = ERR_PTR(-ENOMEM); goto out; } + } else if (flags & FOLL_PIN) { + if (unlikely(!user_page_ref_inc(page))) { + page = ERR_PTR(-ENOMEM); + goto out; + } } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && @@ -544,8 +638,8 @@ 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); @@ -1844,13 +1938,17 @@ 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) + put_user_page(page); + else + put_page(page); } }

@@ -1883,7 +1981,7 @@ 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)) @@ -1892,9 +1990,15 @@ 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); - if (!head) - goto pte_unmap; + if (flags & FOLL_PIN) { + head = page; + if (unlikely(!user_page_ref_inc(head))) + goto pte_unmap; + } else { + head = try_get_compound_head(page, 1); + if (!head) + goto pte_unmap; + }

if (unlikely(pte_val(pte) != pte_val(*ptep))) { put_page(head); @@ -1948,12 +2052,20 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,

pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, pages); + undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } SetPageReferenced(page); pages[*nr] = page; - get_page(page); + + if (flags & FOLL_PIN) { + if (unlikely(!user_page_ref_inc(page))) { + undo_dev_pagemap(nr, nr_start, flags, pages); + return 0; + } + } else + get_page(page); + (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); @@ -1975,7 +2087,7 @@ 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; @@ -1993,7 +2105,7 @@ 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; @@ -2077,9 +2189,16 @@ 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); - if (!head) - return 0; + if (flags & FOLL_PIN) { + head = page; + if (unlikely(!user_page_ref_inc(head))) + return 0; + head = page; + } else { + head = try_get_compound_head(head, refs); + if (!head) + return 0; + }

if (unlikely(pte_val(pte) != pte_val(*ptep))) { put_compound_head(head, refs); @@ -2136,9 +2255,15 @@ 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); - if (!head) - return 0; + if (flags & FOLL_PIN) { + head = page; + if (unlikely(!user_page_ref_inc(head))) + return 0; + } else { + head = try_get_compound_head(pmd_page(orig), refs); + if (!head) + return 0; + }

if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { put_compound_head(head, refs); @@ -2169,9 +2294,15 @@ 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); - if (!head) - return 0; + if (flags & FOLL_PIN) { + head = page; + if (unlikely(!user_page_ref_inc(head))) + return 0; + } else { + head = try_get_compound_head(pud_page(orig), refs); + if (!head) + return 0; + }

if (unlikely(pud_val(orig) != pud_val(*pudp))) { put_compound_head(head, refs); @@ -2197,9 +2328,15 @@ 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); - if (!head) - return 0; + if (flags & FOLL_PIN) { + head = page; + if (unlikely(!user_page_ref_inc(head))) + return 0; + } else { + head = try_get_compound_head(pgd_page(orig), refs); + if (!head) + return 0; + }

if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { put_compound_head(head, refs); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 13cc93785006..4010c269e9e5 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 +973,18 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); - get_page(page); + + if (flags & FOLL_GET) + get_page(page); + else if (flags & FOLL_PIN) { + /* + * user_page_ref_inc() is not actually expected to fail here + * because we hold the pmd lock so no one can unmap the pmd and + * free the page that it points to. + */ + if (unlikely(!user_page_ref_inc(page))) + page = ERR_PTR(-EFAULT); + }

return page; } @@ -1088,6 +1104,11 @@ 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 +1120,10 @@ 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 +1131,18 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); - get_page(page); + + if (flags & FOLL_GET) + get_page(page); + else if (flags & FOLL_PIN) { + /* + * user_page_ref_inc() is not actually expected to fail here + * because we hold the pud lock so no one can unmap the pud and + * free the page that it points to. + */ + if (unlikely(!user_page_ref_inc(page))) + page = ERR_PTR(-EFAULT); + }

return page; } @@ -1522,8 +1556,20 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, skip_mlock: page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); + if (flags & FOLL_GET) get_page(page); + else if (flags & FOLL_PIN) { + /* + * user_page_ref_inc() is not actually expected to fail here + * because we hold the pmd lock so no one can unmap the pmd and + * free the page that it points to. + */ + if (unlikely(!user_page_ref_inc(page))) { + WARN_ON_ONCE(1); + page = NULL; + } + }

out: return page; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b45a95363a84..5ee80eea25e5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4462,7 +4462,22 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); - get_page(pages[i]); + + if (flags & FOLL_GET) + get_page(pages[i]); + else if (flags & FOLL_PIN) { + /* + * user_page_ref_inc() is not actually expected + * to fail here because we hold the ptl. + */ + if (unlikely(!user_page_ref_inc(pages[i]))) { + spin_unlock(ptl); + remainder = 0; + err = -ENOMEM; + WARN_ON_ONCE(1); + break; + } + } }

if (vmas) @@ -5022,6 +5037,12 @@ 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); @@ -5034,8 +5055,20 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, pte = huge_ptep_get((pte_t *)pmd); if (pte_present(pte)) { page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT); + if (flags & FOLL_GET) get_page(page); + else if (flags & FOLL_PIN) { + /* + * user_page_ref_inc() is not actually expected to fail + * here because we hold the ptl. + */ + if (unlikely(!user_page_ref_inc(page))) { + WARN_ON_ONCE(1); + page = NULL; + goto out; + } + } } else { if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); @@ -5056,7 +5089,7 @@ 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); @@ -5065,7 +5098,7 @@ 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 a8222041bd44..fdad40ccde7b 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1167,6 +1167,8 @@ 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",

1. Change vfio from get_user_pages(FOLL_LONGTERM), to pin_longterm_pages(), which sets both FOLL_LONGTERM and FOLL_PIN.

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().

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

Cc: Alex Williamson alex.williamson@redhat.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- drivers/vfio/vfio_iommu_type1.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 7301b710c9a4..1603459805f1 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -327,9 +327,8 @@ 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; @@ -347,8 +346,8 @@ 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, - page, NULL, NULL); + ret = pin_longterm_pages_remote(NULL, mm, vaddr, 1, flags, page, NULL, + NULL); if (ret == 1) { *pfn = page_to_pfn(page[0]); return 0;

Fix the gup benchmark flags to use the symbolic FOLL_WRITE, instead of a hard-coded "1" value.

Also, clean up the filtering of gup flags a little, by just doing it once before issuing any of the get_user_pages*() calls. This makes it harder to overlook, instead of having little "gup_flags & 1" phrases in the function calls.

Signed-off-by: John Hubbard jhubbard@nvidia.com --- mm/gup_benchmark.c | 9 ++++++--- tools/testing/selftests/vm/gup_benchmark.c | 6 +++++- 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 7dd602d7f8db..7fc44d25eca7 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -48,18 +48,21 @@ static int __gup_benchmark_ioctl(unsigned int cmd, nr = (next - addr) / PAGE_SIZE; }

+ /* Filter out most gup flags: only allow a tiny subset here: */ + gup->flags &= FOLL_WRITE; + switch (cmd) { case GUP_FAST_BENCHMARK: - nr = get_user_pages_fast(addr, nr, gup->flags & 1, + nr = get_user_pages_fast(addr, nr, gup->flags, pages + i); break; case GUP_LONGTERM_BENCHMARK: nr = get_user_pages(addr, nr, - (gup->flags & 1) | FOLL_LONGTERM, + gup->flags | FOLL_LONGTERM, pages + i, NULL); break; case GUP_BENCHMARK: - nr = get_user_pages(addr, nr, gup->flags & 1, pages + i, + nr = get_user_pages(addr, nr, gup->flags, pages + i, NULL); break; default: diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index 485cf06ef013..389327e9b30a 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -18,6 +18,9 @@ #define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark) #define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)

+/* Just the flags we need, copied from mm.h: */ +#define FOLL_WRITE 0x01 /* check pte is writable */ + struct gup_benchmark { __u64 get_delta_usec; __u64 put_delta_usec; @@ -85,7 +88,8 @@ int main(int argc, char **argv) }

gup.nr_pages_per_call = nr_pages; - gup.flags = write; + if (write) + gup.flags |= FOLL_WRITE;

fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR); if (fd == -1)

Up until now, gup_benchmark supported testing of the following kernel functions:

* get_user_pages(): via the '-U' command line option * get_user_pages_longterm(): via the '-L' command line option * get_user_pages_fast(): as the default (no options required)

Add test coverage for the new corresponding pin_*() functions:

* pin_user_pages(): via the '-c' command line option * pin_longterm_pages(): via the '-b' command line option * pin_user_pages_fast(): via the '-a' command line option

Also, add an option for clarity: '-u' for what is now (still) the default choice: get_user_pages_fast().

Also, for the three commands that set FOLL_PIN, verify that the pages really are dma-pinned, via the new is_dma_pinned() routine. Those commands are:

PIN_FAST_BENCHMARK : calls pin_user_pages_fast() PIN_LONGTERM_BENCHMARK : calls pin_longterm_pages() PIN_BENCHMARK : calls pin_user_pages()

In between the calls to pin_*() and put_user_pages(), check each page: if page_dma_pinned() returns false, then WARN and return.

Do this outside of the benchmark timestamps, so that it doesn't affect reported times.

Signed-off-by: John Hubbard jhubbard@nvidia.com --- mm/gup_benchmark.c | 73 ++++++++++++++++++++-- tools/testing/selftests/vm/gup_benchmark.c | 23 ++++++- 2 files changed, 90 insertions(+), 6 deletions(-)

diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 7fc44d25eca7..8f980d91dbf5 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -8,6 +8,9 @@ #define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark) #define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark) #define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark) +#define PIN_FAST_BENCHMARK _IOWR('g', 4, struct gup_benchmark) +#define PIN_LONGTERM_BENCHMARK _IOWR('g', 5, struct gup_benchmark) +#define PIN_BENCHMARK _IOWR('g', 6, struct gup_benchmark)

struct gup_benchmark { __u64 get_delta_usec; @@ -19,6 +22,44 @@ struct gup_benchmark { __u64 expansion[10]; /* For future use */ };

+static void put_back_pages(int cmd, struct page **pages, unsigned long nr_pages) +{ + int i; + + switch (cmd) { + case GUP_FAST_BENCHMARK: + case GUP_LONGTERM_BENCHMARK: + case GUP_BENCHMARK: + for (i = 0; i < nr_pages; i++) + put_page(pages[i]); + break; + + case PIN_FAST_BENCHMARK: + case PIN_LONGTERM_BENCHMARK: + case PIN_BENCHMARK: + put_user_pages(pages, nr_pages); + break; + } +} + +static void verify_dma_pinned(int cmd, struct page **pages, + unsigned long nr_pages) +{ + int i; + + switch (cmd) { + case PIN_FAST_BENCHMARK: + case PIN_LONGTERM_BENCHMARK: + case PIN_BENCHMARK: + for (i = 0; i < nr_pages; i++) { + if (WARN(!page_dma_pinned(pages[i]), + "pages[%d] is NOT dma-pinned\n", i)) + break; + } + break; + } +} + static int __gup_benchmark_ioctl(unsigned int cmd, struct gup_benchmark *gup) { @@ -65,6 +106,18 @@ static int __gup_benchmark_ioctl(unsigned int cmd, nr = get_user_pages(addr, nr, gup->flags, pages + i, NULL); break; + case PIN_FAST_BENCHMARK: + nr = pin_user_pages_fast(addr, nr, gup->flags, + pages + i); + break; + case PIN_LONGTERM_BENCHMARK: + nr = pin_longterm_pages(addr, nr, gup->flags, pages + i, + NULL); + break; + case PIN_BENCHMARK: + nr = pin_user_pages(addr, nr, gup->flags, pages + i, + NULL); + break; default: return -1; } @@ -75,15 +128,22 @@ static int __gup_benchmark_ioctl(unsigned int cmd, } end_time = ktime_get();

+ /* Shifting the meaning of nr_pages: now it is actual number pinned: */ + nr_pages = i; + gup->get_delta_usec = ktime_us_delta(end_time, start_time); gup->size = addr - gup->addr;

+ /* + * Take an un-benchmark-timed moment to verify DMA pinned + * state: print a warning if any non-dma-pinned pages are found: + */ + verify_dma_pinned(cmd, pages, nr_pages); + start_time = ktime_get(); - for (i = 0; i < nr_pages; i++) { - if (!pages[i]) - break; - put_page(pages[i]); - } + + put_back_pages(cmd, pages, nr_pages); + end_time = ktime_get(); gup->put_delta_usec = ktime_us_delta(end_time, start_time);

@@ -101,6 +161,9 @@ static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd, case GUP_FAST_BENCHMARK: case GUP_LONGTERM_BENCHMARK: case GUP_BENCHMARK: + case PIN_FAST_BENCHMARK: + case PIN_LONGTERM_BENCHMARK: + case PIN_BENCHMARK: break; default: return -EINVAL; diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index 389327e9b30a..03928e47a86f 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -18,6 +18,15 @@ #define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark) #define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)

+/* + * Similar to above, but use FOLL_PIN instead of FOLL_GET. This is done + * by calling pin_user_pages_fast(), pin_longterm_pages(), and pin_user_pages(), + * respectively. + */ +#define PIN_FAST_BENCHMARK _IOWR('g', 4, struct gup_benchmark) +#define PIN_LONGTERM_BENCHMARK _IOWR('g', 5, struct gup_benchmark) +#define PIN_BENCHMARK _IOWR('g', 6, struct gup_benchmark) + /* Just the flags we need, copied from mm.h: */ #define FOLL_WRITE 0x01 /* check pte is writable */

@@ -40,8 +49,17 @@ int main(int argc, char **argv) char *file = "/dev/zero"; char *p;

- while ((opt = getopt(argc, argv, "m:r:n:f:tTLUwSH")) != -1) { + while ((opt = getopt(argc, argv, "m:r:n:f:abctTLUuwSH")) != -1) { switch (opt) { + case 'a': + cmd = PIN_FAST_BENCHMARK; + break; + case 'b': + cmd = PIN_LONGTERM_BENCHMARK; + break; + case 'c': + cmd = PIN_BENCHMARK; + break; case 'm': size = atoi(optarg) * MB; break; @@ -63,6 +81,9 @@ int main(int argc, char **argv) case 'U': cmd = GUP_BENCHMARK; break; + case 'u': + cmd = GUP_FAST_BENCHMARK; + break; case 'w': write = 1; break;

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.

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 951c507a27f7..93e8dc9a7cad 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -104,6 +104,28 @@ 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 -c (pin_user_pages)" +echo "------------------------------------------" +./gup_benchmark -c +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "-------------------" echo "running userfaultfd" echo "-------------------"

Now that all other kernel callers of get_user_pages(FOLL_LONGTERM) have been converted to pin_longterm_pages(), lock it down:

1) Add an assertion to get_user_pages(), preventing callers from passing FOLL_LONGTERM (in addition to the existing assertion that prevents FOLL_PIN).

2) Remove the associated GUP_LONGTERM_BENCHMARK test.

Signed-off-by: John Hubbard jhubbard@nvidia.com --- mm/gup.c | 8 ++++---- mm/gup_benchmark.c | 9 +-------- tools/testing/selftests/vm/gup_benchmark.c | 7 ++----- 3 files changed, 7 insertions(+), 17 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index 82e7e4ce5027..90f5f95ee7ac 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1756,11 +1756,11 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, struct vm_area_struct **vmas) { /* - * FOLL_PIN must only be set internally by the pin_user_page*() and - * pin_longterm_*() APIs, never directly by the caller, so enforce that - * with an assertion: + * FOLL_PIN and FOLL_LONGTERM must only be set internally by the + * pin_user_page*() and pin_longterm_*() APIs, never directly by the + * caller, so enforce that with an assertion: */ - if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + if (WARN_ON_ONCE(gup_flags & (FOLL_PIN | FOLL_LONGTERM))) return -EINVAL;

return __gup_longterm_locked(current, current->mm, start, nr_pages, diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 8f980d91dbf5..679f0e6a0adb 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -6,7 +6,7 @@ #include <linux/debugfs.h>

#define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark) -#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark) +/* Command 2 has been deleted. */ #define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark) #define PIN_FAST_BENCHMARK _IOWR('g', 4, struct gup_benchmark) #define PIN_LONGTERM_BENCHMARK _IOWR('g', 5, struct gup_benchmark) @@ -28,7 +28,6 @@ static void put_back_pages(int cmd, struct page **pages, unsigned long nr_pages)

switch (cmd) { case GUP_FAST_BENCHMARK: - case GUP_LONGTERM_BENCHMARK: case GUP_BENCHMARK: for (i = 0; i < nr_pages; i++) put_page(pages[i]); @@ -97,11 +96,6 @@ static int __gup_benchmark_ioctl(unsigned int cmd, nr = get_user_pages_fast(addr, nr, gup->flags, pages + i); break; - case GUP_LONGTERM_BENCHMARK: - nr = get_user_pages(addr, nr, - gup->flags | FOLL_LONGTERM, - pages + i, NULL); - break; case GUP_BENCHMARK: nr = get_user_pages(addr, nr, gup->flags, pages + i, NULL); @@ -159,7 +153,6 @@ static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,

switch (cmd) { case GUP_FAST_BENCHMARK: - case GUP_LONGTERM_BENCHMARK: case GUP_BENCHMARK: case PIN_FAST_BENCHMARK: case PIN_LONGTERM_BENCHMARK: diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index 03928e47a86f..836b7082db13 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -15,7 +15,7 @@ #define PAGE_SIZE sysconf(_SC_PAGESIZE)

#define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark) -#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark) +/* Command 2 has been deleted. */ #define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)

/* @@ -49,7 +49,7 @@ int main(int argc, char **argv) char *file = "/dev/zero"; char *p;

- while ((opt = getopt(argc, argv, "m:r:n:f:abctTLUuwSH")) != -1) { + while ((opt = getopt(argc, argv, "m:r:n:f:abctTUuwSH")) != -1) { switch (opt) { case 'a': cmd = PIN_FAST_BENCHMARK; @@ -75,9 +75,6 @@ int main(int argc, char **argv) case 'T': thp = 0; break; - case 'L': - cmd = GUP_LONGTERM_BENCHMARK; - break; case 'U': cmd = GUP_BENCHMARK; break;