x86, mm: Add __get_user_pages_fast()

Introduce a gup_fast() variant which is usable from IRQ/NMI context.

[ WT: this one is only needed for next patch ]

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
CC: Nick Piggin <npiggin@suse.de>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Willy Tarreau <w@1wt.eu>

2 files changed, 62 insertions, 0 deletions

diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 73e6ce1597b..5e5ea8be1d5 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -219,6 +219,62 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+/*
+ * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
+ * back to the regular GUP.
+ */
+int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			  struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next;
+	unsigned long flags;
+	pgd_t *pgdp;
+	int nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+					(void __user *)start, len)))
+		return 0;
+
+	/*
+	 * XXX: batch / limit 'nr', to avoid large irq off latency
+	 * needs some instrumenting to determine the common sizes used by
+	 * important workloads (eg. DB2), and whether limiting the batch size
+	 * will decrease performance.
+	 *
+	 * It seems like we're in the clear for the moment. Direct-IO is
+	 * the main guy that batches up lots of get_user_pages, and even
+	 * they are limited to 64-at-a-time which is not so many.
+	 */
+	/*
+	 * This doesn't prevent pagetable teardown, but does prevent
+	 * the pagetables and pages from being freed on x86.
+	 *
+	 * So long as we atomically load page table pointers versus teardown
+	 * (which we do on x86, with the above PAE exception), we can follow the
+	 * address down to the the page and take a ref on it.
+	 */
+	local_irq_save(flags);
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			break;
+		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+			break;
+	} while (pgdp++, addr = next, addr != end);
+	local_irq_restore(flags);
+
+	return nr;
+}
+
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c20007caa48..4d34c201615 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -850,6 +850,12 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
 
 /*
+ * doesn't attempt to fault and will return short.
+ */
+int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			  struct page **pages);
+
+/*
  * A callback you can register to apply pressure to ageable caches.
  *
  * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'.  It should