[PATCH 62/91] [PATCH] x86, mm: Add __get_user_pages_fast()

From: Willy Tarreau
Date: Sun Feb 05 2012 - 17:27:47 EST


2.6.27-longterm review patch. If anyone has any objections, please let us know.

------------------

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@xxxxxxxxx>
CC: Nick Piggin <npiggin@xxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
---
arch/x86/mm/gup.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++
include/linux/mm.h | 6 +++++
2 files changed, 62 insertions(+), 0 deletions(-)

Index: longterm-2.6.27/arch/x86/mm/gup.c
===================================================================
--- longterm-2.6.27.orig/arch/x86/mm/gup.c 2012-02-05 22:34:33.105915236 +0100
+++ longterm-2.6.27/arch/x86/mm/gup.c 2012-02-05 22:34:43.693914996 +0100
@@ -219,6 +219,62 @@
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)
{
Index: longterm-2.6.27/include/linux/mm.h
===================================================================
--- longterm-2.6.27.orig/include/linux/mm.h 2012-02-05 22:34:33.099915218 +0100
+++ longterm-2.6.27/include/linux/mm.h 2012-02-05 22:34:43.701916289 +0100
@@ -850,6 +850,12 @@
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


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/