summaryrefslogtreecommitdiff
path: root/mm/gup.c
diff options
context:
space:
mode:
authorJason Gunthorpe <jgg@nvidia.com>2020-12-15 06:05:41 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-12-15 23:13:39 +0300
commitc28b1fc70390df32e29991eedd52bd86e7aba080 (patch)
treed3c3e5671bfbd3e82cf87af0cb7f0c7e7764f2da /mm/gup.c
parentd0de82411864c4e1f24aaa3a653c7c08dd55c8d0 (diff)
downloadlinux-c28b1fc70390df32e29991eedd52bd86e7aba080.tar.xz
mm/gup: reorganize internal_get_user_pages_fast()
Patch series "Add a seqcount between gup_fast and copy_page_range()", v4. As discussed and suggested by Linus use a seqcount to close the small race between gup_fast and copy_page_range(). Ahmed confirms that raw_write_seqcount_begin() is the correct API to use in this case and it doesn't trigger any lockdeps. I was able to test it using two threads, one forking and the other using ibv_reg_mr() to trigger GUP fast. Modifying copy_page_range() to sleep made the window large enough to reliably hit to test the logic. This patch (of 2): The next patch in this series makes the lockless flow a little more complex, so move the entire block into a new function and remove a level of indention. Tidy a bit of cruft: - addr is always the same as start, so use start - Use the modern check_add_overflow() for computing end = start + len - nr_pinned/pages << PAGE_SHIFT needs the LHS to be unsigned long to avoid shift overflow, make the variables unsigned long to avoid coding casts in both places. nr_pinned was missing its cast - The handling of ret and nr_pinned can be streamlined a bit No functional change. Link: https://lkml.kernel.org/r/0-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com Link: https://lkml.kernel.org/r/1-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Reviewed-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/gup.c')
-rw-r--r--mm/gup.c99
1 files changed, 54 insertions, 45 deletions
diff --git a/mm/gup.c b/mm/gup.c
index 98eb8e6d2609..c7e24301860a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2677,13 +2677,43 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
return ret;
}
-static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
+static unsigned long lockless_pages_from_mm(unsigned long start,
+ unsigned long end,
+ unsigned int gup_flags,
+ struct page **pages)
+{
+ unsigned long flags;
+ int nr_pinned = 0;
+
+ if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) ||
+ !gup_fast_permitted(start, end))
+ return 0;
+
+ /*
+ * Disable interrupts. The nested form is used, in order to allow full,
+ * general purpose use of this routine.
+ *
+ * With interrupts disabled, we block page table pages from being 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.
+ */
+ local_irq_save(flags);
+ gup_pgd_range(start, end, gup_flags, pages, &nr_pinned);
+ local_irq_restore(flags);
+ return nr_pinned;
+}
+
+static int internal_get_user_pages_fast(unsigned long start,
+ unsigned long nr_pages,
unsigned int gup_flags,
struct page **pages)
{
- unsigned long addr, len, end;
- unsigned long flags;
- int nr_pinned = 0, ret = 0;
+ unsigned long len, end;
+ unsigned long nr_pinned;
+ int ret;
if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
FOLL_FORCE | FOLL_PIN | FOLL_GET |
@@ -2697,54 +2727,33 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
might_lock_read(&current->mm->mmap_lock);
start = untagged_addr(start) & PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
-
- if (end <= start)
+ len = nr_pages << PAGE_SHIFT;
+ if (check_add_overflow(start, len, &end))
return 0;
if (unlikely(!access_ok((void __user *)start, len)))
return -EFAULT;
- /*
- * Disable interrupts. The nested form is used, in order to allow
- * full, general purpose use of this routine.
- *
- * With interrupts disabled, we block page table pages from being
- * 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 (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && gup_fast_permitted(start, end)) {
- unsigned long fast_flags = gup_flags;
-
- local_irq_save(flags);
- gup_pgd_range(addr, end, fast_flags, pages, &nr_pinned);
- local_irq_restore(flags);
- ret = nr_pinned;
- }
-
- if (nr_pinned < nr_pages && !(gup_flags & FOLL_FAST_ONLY)) {
- /* Try to get the remaining pages with get_user_pages */
- start += nr_pinned << PAGE_SHIFT;
- pages += nr_pinned;
+ nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages);
+ if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY)
+ return nr_pinned;
- ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned,
- gup_flags, pages);
-
- /* Have to be a bit careful with return values */
- if (nr_pinned > 0) {
- if (ret < 0)
- ret = nr_pinned;
- else
- ret += nr_pinned;
- }
+ /* Slow path: try to get the remaining pages with get_user_pages */
+ start += nr_pinned << PAGE_SHIFT;
+ pages += nr_pinned;
+ ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned, gup_flags,
+ pages);
+ if (ret < 0) {
+ /*
+ * The caller has to unpin the pages we already pinned so
+ * returning -errno is not an option
+ */
+ if (nr_pinned)
+ return nr_pinned;
+ return ret;
}
-
- return ret;
+ return ret + nr_pinned;
}
+
/**
* get_user_pages_fast_only() - pin user pages in memory
* @start: starting user address