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

Also placate checkpatch.pl by shortening a nearby line.

Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- mm/gup.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index 8f236a335ae9..85caf76b3012 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1890,7 +1890,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,

#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) static int __gup_device_huge(unsigned long pfn, unsigned long addr, - unsigned long end, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { int nr_start = *nr; struct dev_pagemap *pgmap = NULL; @@ -1916,13 +1917,14 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, }

static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr;

fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - if (!__gup_device_huge(fault_pfn, addr, end, pages, nr)) + if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) return 0;

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

static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, - unsigned long end, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr;

fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - if (!__gup_device_huge(fault_pfn, addr, end, pages, nr)) + if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) return 0;

if (unlikely(pud_val(orig) != pud_val(*pudp))) { @@ -1950,14 +1953,16 @@ static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, } #else static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { BUILD_BUG(); return 0; }

static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr, - unsigned long end, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { BUILD_BUG(); return 0; @@ -2062,7 +2067,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; - return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr); + return __gup_device_huge_pmd(orig, pmdp, addr, end, flags, + pages, nr); }

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

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

refs = 0;

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

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

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

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

Cc: Christoph Hellwig hch@lst.de Cc: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- mm/gup.c | 113 ++++++++++++++++++++++--------------------------------- 1 file changed, 46 insertions(+), 67 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index 85caf76b3012..8fb0d9cdfaf5 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1969,6 +1969,35 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr, } #endif

+static int __record_subpages(struct page *page, unsigned long addr, + unsigned long end, struct page **pages, int nr) +{ + int nr_recorded_pages = 0; + + do { + pages[nr] = page; + nr++; + page++; + nr_recorded_pages++; + } while (addr += PAGE_SIZE, addr != end); + return nr_recorded_pages; +} + +static void __remove_refs_from_head(struct page *page, int refs) +{ + /* Do a get_page() first, in case refs == page->_refcount */ + get_page(page); + page_ref_sub(page, refs); + put_page(page); +} + +static int __huge_pt_done(struct page *head, int nr_recorded_pages, int *nr) +{ + *nr += nr_recorded_pages; + SetPageReferenced(head); + return 1; +} + #ifdef CONFIG_ARCH_HAS_HUGEPD static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, unsigned long sz) @@ -1998,34 +2027,19 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, /* hugepages are never "special" */ VM_BUG_ON(!pfn_valid(pte_pfn(pte)));

- refs = 0; head = pte_page(pte); - page = head + ((addr & (sz-1)) >> PAGE_SHIFT); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); + refs = __record_subpages(page, addr, end, pages, *nr);

head = try_get_compound_head(head, refs); - if (!head) { - *nr -= refs; + if (!head) return 0; - }

if (unlikely(pte_val(pte) != pte_val(*ptep))) { - /* Could be optimized better */ - *nr -= refs; - while (refs--) - put_page(head); + __remove_refs_from_head(head, refs); return 0; } - - SetPageReferenced(head); - return 1; + return __huge_pt_done(head, refs, nr); }

static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, @@ -2071,30 +2085,18 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, pages, nr); }

- refs = 0; page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - do { - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); + refs = __record_subpages(page, addr, end, pages, *nr);

head = try_get_compound_head(pmd_page(orig), refs); - if (!head) { - *nr -= refs; + if (!head) return 0; - }

if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { - *nr -= refs; - while (refs--) - put_page(head); + __remove_refs_from_head(head, refs); return 0; } - - SetPageReferenced(head); - return 1; + return __huge_pt_done(head, refs, nr); }

static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, @@ -2114,30 +2116,18 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, pages, nr); }

- refs = 0; page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - do { - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); + refs = __record_subpages(page, addr, end, pages, *nr);

head = try_get_compound_head(pud_page(orig), refs); - if (!head) { - *nr -= refs; + if (!head) return 0; - }

if (unlikely(pud_val(orig) != pud_val(*pudp))) { - *nr -= refs; - while (refs--) - put_page(head); + __remove_refs_from_head(head, refs); return 0; } - - SetPageReferenced(head); - return 1; + return __huge_pt_done(head, refs, nr); }

static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, @@ -2151,30 +2141,19 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0;

BUILD_BUG_ON(pgd_devmap(orig)); - refs = 0; + page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); - do { - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); + refs = __record_subpages(page, addr, end, pages, *nr);

head = try_get_compound_head(pgd_page(orig), refs); - if (!head) { - *nr -= refs; + if (!head) return 0; - }

if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { - *nr -= refs; - while (refs--) - put_page(head); + __remove_refs_from_head(head, refs); return 0; } - - SetPageReferenced(head); - return 1; + return __huge_pt_done(head, refs, nr); }

static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,

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 basically documented. (An upcoming patch provides more extensive documentation.) The second set (pin_longterm*) also sets FOLL_LONGTERM:

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().

Signed-off-by: John Hubbard jhubbard@nvidia.com --- include/linux/mm.h | 53 ++++++++- mm/gup.c | 284 +++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 311 insertions(+), 26 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h index cc292273e6ba..62c838a3e6c7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1526,9 +1526,23 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); +long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked); +long pin_longterm_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); +long pin_user_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas); +long pin_longterm_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, @@ -1536,6 +1550,10 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,

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

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

/* - * NOTE on FOLL_LONGTERM: + * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each + * other. Here is what they mean, and how to use them: * * FOLL_LONGTERM indicates that the page will be held for an indefinite time - * period _often_ under userspace control. This is contrasted with - * iov_iter_get_pages() where usages which are transient. + * period _often_ under userspace control. This is in contrast to + * iov_iter_get_pages(), where usages which are transient. * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm @@ -2615,11 +2635,32 @@ 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. + * + * 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 8fb0d9cdfaf5..8694bc7b3df3 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -179,6 +179,10 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, spinlock_t *ptl; pte_t *ptep, pte;

+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == + (FOLL_PIN | FOLL_GET))) + return ERR_PTR(-EINVAL); retry: if (unlikely(pmd_bad(*pmd))) return no_page_table(vma, flags); @@ -790,7 +794,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,

start = untagged_addr(start);

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

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

- if (pages) + /* + * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior + * is to set FOLL_GET if the caller wants pages[] filled in (but has + * carelessly failed to specify FOLL_GET), so keep doing that, but only + * for FOLL_GET, not for the newer FOLL_PIN. + * + * FOLL_PIN always expects pages to be non-null, but no need to assert + * that here, as any failures will be obvious enough. + */ + if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET;

pages_done = 0; @@ -1133,6 +1146,12 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must * be called after the page is finished with, and before put_page is called. * + * A note on gup_flags: FOLL_PIN must only 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(). + * * get_user_pages is typically used for fewer-copy IO operations, to get a * handle on the memory by some means other than accesses via the user virtual * addresses. The pages may be submitted for DMA to devices or accessed via @@ -1151,6 +1170,14 @@ 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) { + /* + * As detailed above, FOLL_PIN must only be set internally by the + * pin_user_page*() and pin_longterm_*() APIs, never directly by the + * caller, so enforce that with an assertion: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + return -EINVAL; + /* * FIXME: Current FOLL_LONGTERM behavior is incompatible with * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on @@ -1603,11 +1630,25 @@ static __always_inline long __gup_longterm_locked(struct task_struct *tsk, * and mm being operated on are the current task's and don't allow * passing of a locked parameter. We also obviously don't pass * FOLL_REMOTE in here. + * + * A note on gup_flags: FOLL_PIN should only 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(). */ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas) { + /* + * As detailed above, 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); } @@ -2366,24 +2407,9 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages, return ret; }

-/** - * get_user_pages_fast() - pin user pages in memory - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @gup_flags: flags modifying pin behaviour - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. - * - * Attempt to pin user pages in memory without taking mm->mmap_sem. - * If not successful, it will fall back to taking the lock and - * calling get_user_pages(). - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. - */ -int get_user_pages_fast(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) +static int internal_get_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, + struct page **pages) { unsigned long addr, len, end; int nr = 0, ret = 0; @@ -2428,4 +2454,222 @@ 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(). + * + * A note on gup_flags: FOLL_PIN must only 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(). + * + * 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) +{ + /* + * As detailed above, FOLL_PIN must only be set internally by the + * pin_user_page*() and pin_longterm_*() APIs, never directly by the + * caller, so enforce that: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) + return -EINVAL; + + return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); +} EXPORT_SYMBOL_GPL(get_user_pages_fast); + +/** + * pin_user_pages_fast() - pin user pages in memory without taking locks + * + * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See + * get_user_pages_fast() for documentation on the function arguments, because + * the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for further details. + * + * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It + * is NOT intended for Case 2 (RDMA: long-term pins). + */ +int pin_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); +} +EXPORT_SYMBOL_GPL(pin_user_pages_fast); + +/** + * pin_longterm_pages_fast() - pin user pages in memory without taking locks + * + * Nearly the same as get_user_pages_fast(), except that FOLL_PIN and + * FOLL_LONGTERM are set. See get_user_pages_fast() for documentation on the + * function arguments, because the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for further details. + * + * FOLL_LONGTERM means that the pages are being pinned for "long term" use, + * typically by a non-CPU device, and we cannot be sure that waiting for a + * pinned page to become unpin will be effective. + * + * This is intended for Case 2 (RDMA: long-term pins) of the FOLL_PIN + * documentation. + */ +int pin_longterm_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= (FOLL_PIN | FOLL_LONGTERM); + return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); +} +EXPORT_SYMBOL_GPL(pin_longterm_pages_fast); + +/** + * pin_user_pages_remote() - pin pages for (typically) use by Direct IO, and + * return the pages to the user. + * + * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See + * get_user_pages_remote() for documentation on the function arguments, because + * the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for details. + * + * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It + * is NOT intended for Case 2 (RDMA: long-term pins). + */ +long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_TOUCH | FOLL_REMOTE | FOLL_PIN; + + return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, + locked, gup_flags); +} +EXPORT_SYMBOL(pin_user_pages_remote); + +/** + * pin_longterm_pages_remote() - pin pages for (typically) use by Direct IO, and + * return the pages to the user. + * + * Nearly the same as get_user_pages_remote(), but note that FOLL_TOUCH is not + * set, and FOLL_PIN and FOLL_LONGTERM are set. See get_user_pages_remote() for + * documentation on the function arguments, because the arguments here are + * identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for further details. + * + * FOLL_LONGTERM means that the pages are being pinned for "long term" use, + * typically by a non-CPU device, and we cannot be sure that waiting for a + * pinned page to become unpin will be effective. + * + * This is intended for Case 2 (RDMA: long-term pins) in + * Documentation/vm/pin_user_pages.rst. + */ +long pin_longterm_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + /* + * FIXME: as noted in the get_user_pages_remote() implementation, it + * is not yet possible to safely set FOLL_LONGTERM here. FOLL_LONGTERM + * needs to be set, but for now the best we can do is a "TODO" item. + */ + gup_flags |= FOLL_REMOTE | FOLL_PIN; + + return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, + locked, gup_flags); +} +EXPORT_SYMBOL(pin_longterm_pages_remote); + +/** + * pin_user_pages() - pin user pages in memory for use by other devices + * + * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and + * FOLL_PIN is set. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for details. + * + * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It + * is NOT intended for Case 2 (RDMA: long-term pins). + */ +long pin_user_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN; + return __gup_longterm_locked(current, current->mm, start, nr_pages, + pages, vmas, gup_flags); +} +EXPORT_SYMBOL(pin_user_pages); + +/** + * pin_longterm_pages() - pin user pages in memory for long-term use (RDMA, + * typically) + * + * Nearly the same as get_user_pages(), except that FOLL_PIN and FOLL_LONGTERM + * are set. See get_user_pages_fast() for documentation on the function + * arguments, because the arguments here are identical. + * + * FOLL_PIN means that the pages must be released via put_user_page(). Please + * see Documentation/vm/pin_user_pages.rst for further details. + * + * FOLL_LONGTERM means that the pages are being pinned for "long term" use, + * typically by a non-CPU device, and we cannot be sure that waiting for a + * pinned page to become unpin will be effective. + * + * This is intended for Case 2 (RDMA: long-term pins) in + * Documentation/vm/pin_user_pages.rst. + */ +long pin_longterm_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas) +{ + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return -EINVAL; + + gup_flags |= FOLL_PIN | FOLL_LONGTERM; + return __gup_longterm_locked(current, current->mm, start, nr_pages, + pages, vmas, gup_flags); +} +EXPORT_SYMBOL(pin_longterm_pages);

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

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

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

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 24244a2f68cc..c5a78d3e674b 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -272,11 +272,10 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,

while (npages) { down_read(&mm->mmap_sem); - ret = get_user_pages(cur_base, + ret = pin_longterm_pages(cur_base, min_t(unsigned long, npages, PAGE_SIZE / sizeof (struct page *)), - gup_flags | FOLL_LONGTERM, - page_list, NULL); + gup_flags, page_list, NULL); if (ret < 0) { up_read(&mm->mmap_sem); goto umem_release; diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 163ff7ba92b7..a38b67b83db5 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -534,7 +534,7 @@ static int ib_umem_odp_map_dma_single_page( } else if (umem_odp->page_list[page_index] == page) { umem_odp->dma_list[page_index] |= access_mask; } else { - pr_err("error: got different pages in IB device and from get_user_pages. IB device page: %p, gup page: %p\n", + pr_err("error: got different pages in IB device and from pin_longterm_pages. IB device page: %p, gup page: %p\n", umem_odp->page_list[page_index], page); /* Better remove the mapping now, to prevent any further * damage. */ @@ -639,11 +639,11 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt, /* * Note: this might result in redundent page getting. We can * avoid this by checking dma_list to be 0 before calling - * get_user_pages. However, this make the code much more - * complex (and doesn't gain us much performance in most use - * cases). + * pin_longterm_pages. However, this makes the code much + * more complex (and doesn't gain us much performance in most + * use cases). */ - npages = get_user_pages_remote(owning_process, owning_mm, + npages = pin_longterm_pages_remote(owning_process, owning_mm, user_virt, gup_num_pages, flags, local_page_list, NULL, NULL); up_read(&owning_mm->mmap_sem); diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c index 469acb961fbd..9b55b0a73e29 100644 --- a/drivers/infiniband/hw/hfi1/user_pages.c +++ b/drivers/infiniband/hw/hfi1/user_pages.c @@ -104,9 +104,9 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np bool writable, struct page **pages) { int ret; - unsigned int gup_flags = FOLL_LONGTERM | (writable ? FOLL_WRITE : 0); + unsigned int gup_flags = (writable ? FOLL_WRITE : 0);

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

diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c index edccfd6e178f..beec7e4b8a96 100644 --- a/drivers/infiniband/hw/mthca/mthca_memfree.c +++ b/drivers/infiniband/hw/mthca/mthca_memfree.c @@ -472,8 +472,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar, goto out; }

- ret = get_user_pages_fast(uaddr & PAGE_MASK, 1, - FOLL_WRITE | FOLL_LONGTERM, pages); + ret = pin_longterm_pages_fast(uaddr & PAGE_MASK, 1, FOLL_WRITE, pages); if (ret < 0) goto out;

diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c index 6bf764e41891..684a14e14d9b 100644 --- a/drivers/infiniband/hw/qib/qib_user_pages.c +++ b/drivers/infiniband/hw/qib/qib_user_pages.c @@ -108,10 +108,10 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,

down_read(&current->mm->mmap_sem); for (got = 0; got < num_pages; got += ret) { - ret = get_user_pages(start_page + got * PAGE_SIZE, - num_pages - got, - FOLL_LONGTERM | FOLL_WRITE | FOLL_FORCE, - p + got, NULL); + ret = pin_longterm_pages(start_page + got * PAGE_SIZE, + num_pages - got, + FOLL_WRITE | FOLL_FORCE, + p + got, NULL); if (ret < 0) { up_read(&current->mm->mmap_sem); goto bail_release; diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c index 05190edc2611..fd86a9d19370 100644 --- a/drivers/infiniband/hw/qib/qib_user_sdma.c +++ b/drivers/infiniband/hw/qib/qib_user_sdma.c @@ -670,7 +670,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd, else j = npages;

- ret = get_user_pages_fast(addr, j, FOLL_LONGTERM, pages); + ret = pin_longterm_pages_fast(addr, j, 0, pages); if (ret != j) { i = 0; j = ret; diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index 62e6ffa9ad78..6b90ca1c3771 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -141,11 +141,10 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable, ret = 0;

while (npages) { - ret = get_user_pages(cur_base, - min_t(unsigned long, npages, - PAGE_SIZE / sizeof(struct page *)), - gup_flags | FOLL_LONGTERM, - page_list, NULL); + ret = pin_longterm_pages(cur_base, + min_t(unsigned long, npages, + PAGE_SIZE / sizeof(struct page *)), + gup_flags, page_list, NULL);

if (ret < 0) goto out; diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c index e99983f07663..20e663d7ada8 100644 --- a/drivers/infiniband/sw/siw/siw_mem.c +++ b/drivers/infiniband/sw/siw/siw_mem.c @@ -426,9 +426,8 @@ struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable) while (nents) { struct page **plist = &umem->page_chunk[i].plist[got];

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

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

Signed-off-by: John Hubbard jhubbard@nvidia.com --- drivers/gpu/drm/via/via_dmablit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c index 3db000aacd26..37c5e572993a 100644 --- a/drivers/gpu/drm/via/via_dmablit.c +++ b/drivers/gpu/drm/via/via_dmablit.c @@ -239,7 +239,7 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg, drm_via_dmablit_t *xfer) vsg->pages = vzalloc(array_size(sizeof(struct page *), vsg->num_pages)); if (NULL == vsg->pages) return -ENOMEM; - ret = get_user_pages_fast((unsigned long)xfer->mem_addr, + ret = pin_user_pages_fast((unsigned long)xfer->mem_addr, vsg->num_pages, vsg->direction == DMA_FROM_DEVICE ? FOLL_WRITE : 0, vsg->pages);

Convert 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().

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 a30c4f622cb3..d3924b1760eb 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3431,9 +3431,8 @@ 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().

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

This includes the following fix from Ira Weiny:

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

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

Suggested-by: Jan Kara jack@suse.cz Suggested-by: Jérôme Glisse jglisse@redhat.com Signed-off-by: Ira Weiny ira.weiny@intel.com Signed-off-by: John Hubbard jhubbard@nvidia.com --- include/linux/mm.h | 80 +++++++++++---- include/linux/mmzone.h | 2 + include/linux/page_ref.h | 10 ++ mm/gup.c | 213 +++++++++++++++++++++++++++++++-------- mm/huge_memory.c | 32 +++++- mm/hugetlb.c | 28 ++++- mm/memremap.c | 4 +- mm/vmstat.c | 2 + 8 files changed, 300 insertions(+), 71 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h index 62c838a3e6c7..882fda919c81 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -972,9 +972,10 @@ static inline bool is_zone_device_page(const struct page *page) #endif

#ifdef CONFIG_DEV_PAGEMAP_OPS -void __put_devmap_managed_page(struct page *page); +void __put_devmap_managed_page(struct page *page, int count); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -static inline bool put_devmap_managed_page(struct page *page) + +static inline bool page_is_devmap_managed(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; @@ -983,7 +984,6 @@ static inline bool put_devmap_managed_page(struct page *page) switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_FS_DAX: - __put_devmap_managed_page(page); return true; default: break; @@ -991,6 +991,19 @@ static inline bool put_devmap_managed_page(struct page *page) return false; }

+static inline bool put_devmap_managed_page(struct page *page) +{ + bool is_devmap = page_is_devmap_managed(page); + + if (is_devmap) { + int count = page_ref_dec_return(page); + + __put_devmap_managed_page(page, count); + } + + return is_devmap; +} + #else /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool put_devmap_managed_page(struct page *page) { @@ -1038,6 +1051,8 @@ static inline __must_check bool try_get_page(struct page *page) return true; }

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

-/** - * put_user_page() - release a gup-pinned page - * @page: pointer to page to be released +/* + * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload + * the page's refcount so that two separate items are tracked: the original page + * reference count, and also a new count of how many get_user_pages() calls were + * made against the page. ("gup-pinned" is another term for the latter). + * + * With this scheme, get_user_pages() becomes special: such pages are marked + * as distinct from normal pages. As such, the new put_user_page() call (and + * its variants) must be used in order to release gup-pinned pages. + * + * Choice of value: * - * Pages that were pinned via get_user_pages*() must be released via - * either put_user_page(), or one of the put_user_pages*() routines - * below. This is so that eventually, pages that are pinned via - * get_user_pages*() can be separately tracked and uniquely handled. In - * particular, interactions with RDMA and filesystems need special - * handling. + * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference + * counts with respect to get_user_pages() and put_user_page() becomes simpler, + * due to the fact that adding an even power of two to the page refcount has + * the effect of using only the upper N bits, for the code that counts up using + * the bias value. This means that the lower bits are left for the exclusive + * use of the original code that increments and decrements by one (or at least, + * by much smaller values than the bias value). * - * put_user_page() and put_page() are not interchangeable, despite this early - * implementation that makes them look the same. put_user_page() calls must - * be perfectly matched up with get_user_page() calls. + * Of course, once the lower bits overflow into the upper bits (and this is + * OK, because subtraction recovers the original values), then visual inspection + * no longer suffices to directly view the separate counts. However, for normal + * applications that don't have huge page reference counts, this won't be an + * issue. + * + * Locking: the lockless algorithm described in page_cache_get_speculative() + * and page_cache_gup_pin_speculative() provides safe operation for + * get_user_pages and page_mkclean and other calls that race to set up page + * table entries. */ -static inline void put_user_page(struct page *page) -{ - put_page(page); -} +#define GUP_PIN_COUNTING_BIAS (1UL << 10)

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

+/** + * page_dma_pinned() - report if a page is pinned by a call to pin_user_pages*() + * or pin_longterm_pages*() + * @page: pointer to page to be queried. + * @Return: True, if it is likely that the page has been "dma-pinned". + * False, if the page is definitely not dma-pinned. + */ +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 8694bc7b3df3..e51b3820a995 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -29,6 +29,102 @@ 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; +} + +#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); + __put_devmap_managed_page(page, count); + } + + 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 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. + */ +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. @@ -215,10 +311,11 @@ 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) @@ -261,6 +358,11 @@ 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) && @@ -522,8 +624,8 @@ 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); @@ -1824,30 +1926,20 @@ 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); } }

-/* - * 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) @@ -1877,7 +1969,7 @@ 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)) @@ -1886,9 +1978,15 @@ 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); @@ -1942,12 +2040,20 @@ 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); @@ -1969,7 +2075,7 @@ 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; @@ -1987,7 +2093,7 @@ 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; @@ -2072,9 +2178,16 @@ 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))) { __remove_refs_from_head(head, refs); @@ -2129,9 +2242,15 @@ 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))) { __remove_refs_from_head(head, refs); @@ -2160,9 +2279,15 @@ 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))) { __remove_refs_from_head(head, refs); @@ -2186,9 +2311,15 @@ 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))) { __remove_refs_from_head(head, refs); @@ -2414,7 +2545,7 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, unsigned long addr, len, end; int nr = 0, ret = 0;

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

start = untagged_addr(start) & PAGE_MASK; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 13cc93785006..66bf4c8b88f1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -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 +973,12 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); - get_page(page); + + if (flags & FOLL_GET) + get_page(page); + else if (flags & FOLL_PIN) + if (unlikely(!user_page_ref_inc(page))) + page = ERR_PTR(-ENOMEM);

return page; } @@ -1088,6 +1098,11 @@ 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 @@ -1100,7 +1115,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, * device mapped pages can only be returned if the * caller will manage the page reference count. */ - if (!(flags & FOLL_GET)) + if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST);

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

return page; } @@ -1522,8 +1542,12 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, skip_mlock: page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); + if (flags & FOLL_GET) get_page(page); + else if (flags & FOLL_PIN) + if (unlikely(!user_page_ref_inc(page))) + page = NULL;

out: return page; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b45a95363a84..da335b1cd798 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4462,7 +4462,17 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); - get_page(pages[i]); + + if (flags & FOLL_GET) + get_page(pages[i]); + else if (flags & FOLL_PIN) + if (unlikely(!user_page_ref_inc(pages[i]))) { + spin_unlock(ptl); + remainder = 0; + err = -ENOMEM; + WARN_ON_ONCE(1); + break; + } }

if (vmas) @@ -5022,6 +5032,12 @@ 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 +5050,14 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, pte = huge_ptep_get((pte_t *)pmd); if (pte_present(pte)) { page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT); + if (flags & FOLL_GET) get_page(page); + else if (flags & FOLL_PIN) + if (unlikely(!user_page_ref_inc(page))) { + page = NULL; + goto out; + } } else { if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); @@ -5056,7 +5078,7 @@ 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 +5087,7 @@ 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/memremap.c b/mm/memremap.c index 03ccbdfeb697..3b1c69df1d2a 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -410,10 +410,8 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, EXPORT_SYMBOL_GPL(get_dev_pagemap);

#ifdef CONFIG_DEV_PAGEMAP_OPS -void __put_devmap_managed_page(struct page *page) +void __put_devmap_managed_page(struct page *page, int count) { - int count = page_ref_dec_return(page); - /* * If refcount is 1 then page is freed and refcount is stable as nobody * holds a reference on the page. diff --git a/mm/vmstat.c b/mm/vmstat.c index 6afc892a148a..65c027d9b637 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",

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 | 74 ++++++++++++++++++++-- tools/testing/selftests/vm/gup_benchmark.c | 23 ++++++- 2 files changed, 91 insertions(+), 6 deletions(-)

diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 7dd602d7f8db..2bb0f5df4803 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) { @@ -62,6 +103,19 @@ static int __gup_benchmark_ioctl(unsigned int cmd, nr = get_user_pages(addr, nr, gup->flags & 1, pages + i, NULL); break; + case PIN_FAST_BENCHMARK: + nr = pin_user_pages_fast(addr, nr, gup->flags & 1, + pages + i); + break; + case PIN_LONGTERM_BENCHMARK: + nr = pin_longterm_pages(addr, nr, + (gup->flags & 1), + pages + i, NULL); + break; + case PIN_BENCHMARK: + nr = pin_user_pages(addr, nr, gup->flags & 1, pages + i, + NULL); + break; default: return -1; } @@ -72,15 +126,22 @@ 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);

@@ -98,6 +159,9 @@ 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 485cf06ef013..c5c934c0f402 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) + struct gup_benchmark { __u64 get_delta_usec; __u64 put_delta_usec; @@ -37,8 +46,17 @@ 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; @@ -60,6 +78,9 @@ int main(int argc, char **argv) case 'U': cmd = GUP_BENCHMARK; break; + case 'u': + cmd = GUP_FAST_BENCHMARK; + break; case 'w': write = 1; break;

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 e51b3820a995..9a28935a2cb1 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1744,11 +1744,11 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, struct vm_area_struct **vmas) { /* - * As detailed above, 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: + * As detailed above, 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 2bb0f5df4803..de6941855b7e 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]); @@ -94,11 +93,6 @@ static int __gup_benchmark_ioctl(unsigned int cmd, nr = get_user_pages_fast(addr, nr, gup->flags & 1, pages + i); break; - case GUP_LONGTERM_BENCHMARK: - nr = get_user_pages(addr, nr, - (gup->flags & 1) | FOLL_LONGTERM, - pages + i, NULL); - break; case GUP_BENCHMARK: nr = get_user_pages(addr, nr, gup->flags & 1, pages + i, NULL); @@ -157,7 +151,6 @@ 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 c5c934c0f402..5ef3cf8f3da5 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)

/* @@ -46,7 +46,7 @@ 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; @@ -72,9 +72,6 @@ int main(int argc, char **argv) case 'T': thp = 0; break; - case 'L': - cmd = GUP_LONGTERM_BENCHMARK; - break; case 'U': cmd = GUP_BENCHMARK; break;