mm: add get_kernel_page[s] for pinning of kernel addresses for I/O

This patch adds two new APIs get_kernel_pages() and get_kernel_page() that
may be used to pin a vector of kernel addresses for IO.  The initial user
is expected to be NFS for allowing pages to be written to swap using
aops->direct_IO().  Strictly speaking, swap-over-NFS only needs to pin one
page for IO but it makes sense to express the API in terms of a vector and
add a helper for pinning single pages.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Xiaotian Feng <dfeng@redhat.com>
Cc: Mark Salter <msalter@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 61 insertions, 0 deletions

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 0edb65dd8edd..7b7ac9ccec7a 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -160,6 +160,7 @@ enum rq_flag_bits {
         __REQ_FLUSH_SEQ,        /* request for flush sequence */
         __REQ_IO_STAT,          /* account I/O stat */
         __REQ_MIXED_MERGE,      /* merge of different types, fail separately */
+        __REQ_KERNEL,           /* direct IO to kernel pages */
         __REQ_NR_BITS,          /* stops here */
 };
 
@@ -201,5 +202,6 @@ enum rq_flag_bits {
 #define REQ_IO_STAT             (1 << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE         (1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE              (1 << __REQ_SECURE)
+#define REQ_KERNEL              (1 << __REQ_KERNEL)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8fabb037a48d..9d77309da153 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -165,6 +165,8 @@ struct inodes_stat_t {
 #define READ                    0
 #define WRITE                   RW_MASK
 #define READA                   RWA_MASK
+#define KERNEL_READ             (READ|REQ_KERNEL)
+#define KERNEL_WRITE            (WRITE|REQ_KERNEL)
 
 #define READ_SYNC               (READ | REQ_SYNC)
 #define WRITE_SYNC              (WRITE | REQ_SYNC | REQ_NOIDLE)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7cdac1676b59..bd079a1b0fdc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1019,6 +1019,10 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                         struct page **pages, struct vm_area_struct **vmas);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
                         struct page **pages);
+struct kvec;
+int get_kernel_pages(const struct kvec *iov, int nr_pages, int write,
+                        struct page **pages);
+int get_kernel_page(unsigned long start, int write, struct page **pages);
 struct page *get_dump_page(unsigned long addr);
 
 extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
diff --git a/mm/swap.c b/mm/swap.c
index 4e7e2ec67078..7d7f80c8044a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -236,6 +236,59 @@ void put_pages_list(struct list_head *pages)
 }
 EXPORT_SYMBOL(put_pages_list);
 
+/*
+ * get_kernel_pages() - pin kernel pages in memory
+ * @kiov:       An array of struct kvec structures
+ * @nr_segs:    number of segments to pin
+ * @write:      pinning for read/write, currently ignored
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at least nr_segs long.
+ *
+ * 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. Each page returned must be released
+ * with a put_page() call when it is finished with.
+ */
+int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
+                struct page **pages)
+{
+        int seg;
+
+        for (seg = 0; seg < nr_segs; seg++) {
+                if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE))
+                        return seg;
+
+                /* virt_to_page sanity checks the PFN */
+                pages[seg] = virt_to_page(kiov[seg].iov_base);
+                page_cache_get(pages[seg]);
+        }
+
+        return seg;
+}
+EXPORT_SYMBOL_GPL(get_kernel_pages);
+
+/*
+ * get_kernel_page() - pin a kernel page in memory
+ * @start:      starting kernel address
+ * @write:      pinning for read/write, currently ignored
+ * @pages:      array that receives pointer to the page pinned.
+ *              Must be at least nr_segs long.
+ *
+ * Returns 1 if page is pinned. If the page was not pinned, returns
+ * -errno. The page returned must be released with a put_page() call
+ * when it is finished with.
+ */
+int get_kernel_page(unsigned long start, int write, struct page **pages)
+{
+        const struct kvec kiov = {
+                .iov_base = (void *)start,
+                .iov_len = PAGE_SIZE
+        };
+
+        return get_kernel_pages(&kiov, 1, write, pages);
+}
+EXPORT_SYMBOL_GPL(get_kernel_page);
+
 static void pagevec_lru_move_fn(struct pagevec *pvec,
         void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg),
         void *arg)