block/xen-blkback: Make it running on 64KB page granularity

The PV block protocol is using 4KB page granularity. The goal of this
patch is to allow a Linux using 64KB page granularity behaving as a
block backend on a non-modified Xen.

It's only necessary to adapt the ring size and the number of request per
indirect frames. The rest of the code is relying on the grant table
code.

Note that the grant table code is allocating a Linux page per grant
which will result to waste 6OKB for every grant when Linux is using 64KB
page granularity. This could be improved by sharing the page between
multiple grants.

Signed-off-by: Julien Grall <julien.grall@citrix.com>
Acked-by: "Roger Pau Monné" <roger.pau@citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
(cherry picked from commit 67de5dfbc176ea86ab0278658b5d55f64207ff2d)
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>

diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 954c0029fb3babc49d1a1f490f9d420934701e30..802319ab896b667a8860476fd1467e20d2420b6f 100644 (file)
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -961,7 +961,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req,
                seg[n].nsec = segments[i].last_sect -
                        segments[i].first_sect + 1;
                seg[n].offset = (segments[i].first_sect << 9);
-               if ((segments[i].last_sect >= (PAGE_SIZE >> 9)) ||
+               if ((segments[i].last_sect >= (XEN_PAGE_SIZE >> 9)) ||
                    (segments[i].last_sect < segments[i].first_sect)) {
                        rc = -EINVAL;
                        goto unmap;
@@ -1210,6 +1210,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 
        req_operation = req->operation == BLKIF_OP_INDIRECT ?
                        req->u.indirect.indirect_op : req->operation;
+
        if ((req->operation == BLKIF_OP_INDIRECT) &&
            (req_operation != BLKIF_OP_READ) &&
            (req_operation != BLKIF_OP_WRITE)) {
@@ -1268,7 +1269,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
                        seg[i].nsec = req->u.rw.seg[i].last_sect -
                                req->u.rw.seg[i].first_sect + 1;
                        seg[i].offset = (req->u.rw.seg[i].first_sect << 9);
-                       if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) ||
+                       if ((req->u.rw.seg[i].last_sect >= (XEN_PAGE_SIZE >> 9)) ||
                            (req->u.rw.seg[i].last_sect <
                             req->u.rw.seg[i].first_sect))
                                goto fail_response;

diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 45a044a53d1e562db4e606623840d0c667aa56e3..68e87a037b992df8c64d6894719b5b390ef1d10a 100644 (file)
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -39,6 +39,7 @@
 #include <asm/pgalloc.h>
 #include <asm/hypervisor.h>
 #include <xen/grant_table.h>
+#include <xen/page.h>
 #include <xen/xenbus.h>
 #include <xen/interface/io/ring.h>
 #include <xen/interface/io/blkif.h>
@@ -51,12 +52,20 @@ extern unsigned int xen_blkif_max_ring_order;
  */
 #define MAX_INDIRECT_SEGMENTS 256
 
-#define SEGS_PER_INDIRECT_FRAME \
-       (PAGE_SIZE/sizeof(struct blkif_request_segment))
+/*
+ * Xen use 4K pages. The guest may use different page size (4K or 64K)
+ * Number of Xen pages per segment
+ */
+#define XEN_PAGES_PER_SEGMENT   (PAGE_SIZE / XEN_PAGE_SIZE)
+
+#define XEN_PAGES_PER_INDIRECT_FRAME \
+       (XEN_PAGE_SIZE/sizeof(struct blkif_request_segment))
+#define SEGS_PER_INDIRECT_FRAME        \
+       (XEN_PAGES_PER_INDIRECT_FRAME / XEN_PAGES_PER_SEGMENT)
+
 #define MAX_INDIRECT_PAGES \
        ((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
-#define INDIRECT_PAGES(_segs) \
-       ((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
+#define INDIRECT_PAGES(_segs) DIV_ROUND_UP(_segs, XEN_PAGES_PER_INDIRECT_FRAME)
 
 /* Not a real protocol.  Used to generate ring structs which contain
  * the elements common to all protocols only.  This way we get a

diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 767657565de64e73f61304741fe9f39c496a2892..01c6b41de4e533a099864cd79f956992ca26a84e 100644 (file)
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -176,21 +176,24 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref,
        {
                struct blkif_sring *sring;
                sring = (struct blkif_sring *)blkif->blk_ring;
-               BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE * nr_grefs);
+               BACK_RING_INIT(&blkif->blk_rings.native, sring,
+                              XEN_PAGE_SIZE * nr_grefs);
                break;
        }
        case BLKIF_PROTOCOL_X86_32:
        {
                struct blkif_x86_32_sring *sring_x86_32;
                sring_x86_32 = (struct blkif_x86_32_sring *)blkif->blk_ring;
-               BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, PAGE_SIZE * nr_grefs);
+               BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32,
+                              XEN_PAGE_SIZE * nr_grefs);
                break;
        }
        case BLKIF_PROTOCOL_X86_64:
        {
                struct blkif_x86_64_sring *sring_x86_64;
                sring_x86_64 = (struct blkif_x86_64_sring *)blkif->blk_ring;
-               BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, PAGE_SIZE * nr_grefs);
+               BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64,
+                              XEN_PAGE_SIZE * nr_grefs);
                break;
        }
        default: