Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/mm/gup.c b/mm/gup.c
index 1abc8b4..8f236a3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/err.h>
@@ -13,6 +14,9 @@
#include <linux/sched/signal.h>
#include <linux/rwsem.h>
#include <linux/hugetlb.h>
+#include <linux/migrate.h>
+#include <linux/mm_inline.h>
+#include <linux/sched/mm.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
@@ -20,6 +24,102 @@
#include "internal.h"
+struct follow_page_context {
+ struct dev_pagemap *pgmap;
+ unsigned int page_mask;
+};
+
+/**
+ * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
+ * @pages: array of pages to be maybe marked dirty, and definitely released.
+ * @npages: number of pages in the @pages array.
+ * @make_dirty: whether to mark the pages dirty
+ *
+ * "gup-pinned page" refers to a page that has had one of the get_user_pages()
+ * variants called on that page.
+ *
+ * For each page in the @pages array, make that page (or its head page, if a
+ * compound page) dirty, if @make_dirty is true, and if the page was previously
+ * listed as clean. In any case, releases all pages using put_user_page(),
+ * possibly via put_user_pages(), for the non-dirty case.
+ *
+ * Please see the put_user_page() documentation for details.
+ *
+ * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
+ * required, then the caller should a) verify that this is really correct,
+ * because _lock() is usually required, and b) hand code it:
+ * set_page_dirty_lock(), put_user_page().
+ *
+ */
+void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+ bool make_dirty)
+{
+ unsigned long index;
+
+ /*
+ * TODO: this can be optimized for huge pages: if a series of pages is
+ * physically contiguous and part of the same compound page, then a
+ * single operation to the head page should suffice.
+ */
+
+ if (!make_dirty) {
+ put_user_pages(pages, npages);
+ return;
+ }
+
+ for (index = 0; index < npages; index++) {
+ struct page *page = compound_head(pages[index]);
+ /*
+ * Checking PageDirty at this point may race with
+ * clear_page_dirty_for_io(), but that's OK. Two key
+ * cases:
+ *
+ * 1) This code sees the page as already dirty, so it
+ * skips the call to set_page_dirty(). That could happen
+ * because clear_page_dirty_for_io() called
+ * page_mkclean(), followed by set_page_dirty().
+ * However, now the page is going to get written back,
+ * which meets the original intention of setting it
+ * dirty, so all is well: clear_page_dirty_for_io() goes
+ * on to call TestClearPageDirty(), and write the page
+ * back.
+ *
+ * 2) This code sees the page as clean, so it calls
+ * set_page_dirty(). The page stays dirty, despite being
+ * written back, so it gets written back again in the
+ * next writeback cycle. This is harmless.
+ */
+ if (!PageDirty(page))
+ set_page_dirty_lock(page);
+ put_user_page(page);
+ }
+}
+EXPORT_SYMBOL(put_user_pages_dirty_lock);
+
+/**
+ * put_user_pages() - release an array of gup-pinned pages.
+ * @pages: array of pages to be marked dirty and released.
+ * @npages: number of pages in the @pages array.
+ *
+ * For each page in the @pages array, release the page using put_user_page().
+ *
+ * Please see the put_user_page() documentation for details.
+ */
+void put_user_pages(struct page **pages, unsigned long npages)
+{
+ unsigned long index;
+
+ /*
+ * TODO: this can be optimized for huge pages: if a series of pages is
+ * physically contiguous and part of the same compound page, then a
+ * single operation to the head page should suffice.
+ */
+ for (index = 0; index < npages; index++)
+ put_user_page(pages[index]);
+}
+EXPORT_SYMBOL(put_user_pages);
+
+#ifdef CONFIG_MMU
static struct page *no_page_table(struct vm_area_struct *vma,
unsigned int flags)
{
@@ -71,10 +171,10 @@
}
static struct page *follow_page_pte(struct vm_area_struct *vma,
- unsigned long address, pmd_t *pmd, unsigned int flags)
+ unsigned long address, pmd_t *pmd, unsigned int flags,
+ struct dev_pagemap **pgmap)
{
struct mm_struct *mm = vma->vm_mm;
- struct dev_pagemap *pgmap = NULL;
struct page *page;
spinlock_t *ptl;
pte_t *ptep, pte;
@@ -116,8 +216,8 @@
* Only return device mapping pages in the FOLL_GET case since
* they are only valid while holding the pgmap reference.
*/
- pgmap = get_dev_pagemap(pte_pfn(pte), NULL);
- if (pgmap)
+ *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
+ if (*pgmap)
page = pte_page(pte);
else
goto no_page;
@@ -153,12 +253,9 @@
}
if (flags & FOLL_GET) {
- get_page(page);
-
- /* drop the pgmap reference now that we hold the page */
- if (pgmap) {
- put_dev_pagemap(pgmap);
- pgmap = NULL;
+ if (unlikely(!try_get_page(page))) {
+ page = ERR_PTR(-ENOMEM);
+ goto out;
}
}
if (flags & FOLL_TOUCH) {
@@ -210,7 +307,8 @@
static struct page *follow_pmd_mask(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
- unsigned int flags, unsigned int *page_mask)
+ unsigned int flags,
+ struct follow_page_context *ctx)
{
pmd_t *pmd, pmdval;
spinlock_t *ptl;
@@ -258,13 +356,13 @@
}
if (pmd_devmap(pmdval)) {
ptl = pmd_lock(mm, pmd);
- page = follow_devmap_pmd(vma, address, pmd, flags);
+ page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
spin_unlock(ptl);
if (page)
return page;
}
if (likely(!pmd_trans_huge(pmdval)))
- return follow_page_pte(vma, address, pmd, flags);
+ return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
if ((flags & FOLL_NUMA) && pmd_protnone(pmdval))
return no_page_table(vma, flags);
@@ -284,9 +382,9 @@
}
if (unlikely(!pmd_trans_huge(*pmd))) {
spin_unlock(ptl);
- return follow_page_pte(vma, address, pmd, flags);
+ return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
}
- if (flags & FOLL_SPLIT) {
+ if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) {
int ret;
page = pmd_page(*pmd);
if (is_huge_zero_page(page)) {
@@ -295,8 +393,11 @@
split_huge_pmd(vma, pmd, address);
if (pmd_trans_unstable(pmd))
ret = -EBUSY;
- } else {
- get_page(page);
+ } else if (flags & FOLL_SPLIT) {
+ if (unlikely(!try_get_page(page))) {
+ spin_unlock(ptl);
+ return ERR_PTR(-ENOMEM);
+ }
spin_unlock(ptl);
lock_page(page);
ret = split_huge_page(page);
@@ -304,21 +405,25 @@
put_page(page);
if (pmd_none(*pmd))
return no_page_table(vma, flags);
+ } else { /* flags & FOLL_SPLIT_PMD */
+ spin_unlock(ptl);
+ split_huge_pmd(vma, pmd, address);
+ ret = pte_alloc(mm, pmd) ? -ENOMEM : 0;
}
return ret ? ERR_PTR(ret) :
- follow_page_pte(vma, address, pmd, flags);
+ follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
}
page = follow_trans_huge_pmd(vma, address, pmd, flags);
spin_unlock(ptl);
- *page_mask = HPAGE_PMD_NR - 1;
+ ctx->page_mask = HPAGE_PMD_NR - 1;
return page;
}
-
static struct page *follow_pud_mask(struct vm_area_struct *vma,
unsigned long address, p4d_t *p4dp,
- unsigned int flags, unsigned int *page_mask)
+ unsigned int flags,
+ struct follow_page_context *ctx)
{
pud_t *pud;
spinlock_t *ptl;
@@ -344,7 +449,7 @@
}
if (pud_devmap(*pud)) {
ptl = pud_lock(mm, pud);
- page = follow_devmap_pud(vma, address, pud, flags);
+ page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
spin_unlock(ptl);
if (page)
return page;
@@ -352,13 +457,13 @@
if (unlikely(pud_bad(*pud)))
return no_page_table(vma, flags);
- return follow_pmd_mask(vma, address, pud, flags, page_mask);
+ return follow_pmd_mask(vma, address, pud, flags, ctx);
}
-
static struct page *follow_p4d_mask(struct vm_area_struct *vma,
unsigned long address, pgd_t *pgdp,
- unsigned int flags, unsigned int *page_mask)
+ unsigned int flags,
+ struct follow_page_context *ctx)
{
p4d_t *p4d;
struct page *page;
@@ -378,7 +483,7 @@
return page;
return no_page_table(vma, flags);
}
- return follow_pud_mask(vma, address, p4d, flags, page_mask);
+ return follow_pud_mask(vma, address, p4d, flags, ctx);
}
/**
@@ -386,23 +491,29 @@
* @vma: vm_area_struct mapping @address
* @address: virtual address to look up
* @flags: flags modifying lookup behaviour
- * @page_mask: on output, *page_mask is set according to the size of the page
+ * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a
+ * pointer to output page_mask
*
* @flags can have FOLL_ flags set, defined in <linux/mm.h>
*
- * Returns the mapped (struct page *), %NULL if no mapping exists, or
+ * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
+ * the device's dev_pagemap metadata to avoid repeating expensive lookups.
+ *
+ * On output, the @ctx->page_mask is set according to the size of the page.
+ *
+ * Return: the mapped (struct page *), %NULL if no mapping exists, or
* an error pointer if there is a mapping to something not represented
* by a page descriptor (see also vm_normal_page()).
*/
-struct page *follow_page_mask(struct vm_area_struct *vma,
+static struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
- unsigned int *page_mask)
+ struct follow_page_context *ctx)
{
pgd_t *pgd;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
- *page_mask = 0;
+ ctx->page_mask = 0;
/* make this handle hugepd */
page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
@@ -431,7 +542,19 @@
return no_page_table(vma, flags);
}
- return follow_p4d_mask(vma, address, pgd, flags, page_mask);
+ return follow_p4d_mask(vma, address, pgd, flags, ctx);
+}
+
+struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
+ unsigned int foll_flags)
+{
+ struct follow_page_context ctx = { NULL };
+ struct page *page;
+
+ page = follow_page_mask(vma, address, foll_flags, &ctx);
+ if (ctx.pgmap)
+ put_dev_pagemap(ctx.pgmap);
+ return page;
}
static int get_gate_page(struct mm_struct *mm, unsigned long address,
@@ -452,11 +575,14 @@
pgd = pgd_offset_k(address);
else
pgd = pgd_offset_gate(mm, address);
- BUG_ON(pgd_none(*pgd));
+ if (pgd_none(*pgd))
+ return -EFAULT;
p4d = p4d_offset(pgd, address);
- BUG_ON(p4d_none(*p4d));
+ if (p4d_none(*p4d))
+ return -EFAULT;
pud = pud_offset(p4d, address);
- BUG_ON(pud_none(*pud));
+ if (pud_none(*pud))
+ return -EFAULT;
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return -EFAULT;
@@ -472,15 +598,11 @@
if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte)))
goto unmap;
*page = pte_page(*pte);
-
- /*
- * This should never happen (a device public page in the gate
- * area).
- */
- if (is_device_public_page(*page))
- goto unmap;
}
- get_page(*page);
+ if (unlikely(!try_get_page(*page))) {
+ ret = -ENOMEM;
+ goto unmap;
+ }
out:
ret = 0;
unmap:
@@ -659,13 +781,15 @@
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *nonblocking)
{
- long i = 0;
- unsigned int page_mask;
+ long ret = 0, i = 0;
struct vm_area_struct *vma = NULL;
+ struct follow_page_context ctx = { NULL };
if (!nr_pages)
return 0;
+ start = untagged_addr(start);
+
VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
/*
@@ -685,18 +809,19 @@
if (!vma || start >= vma->vm_end) {
vma = find_extend_vma(mm, start);
if (!vma && in_gate_area(mm, start)) {
- int ret;
ret = get_gate_page(mm, start & PAGE_MASK,
gup_flags, &vma,
pages ? &pages[i] : NULL);
if (ret)
- return i ? : ret;
- page_mask = 0;
+ goto out;
+ ctx.page_mask = 0;
goto next_page;
}
- if (!vma || check_vma_flags(vma, gup_flags))
- return i ? : -EFAULT;
+ if (!vma || check_vma_flags(vma, gup_flags)) {
+ ret = -EFAULT;
+ goto out;
+ }
if (is_vm_hugetlb_page(vma)) {
i = follow_hugetlb_page(mm, vma, pages, vmas,
&start, &nr_pages, i,
@@ -709,23 +834,26 @@
* If we have a pending SIGKILL, don't keep faulting pages and
* potentially allocating memory.
*/
- if (unlikely(fatal_signal_pending(current)))
- return i ? i : -ERESTARTSYS;
+ if (fatal_signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ goto out;
+ }
cond_resched();
- page = follow_page_mask(vma, start, foll_flags, &page_mask);
+
+ page = follow_page_mask(vma, start, foll_flags, &ctx);
if (!page) {
- int ret;
ret = faultin_page(tsk, vma, start, &foll_flags,
nonblocking);
switch (ret) {
case 0:
goto retry;
+ case -EBUSY:
+ ret = 0;
+ /* FALLTHRU */
case -EFAULT:
case -ENOMEM:
case -EHWPOISON:
- return i ? i : ret;
- case -EBUSY:
- return i;
+ goto out;
case -ENOENT:
goto next_page;
}
@@ -737,27 +865,31 @@
*/
goto next_page;
} else if (IS_ERR(page)) {
- return i ? i : PTR_ERR(page);
+ ret = PTR_ERR(page);
+ goto out;
}
if (pages) {
pages[i] = page;
flush_anon_page(vma, page, start);
flush_dcache_page(page);
- page_mask = 0;
+ ctx.page_mask = 0;
}
next_page:
if (vmas) {
vmas[i] = vma;
- page_mask = 0;
+ ctx.page_mask = 0;
}
- page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+ page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
if (page_increm > nr_pages)
page_increm = nr_pages;
i += page_increm;
start += page_increm * PAGE_SIZE;
nr_pages -= page_increm;
} while (nr_pages);
- return i;
+out:
+ if (ctx.pgmap)
+ put_dev_pagemap(ctx.pgmap);
+ return i ? i : ret;
}
static bool vma_permits_fault(struct vm_area_struct *vma,
@@ -820,6 +952,8 @@
struct vm_area_struct *vma;
vm_fault_t ret, major = 0;
+ address = untagged_addr(address);
+
if (unlocked)
fault_flags |= FAULT_FLAG_ALLOW_RETRY;
@@ -898,10 +1032,6 @@
BUG_ON(ret >= nr_pages);
}
- if (!pages)
- /* If it's a prefault don't insist harder */
- return ret;
-
if (ret > 0) {
nr_pages -= ret;
pages_done += ret;
@@ -917,8 +1047,12 @@
pages_done = ret;
break;
}
- /* VM_FAULT_RETRY triggered, so seek to the faulting offset */
- pages += ret;
+ /*
+ * VM_FAULT_RETRY triggered, so seek to the faulting offset.
+ * For the prefault case (!pages) we only update counts.
+ */
+ if (likely(pages))
+ pages += ret;
start += ret << PAGE_SHIFT;
/*
@@ -941,7 +1075,8 @@
pages_done++;
if (!nr_pages)
break;
- pages++;
+ if (likely(pages))
+ pages++;
start += PAGE_SIZE;
}
if (lock_dropped && *locked) {
@@ -956,68 +1091,6 @@
}
/*
- * We can leverage the VM_FAULT_RETRY functionality in the page fault
- * paths better by using either get_user_pages_locked() or
- * get_user_pages_unlocked().
- *
- * get_user_pages_locked() is suitable to replace the form:
- *
- * down_read(&mm->mmap_sem);
- * do_something()
- * get_user_pages(tsk, mm, ..., pages, NULL);
- * up_read(&mm->mmap_sem);
- *
- * to:
- *
- * int locked = 1;
- * down_read(&mm->mmap_sem);
- * do_something()
- * get_user_pages_locked(tsk, mm, ..., pages, &locked);
- * if (locked)
- * up_read(&mm->mmap_sem);
- */
-long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- int *locked)
-{
- return __get_user_pages_locked(current, current->mm, start, nr_pages,
- pages, NULL, locked,
- gup_flags | FOLL_TOUCH);
-}
-EXPORT_SYMBOL(get_user_pages_locked);
-
-/*
- * get_user_pages_unlocked() is suitable to replace the form:
- *
- * down_read(&mm->mmap_sem);
- * get_user_pages(tsk, mm, ..., pages, NULL);
- * up_read(&mm->mmap_sem);
- *
- * with:
- *
- * get_user_pages_unlocked(tsk, mm, ..., pages);
- *
- * It is functionally equivalent to get_user_pages_fast so
- * get_user_pages_fast should be used instead if specific gup_flags
- * (e.g. FOLL_FORCE) are not required.
- */
-long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
- struct page **pages, unsigned int gup_flags)
-{
- struct mm_struct *mm = current->mm;
- int locked = 1;
- long ret;
-
- down_read(&mm->mmap_sem);
- ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
- &locked, gup_flags | FOLL_TOUCH);
- if (locked)
- up_read(&mm->mmap_sem);
- return ret;
-}
-EXPORT_SYMBOL(get_user_pages_unlocked);
-
-/*
* get_user_pages_remote() - pin user pages in memory
* @tsk: the task_struct to use for page fault accounting, or
* NULL if faults are not to be recorded.
@@ -1078,93 +1151,21 @@
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *locked)
{
+ /*
+ * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. As there are no users of this flag in this call we simply
+ * disallow this option for now.
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+ return -EINVAL;
+
return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
locked,
gup_flags | FOLL_TOUCH | FOLL_REMOTE);
}
EXPORT_SYMBOL(get_user_pages_remote);
-/*
- * This is the same as get_user_pages_remote(), just with a
- * less-flexible calling convention where we assume that the task
- * 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.
- */
-long get_user_pages(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas)
-{
- return __get_user_pages_locked(current, current->mm, start, nr_pages,
- pages, vmas, NULL,
- gup_flags | FOLL_TOUCH);
-}
-EXPORT_SYMBOL(get_user_pages);
-
-#ifdef CONFIG_FS_DAX
-/*
- * This is the same as get_user_pages() in that it assumes we are
- * operating on the current task's mm, but it goes further to validate
- * that the vmas associated with the address range are suitable for
- * longterm elevated page reference counts. For example, filesystem-dax
- * mappings are subject to the lifetime enforced by the filesystem and
- * we need guarantees that longterm users like RDMA and V4L2 only
- * establish mappings that have a kernel enforced revocation mechanism.
- *
- * "longterm" == userspace controlled elevated page count lifetime.
- * Contrast this to iov_iter_get_pages() usages which are transient.
- */
-long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas_arg)
-{
- struct vm_area_struct **vmas = vmas_arg;
- struct vm_area_struct *vma_prev = NULL;
- long rc, i;
-
- if (!pages)
- return -EINVAL;
-
- if (!vmas) {
- vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *),
- GFP_KERNEL);
- if (!vmas)
- return -ENOMEM;
- }
-
- rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
-
- for (i = 0; i < rc; i++) {
- struct vm_area_struct *vma = vmas[i];
-
- if (vma == vma_prev)
- continue;
-
- vma_prev = vma;
-
- if (vma_is_fsdax(vma))
- break;
- }
-
- /*
- * Either get_user_pages() failed, or the vma validation
- * succeeded, in either case we don't need to put_page() before
- * returning.
- */
- if (i >= rc)
- goto out;
-
- for (i = 0; i < rc; i++)
- put_page(pages[i]);
- rc = -EOPNOTSUPP;
-out:
- if (vmas != vmas_arg)
- kfree(vmas);
- return rc;
-}
-EXPORT_SYMBOL(get_user_pages_longterm);
-#endif /* CONFIG_FS_DAX */
-
/**
* populate_vma_page_range() - populate a range of pages in the vma.
* @vma: target vma
@@ -1311,9 +1312,389 @@
return page;
}
#endif /* CONFIG_ELF_CORE */
+#else /* CONFIG_MMU */
+static long __get_user_pages_locked(struct task_struct *tsk,
+ struct mm_struct *mm, unsigned long start,
+ unsigned long nr_pages, struct page **pages,
+ struct vm_area_struct **vmas, int *locked,
+ unsigned int foll_flags)
+{
+ struct vm_area_struct *vma;
+ unsigned long vm_flags;
+ int i;
+
+ /* calculate required read or write permissions.
+ * If FOLL_FORCE is set, we only require the "MAY" flags.
+ */
+ vm_flags = (foll_flags & FOLL_WRITE) ?
+ (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+ vm_flags &= (foll_flags & FOLL_FORCE) ?
+ (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+
+ for (i = 0; i < nr_pages; i++) {
+ vma = find_vma(mm, start);
+ if (!vma)
+ goto finish_or_fault;
+
+ /* protect what we can, including chardevs */
+ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
+ !(vm_flags & vma->vm_flags))
+ goto finish_or_fault;
+
+ if (pages) {
+ pages[i] = virt_to_page(start);
+ if (pages[i])
+ get_page(pages[i]);
+ }
+ if (vmas)
+ vmas[i] = vma;
+ start = (start + PAGE_SIZE) & PAGE_MASK;
+ }
+
+ return i;
+
+finish_or_fault:
+ return i ? : -EFAULT;
+}
+#endif /* !CONFIG_MMU */
+
+#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
+static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
+{
+ long i;
+ struct vm_area_struct *vma_prev = NULL;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct vm_area_struct *vma = vmas[i];
+
+ if (vma == vma_prev)
+ continue;
+
+ vma_prev = vma;
+
+ if (vma_is_fsdax(vma))
+ return true;
+ }
+ return false;
+}
+
+#ifdef CONFIG_CMA
+static struct page *new_non_cma_page(struct page *page, unsigned long private)
+{
+ /*
+ * We want to make sure we allocate the new page from the same node
+ * as the source page.
+ */
+ int nid = page_to_nid(page);
+ /*
+ * Trying to allocate a page for migration. Ignore allocation
+ * failure warnings. We don't force __GFP_THISNODE here because
+ * this node here is the node where we have CMA reservation and
+ * in some case these nodes will have really less non movable
+ * allocation memory.
+ */
+ gfp_t gfp_mask = GFP_USER | __GFP_NOWARN;
+
+ if (PageHighMem(page))
+ gfp_mask |= __GFP_HIGHMEM;
+
+#ifdef CONFIG_HUGETLB_PAGE
+ if (PageHuge(page)) {
+ struct hstate *h = page_hstate(page);
+ /*
+ * We don't want to dequeue from the pool because pool pages will
+ * mostly be from the CMA region.
+ */
+ return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
+ }
+#endif
+ if (PageTransHuge(page)) {
+ struct page *thp;
+ /*
+ * ignore allocation failure warnings
+ */
+ gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_NOWARN;
+
+ /*
+ * Remove the movable mask so that we don't allocate from
+ * CMA area again.
+ */
+ thp_gfpmask &= ~__GFP_MOVABLE;
+ thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
+ if (!thp)
+ return NULL;
+ prep_transhuge_page(thp);
+ return thp;
+ }
+
+ return __alloc_pages_node(nid, gfp_mask, 0);
+}
+
+static long check_and_migrate_cma_pages(struct task_struct *tsk,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int gup_flags)
+{
+ unsigned long i;
+ unsigned long step;
+ bool drain_allow = true;
+ bool migrate_allow = true;
+ LIST_HEAD(cma_page_list);
+
+check_again:
+ for (i = 0; i < nr_pages;) {
+
+ struct page *head = compound_head(pages[i]);
+
+ /*
+ * gup may start from a tail page. Advance step by the left
+ * part.
+ */
+ step = compound_nr(head) - (pages[i] - head);
+ /*
+ * If we get a page from the CMA zone, since we are going to
+ * be pinning these entries, we might as well move them out
+ * of the CMA zone if possible.
+ */
+ if (is_migrate_cma_page(head)) {
+ if (PageHuge(head))
+ isolate_huge_page(head, &cma_page_list);
+ else {
+ if (!PageLRU(head) && drain_allow) {
+ lru_add_drain_all();
+ drain_allow = false;
+ }
+
+ if (!isolate_lru_page(head)) {
+ list_add_tail(&head->lru, &cma_page_list);
+ mod_node_page_state(page_pgdat(head),
+ NR_ISOLATED_ANON +
+ page_is_file_cache(head),
+ hpage_nr_pages(head));
+ }
+ }
+ }
+
+ i += step;
+ }
+
+ if (!list_empty(&cma_page_list)) {
+ /*
+ * drop the above get_user_pages reference.
+ */
+ for (i = 0; i < nr_pages; i++)
+ put_page(pages[i]);
+
+ if (migrate_pages(&cma_page_list, new_non_cma_page,
+ NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
+ /*
+ * some of the pages failed migration. Do get_user_pages
+ * without migration.
+ */
+ migrate_allow = false;
+
+ if (!list_empty(&cma_page_list))
+ putback_movable_pages(&cma_page_list);
+ }
+ /*
+ * We did migrate all the pages, Try to get the page references
+ * again migrating any new CMA pages which we failed to isolate
+ * earlier.
+ */
+ nr_pages = __get_user_pages_locked(tsk, mm, start, nr_pages,
+ pages, vmas, NULL,
+ gup_flags);
+
+ if ((nr_pages > 0) && migrate_allow) {
+ drain_allow = true;
+ goto check_again;
+ }
+ }
+
+ return nr_pages;
+}
+#else
+static long check_and_migrate_cma_pages(struct task_struct *tsk,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int gup_flags)
+{
+ return nr_pages;
+}
+#endif /* CONFIG_CMA */
/*
- * Generic Fast GUP
+ * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
+ * allows us to process the FOLL_LONGTERM flag.
+ */
+static long __gup_longterm_locked(struct task_struct *tsk,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int gup_flags)
+{
+ struct vm_area_struct **vmas_tmp = vmas;
+ unsigned long flags = 0;
+ long rc, i;
+
+ if (gup_flags & FOLL_LONGTERM) {
+ if (!pages)
+ return -EINVAL;
+
+ if (!vmas_tmp) {
+ vmas_tmp = kcalloc(nr_pages,
+ sizeof(struct vm_area_struct *),
+ GFP_KERNEL);
+ if (!vmas_tmp)
+ return -ENOMEM;
+ }
+ flags = memalloc_nocma_save();
+ }
+
+ rc = __get_user_pages_locked(tsk, mm, start, nr_pages, pages,
+ vmas_tmp, NULL, gup_flags);
+
+ if (gup_flags & FOLL_LONGTERM) {
+ memalloc_nocma_restore(flags);
+ if (rc < 0)
+ goto out;
+
+ if (check_dax_vmas(vmas_tmp, rc)) {
+ for (i = 0; i < rc; i++)
+ put_page(pages[i]);
+ rc = -EOPNOTSUPP;
+ goto out;
+ }
+
+ rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
+ vmas_tmp, gup_flags);
+ }
+
+out:
+ if (vmas_tmp != vmas)
+ kfree(vmas_tmp);
+ return rc;
+}
+#else /* !CONFIG_FS_DAX && !CONFIG_CMA */
+static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int flags)
+{
+ return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+ NULL, flags);
+}
+#endif /* CONFIG_FS_DAX || CONFIG_CMA */
+
+/*
+ * This is the same as get_user_pages_remote(), just with a
+ * less-flexible calling convention where we assume that the task
+ * 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.
+ */
+long get_user_pages(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas)
+{
+ return __gup_longterm_locked(current, current->mm, start, nr_pages,
+ pages, vmas, gup_flags | FOLL_TOUCH);
+}
+EXPORT_SYMBOL(get_user_pages);
+
+/*
+ * We can leverage the VM_FAULT_RETRY functionality in the page fault
+ * paths better by using either get_user_pages_locked() or
+ * get_user_pages_unlocked().
+ *
+ * get_user_pages_locked() is suitable to replace the form:
+ *
+ * down_read(&mm->mmap_sem);
+ * do_something()
+ * get_user_pages(tsk, mm, ..., pages, NULL);
+ * up_read(&mm->mmap_sem);
+ *
+ * to:
+ *
+ * int locked = 1;
+ * down_read(&mm->mmap_sem);
+ * do_something()
+ * get_user_pages_locked(tsk, mm, ..., pages, &locked);
+ * if (locked)
+ * up_read(&mm->mmap_sem);
+ */
+long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ int *locked)
+{
+ /*
+ * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. As there are no users of this flag in this call we simply
+ * disallow this option for now.
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+ return -EINVAL;
+
+ return __get_user_pages_locked(current, current->mm, start, nr_pages,
+ pages, NULL, locked,
+ gup_flags | FOLL_TOUCH);
+}
+EXPORT_SYMBOL(get_user_pages_locked);
+
+/*
+ * get_user_pages_unlocked() is suitable to replace the form:
+ *
+ * down_read(&mm->mmap_sem);
+ * get_user_pages(tsk, mm, ..., pages, NULL);
+ * up_read(&mm->mmap_sem);
+ *
+ * with:
+ *
+ * get_user_pages_unlocked(tsk, mm, ..., pages);
+ *
+ * It is functionally equivalent to get_user_pages_fast so
+ * get_user_pages_fast should be used instead if specific gup_flags
+ * (e.g. FOLL_FORCE) are not required.
+ */
+long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
+ struct page **pages, unsigned int gup_flags)
+{
+ struct mm_struct *mm = current->mm;
+ int locked = 1;
+ long ret;
+
+ /*
+ * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. As there are no users of this flag in this call we simply
+ * disallow this option for now.
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+ return -EINVAL;
+
+ down_read(&mm->mmap_sem);
+ ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
+ &locked, gup_flags | FOLL_TOUCH);
+ if (locked)
+ up_read(&mm->mmap_sem);
+ return ret;
+}
+EXPORT_SYMBOL(get_user_pages_unlocked);
+
+/*
+ * Fast GUP
*
* get_user_pages_fast attempts to pin user pages by walking the page
* tables directly and avoids taking locks. Thus the walker needs to be
@@ -1345,20 +1726,64 @@
*
* This code is based heavily on the PowerPC implementation by Nick Piggin.
*/
-#ifdef CONFIG_HAVE_GENERIC_GUP
-
-#ifndef gup_get_pte
+#ifdef CONFIG_HAVE_FAST_GUP
+#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
/*
- * We assume that the PTE can be read atomically. If this is not the case for
- * your architecture, please provide the helper.
+ * WARNING: only to be used in the get_user_pages_fast() implementation.
+ *
+ * With get_user_pages_fast(), we walk down the pagetables without taking any
+ * locks. For this we would like to load the pointers atomically, but sometimes
+ * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE). What
+ * we do have is the guarantee that a PTE will only either go from not present
+ * to present, or present to not present or both -- it will not switch to a
+ * completely different present page without a TLB flush in between; something
+ * that we are blocking by holding interrupts off.
+ *
+ * Setting ptes from not present to present goes:
+ *
+ * ptep->pte_high = h;
+ * smp_wmb();
+ * ptep->pte_low = l;
+ *
+ * And present to not present goes:
+ *
+ * ptep->pte_low = 0;
+ * smp_wmb();
+ * ptep->pte_high = 0;
+ *
+ * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'.
+ * We load pte_high *after* loading pte_low, which ensures we don't see an older
+ * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't
+ * picked up a changed pte high. We might have gotten rubbish values from
+ * pte_low and pte_high, but we are guaranteed that pte_low will not have the
+ * present bit set *unless* it is 'l'. Because get_user_pages_fast() only
+ * operates on present ptes we're safe.
+ */
+static inline pte_t gup_get_pte(pte_t *ptep)
+{
+ pte_t pte;
+
+ do {
+ pte.pte_low = ptep->pte_low;
+ smp_rmb();
+ pte.pte_high = ptep->pte_high;
+ smp_rmb();
+ } while (unlikely(pte.pte_low != ptep->pte_low));
+
+ return pte;
+}
+#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */
+/*
+ * We require that the PTE can be read atomically.
*/
static inline pte_t gup_get_pte(pte_t *ptep)
{
return READ_ONCE(*ptep);
}
-#endif
+#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */
-static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
+static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
+ struct page **pages)
{
while ((*nr) - nr_start) {
struct page *page = pages[--(*nr)];
@@ -1368,9 +1793,23 @@
}
}
+/*
+ * 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,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
struct dev_pagemap *pgmap = NULL;
int nr_start = *nr, ret = 0;
@@ -1388,10 +1827,13 @@
if (pte_protnone(pte))
goto pte_unmap;
- if (!pte_access_permitted(pte, write))
+ if (!pte_access_permitted(pte, flags & FOLL_WRITE))
goto pte_unmap;
if (pte_devmap(pte)) {
+ if (unlikely(flags & FOLL_LONGTERM))
+ goto pte_unmap;
+
pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
if (unlikely(!pgmap)) {
undo_dev_pagemap(nr, nr_start, pages);
@@ -1402,9 +1844,9 @@
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ head = try_get_compound_head(page, 1);
+ if (!head)
goto pte_unmap;
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
@@ -1440,13 +1882,13 @@
* useful to have gup_huge_pmd even if we can't operate on ptes.
*/
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
return 0;
}
#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
-#if defined(__HAVE_ARCH_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+#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)
{
@@ -1522,17 +1964,106 @@
}
#endif
+#ifdef CONFIG_ARCH_HAS_HUGEPD
+static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
+ unsigned long sz)
+{
+ unsigned long __boundary = (addr + sz) & ~(sz-1);
+ return (__boundary - 1 < end - 1) ? __boundary : end;
+}
+
+static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
+{
+ unsigned long pte_end;
+ struct page *head, *page;
+ pte_t pte;
+ int refs;
+
+ pte_end = (addr + sz) & ~(sz-1);
+ if (pte_end < end)
+ end = pte_end;
+
+ pte = READ_ONCE(*ptep);
+
+ if (!pte_access_permitted(pte, flags & FOLL_WRITE))
+ return 0;
+
+ /* 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);
+
+ head = try_get_compound_head(head, refs);
+ if (!head) {
+ *nr -= refs;
+ return 0;
+ }
+
+ if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+ /* Could be optimized better */
+ *nr -= refs;
+ while (refs--)
+ put_page(head);
+ return 0;
+ }
+
+ SetPageReferenced(head);
+ return 1;
+}
+
+static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+ unsigned int pdshift, unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
+{
+ pte_t *ptep;
+ unsigned long sz = 1UL << hugepd_shift(hugepd);
+ unsigned long next;
+
+ ptep = hugepte_offset(hugepd, addr, pdshift);
+ do {
+ next = hugepte_addr_end(addr, end, sz);
+ if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr))
+ return 0;
+ } while (ptep++, addr = next, addr != end);
+
+ return 1;
+}
+#else
+static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+ unsigned int pdshift, unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
+{
+ return 0;
+}
+#endif /* CONFIG_ARCH_HAS_HUGEPD */
+
static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
struct page *head, *page;
int refs;
- if (!pmd_access_permitted(orig, write))
+ if (!pmd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
- if (pmd_devmap(orig))
+ if (pmd_devmap(orig)) {
+ if (unlikely(flags & FOLL_LONGTERM))
+ return 0;
return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
+ }
refs = 0;
page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
@@ -1543,8 +2074,8 @@
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pmd_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pmd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1561,16 +2092,19 @@
}
static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags, struct page **pages, int *nr)
{
struct page *head, *page;
int refs;
- if (!pud_access_permitted(orig, write))
+ if (!pud_access_permitted(orig, flags & FOLL_WRITE))
return 0;
- if (pud_devmap(orig))
+ if (pud_devmap(orig)) {
+ if (unlikely(flags & FOLL_LONGTERM))
+ return 0;
return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
+ }
refs = 0;
page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
@@ -1581,8 +2115,8 @@
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pud_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pud_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1599,13 +2133,13 @@
}
static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
- unsigned long end, int write,
+ unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
int refs;
struct page *head, *page;
- if (!pgd_access_permitted(orig, write))
+ if (!pgd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
BUILD_BUG_ON(pgd_devmap(orig));
@@ -1618,8 +2152,8 @@
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pgd_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pgd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1636,7 +2170,7 @@
}
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pmd_t *pmdp;
@@ -1649,7 +2183,8 @@
if (!pmd_present(pmd))
return 0;
- if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) {
+ if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) ||
+ pmd_devmap(pmd))) {
/*
* NUMA hinting faults need to be handled in the GUP
* slowpath for accounting purposes and so that they
@@ -1658,7 +2193,7 @@
if (pmd_protnone(pmd))
return 0;
- if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
+ if (!gup_huge_pmd(pmd, pmdp, addr, next, flags,
pages, nr))
return 0;
@@ -1668,9 +2203,9 @@
* pmd format and THP pmd format
*/
if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
- PMD_SHIFT, next, write, pages, nr))
+ PMD_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+ } else if (!gup_pte_range(pmd, addr, next, flags, pages, nr))
return 0;
} while (pmdp++, addr = next, addr != end);
@@ -1678,7 +2213,7 @@
}
static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
@@ -1691,14 +2226,14 @@
if (pud_none(pud))
return 0;
if (unlikely(pud_huge(pud))) {
- if (!gup_huge_pud(pud, pudp, addr, next, write,
+ if (!gup_huge_pud(pud, pudp, addr, next, flags,
pages, nr))
return 0;
} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
- PUD_SHIFT, next, write, pages, nr))
+ PUD_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+ } else if (!gup_pmd_range(pud, addr, next, flags, pages, nr))
return 0;
} while (pudp++, addr = next, addr != end);
@@ -1706,7 +2241,7 @@
}
static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
p4d_t *p4dp;
@@ -1721,9 +2256,9 @@
BUILD_BUG_ON(p4d_huge(p4d));
if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
- P4D_SHIFT, next, write, pages, nr))
+ P4D_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pud_range(p4d, addr, next, write, pages, nr))
+ } else if (!gup_pud_range(p4d, addr, next, flags, pages, nr))
return 0;
} while (p4dp++, addr = next, addr != end);
@@ -1731,7 +2266,7 @@
}
static void gup_pgd_range(unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pgd_t *pgdp;
@@ -1744,30 +2279,32 @@
if (pgd_none(pgd))
return;
if (unlikely(pgd_huge(pgd))) {
- if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+ if (!gup_huge_pgd(pgd, pgdp, addr, next, flags,
pages, nr))
return;
} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
- PGDIR_SHIFT, next, write, pages, nr))
+ PGDIR_SHIFT, next, flags, pages, nr))
return;
- } else if (!gup_p4d_range(pgd, addr, next, write, pages, nr))
+ } else if (!gup_p4d_range(pgd, addr, next, flags, pages, nr))
return;
} while (pgdp++, addr = next, addr != end);
}
+#else
+static inline void gup_pgd_range(unsigned long addr, unsigned long end,
+ unsigned int flags, struct page **pages, int *nr)
+{
+}
+#endif /* CONFIG_HAVE_FAST_GUP */
#ifndef gup_fast_permitted
/*
* Check if it's allowed to use __get_user_pages_fast() for the range, or
* we need to fall back to the slow version:
*/
-bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
+static bool gup_fast_permitted(unsigned long start, unsigned long end)
{
- unsigned long len, end;
-
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
- return end >= start;
+ return true;
}
#endif
@@ -1776,21 +2313,24 @@
* the regular GUP.
* Note a difference with get_user_pages_fast: this always returns the
* number of pages pinned, 0 if no pages were pinned.
+ *
+ * If the architecture does not support this function, simply return with no
+ * pages pinned.
*/
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages)
{
- unsigned long addr, len, end;
+ unsigned long len, end;
unsigned long flags;
int nr = 0;
- start &= PAGE_MASK;
- addr = start;
+ start = untagged_addr(start) & PAGE_MASK;
len = (unsigned long) nr_pages << PAGE_SHIFT;
end = start + len;
- if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
- (void __user *)start, len)))
+ if (end <= start)
+ return 0;
+ if (unlikely(!access_ok((void __user *)start, len)))
return 0;
/*
@@ -1798,27 +2338,52 @@
* interrupts disabled by get_futex_key.
*
* With interrupts disabled, we block page table pages from being
- * freed from under us. See mmu_gather_tlb in asm-generic/tlb.h
- * for more details.
+ * freed from under us. See struct mmu_table_batch comments in
+ * include/asm-generic/tlb.h for more details.
*
* We do not adopt an rcu_read_lock(.) here as we also want to
* block IPIs that come from THPs splitting.
*/
- if (gup_fast_permitted(start, nr_pages, write)) {
+ if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) &&
+ gup_fast_permitted(start, end)) {
local_irq_save(flags);
- gup_pgd_range(addr, end, write, pages, &nr);
+ gup_pgd_range(start, end, write ? FOLL_WRITE : 0, pages, &nr);
local_irq_restore(flags);
}
return nr;
}
+EXPORT_SYMBOL_GPL(__get_user_pages_fast);
+
+static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
+{
+ int ret;
+
+ /*
+ * FIXME: FOLL_LONGTERM does not work with
+ * get_user_pages_unlocked() (see comments in that function)
+ */
+ if (gup_flags & FOLL_LONGTERM) {
+ down_read(¤t->mm->mmap_sem);
+ ret = __gup_longterm_locked(current, current->mm,
+ start, nr_pages,
+ pages, NULL, gup_flags);
+ up_read(¤t->mm->mmap_sem);
+ } else {
+ ret = get_user_pages_unlocked(start, nr_pages,
+ pages, gup_flags);
+ }
+
+ return ret;
+}
/**
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to
+ * @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
@@ -1830,27 +2395,29 @@
* 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, int write,
- struct page **pages)
+int 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;
- start &= PAGE_MASK;
+ if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM)))
+ return -EINVAL;
+
+ start = untagged_addr(start) & PAGE_MASK;
addr = start;
len = (unsigned long) nr_pages << PAGE_SHIFT;
end = start + len;
- if (nr_pages <= 0)
+ if (end <= start)
return 0;
-
- if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
- (void __user *)start, len)))
+ if (unlikely(!access_ok((void __user *)start, len)))
return -EFAULT;
- if (gup_fast_permitted(start, nr_pages, write)) {
+ if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) &&
+ gup_fast_permitted(start, end)) {
local_irq_disable();
- gup_pgd_range(addr, end, write, pages, &nr);
+ gup_pgd_range(addr, end, gup_flags, pages, &nr);
local_irq_enable();
ret = nr;
}
@@ -1860,8 +2427,8 @@
start += nr << PAGE_SHIFT;
pages += nr;
- ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
- write ? FOLL_WRITE : 0);
+ ret = __gup_longterm_unlocked(start, nr_pages - nr,
+ gup_flags, pages);
/* Have to be a bit careful with return values */
if (nr > 0) {
@@ -1874,5 +2441,4 @@
return ret;
}
-
-#endif /* CONFIG_HAVE_GENERIC_GUP */
+EXPORT_SYMBOL_GPL(get_user_pages_fast);