summaryrefslogtreecommitdiffstats
path: root/mm/gup.c
diff options
context:
space:
mode:
authorJohn Hubbard <jhubbard@nvidia.com>2020-04-01 21:05:29 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-04-02 09:35:27 -0700
commit3faa52c03f440d1b9ddef18c4f189f4790d52d7e (patch)
treebb6a2fef66352f853961d6a90c379f01b0a9ada4 /mm/gup.c
parent94202f126f698691f8865906ad6a68203e5dde8c (diff)
downloadlinux-3faa52c03f440d1b9ddef18c4f189f4790d52d7e.tar.gz
linux-3faa52c03f440d1b9ddef18c4f189f4790d52d7e.tar.bz2
linux-3faa52c03f440d1b9ddef18c4f189f4790d52d7e.zip
mm/gup: track FOLL_PIN pages
Add tracking of pages that were pinned via FOLL_PIN. This tracking is implemented via overloading of page->_refcount: pins are added by adding GUP_PIN_COUNTING_BIAS (1024) to the refcount. This provides a fuzzy indication of pinning, and it can have false positives (and that's OK). Please see the pre-existing Documentation/core-api/pin_user_pages.rst for details. As mentioned in pin_user_pages.rst, callers who effectively set FOLL_PIN (typically via pin_user_pages*()) are required to ultimately free such pages via unpin_user_page(). Please also note the limitation, discussed in pin_user_pages.rst under the "TODO: for 1GB and larger huge pages" section. (That limitation will be removed in a following patch.) The effect of a FOLL_PIN flag is similar to that of 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_maybe_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], [3], and [4]. 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/ [4] LWN kernel index: get_user_pages(): https://lwn.net/Kernel/Index/#Memory_management-get_user_pages [jhubbard@nvidia.com: add kerneldoc] Link: http://lkml.kernel.org/r/20200307021157.235726-1-jhubbard@nvidia.com [imbrenda@linux.ibm.com: if pin fails, we need to unpin, a simple put_page will not be enough] Link: http://lkml.kernel.org/r/20200306132537.783769-2-imbrenda@linux.ibm.com [akpm@linux-foundation.org: fix put_compound_head defined but not used] Suggested-by: Jan Kara <jack@suse.cz> Suggested-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Link: http://lkml.kernel.org/r/20200211001536.1027652-7-jhubbard@nvidia.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/gup.c')
-rw-r--r--mm/gup.c312
1 files changed, 250 insertions, 62 deletions
diff --git a/mm/gup.c b/mm/gup.c
index c8affbea2019..ee4f14f108fe 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -44,6 +44,135 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
return head;
}
+/*
+ * try_grab_compound_head() - attempt to elevate a page's refcount, by a
+ * flags-dependent amount.
+ *
+ * "grab" names in this file mean, "look at flags to decide whether to use
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
+ *
+ * Either FOLL_PIN or FOLL_GET (or neither) must 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.
+ *
+ * Return: head page (with refcount appropriately incremented) for success, or
+ * NULL upon failure. If neither FOLL_GET nor FOLL_PIN was set, that's
+ * considered failure, and furthermore, a likely bug in the caller, so a warning
+ * is also emitted.
+ */
+static __maybe_unused struct page *try_grab_compound_head(struct page *page,
+ int refs,
+ unsigned int flags)
+{
+ if (flags & FOLL_GET)
+ return try_get_compound_head(page, refs);
+ else if (flags & FOLL_PIN) {
+ refs *= GUP_PIN_COUNTING_BIAS;
+ return try_get_compound_head(page, refs);
+ }
+
+ WARN_ON_ONCE(1);
+ return NULL;
+}
+
+/**
+ * try_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 whether 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. Cases:
+ *
+ * FOLL_GET: page's refcount will be incremented by 1.
+ * FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ *
+ * Return: true for success, or if no action was required (if neither FOLL_PIN
+ * nor FOLL_GET was set, nothing is done). False for failure: FOLL_GET or
+ * FOLL_PIN was set, but the page could not be grabbed.
+ */
+bool __must_check try_grab_page(struct page *page, unsigned int flags)
+{
+ WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN));
+
+ if (flags & FOLL_GET)
+ return try_get_page(page);
+ else if (flags & FOLL_PIN) {
+ page = compound_head(page);
+
+ if (WARN_ON_ONCE(page_ref_count(page) <= 0))
+ return false;
+
+ page_ref_add(page, GUP_PIN_COUNTING_BIAS);
+ }
+
+ return true;
+}
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+static bool __unpin_devmap_managed_user_page(struct page *page)
+{
+ int count;
+
+ if (!page_is_devmap_managed(page))
+ return false;
+
+ count = page_ref_sub_return(page, GUP_PIN_COUNTING_BIAS);
+
+ /*
+ * 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 true;
+}
+#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);
+}
+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.
@@ -230,10 +359,11 @@ retry:
}
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)
@@ -271,11 +401,10 @@ retry:
goto retry;
}
- if (flags & FOLL_GET) {
- if (unlikely(!try_get_page(page))) {
- page = ERR_PTR(-ENOMEM);
- goto out;
- }
+ /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
+ if (unlikely(!try_grab_page(page, flags))) {
+ page = ERR_PTR(-ENOMEM);
+ goto out;
}
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
@@ -537,7 +666,7 @@ 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);
+ WARN_ON_ONCE(flags & (FOLL_GET | FOLL_PIN));
return page;
}
@@ -1675,6 +1804,15 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
{
return 0;
}
+
+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;
+}
#endif /* !CONFIG_MMU */
/*
@@ -1814,7 +1952,24 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
* This code is based heavily on the PowerPC implementation by Nick Piggin.
*/
#ifdef CONFIG_HAVE_FAST_GUP
+
+static void put_compound_head(struct page *page, int refs, unsigned int flags)
+{
+ if (flags & FOLL_PIN)
+ refs *= GUP_PIN_COUNTING_BIAS;
+
+ VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
+ /*
+ * Calling put_page() for each ref is unnecessarily slow. Only the last
+ * ref needs a put_page().
+ */
+ if (refs > 1)
+ page_ref_sub(page, refs - 1);
+ put_page(page);
+}
+
#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
+
/*
* WARNING: only to be used in the get_user_pages_fast() implementation.
*
@@ -1877,7 +2032,10 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
struct page *page = pages[--(*nr)];
ClearPageReferenced(page);
- put_page(page);
+ if (flags & FOLL_PIN)
+ unpin_user_page(page);
+ else
+ put_page(page);
}
}
@@ -1919,12 +2077,12 @@ 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;
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
- put_page(head);
+ put_compound_head(head, 1, flags);
goto pte_unmap;
}
@@ -1980,7 +2138,10 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
}
SetPageReferenced(page);
pages[*nr] = page;
- get_page(page);
+ if (unlikely(!try_grab_page(page, flags))) {
+ undo_dev_pagemap(nr, nr_start, flags, pages);
+ return 0;
+ }
(*nr)++;
pfn++;
} while (addr += PAGE_SIZE, addr != end);
@@ -2054,18 +2215,6 @@ static int record_subpages(struct page *page, unsigned long addr,
return nr;
}
-static void put_compound_head(struct page *page, int refs, unsigned int flags)
-{
- VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
- /*
- * Calling put_page() for each ref is unnecessarily slow. Only the last
- * ref needs a put_page().
- */
- if (refs > 1)
- page_ref_sub(page, refs - 1);
- put_page(page);
-}
-
#ifdef CONFIG_ARCH_HAS_HUGEPD
static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
unsigned long sz)
@@ -2099,7 +2248,7 @@ 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;
@@ -2159,7 +2308,7 @@ 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;
@@ -2193,7 +2342,7 @@ 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;
@@ -2222,7 +2371,7 @@ 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;
@@ -2505,11 +2654,11 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
/**
* 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.
+ * @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
@@ -2543,9 +2692,18 @@ 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().
+ * @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.
+ *
+ * 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).
@@ -2553,21 +2711,39 @@ 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().
+ * @tsk: the task_struct to use for page fault accounting, or
+ * NULL if faults are not to be recorded.
+ * @mm: mm_struct of target mm
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying lookup behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @vmas: array of pointers to vmas corresponding to each page.
+ * Or NULL if the caller does not require them.
+ * @locked: pointer to lock flag indicating whether lock is held and
+ * subsequently whether VM_FAULT_RETRY functionality can be
+ * utilised. Lock must initially be held.
+ *
+ * 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).
@@ -2577,22 +2753,33 @@ 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().
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying lookup behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @vmas: array of pointers to vmas corresponding to each page.
+ * Or NULL if the caller does not require them.
+ *
+ * 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).
@@ -2601,11 +2788,12 @@ 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);