Commit 67de5dfb authored by Julien Grall's avatar Julien Grall Committed by David Vrabel

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: default avatarJulien Grall <julien.grall@citrix.com>
Acked-by: default avatar"Roger Pau Monné" <roger.pau@citrix.com>
Signed-off-by: default avatarDavid Vrabel <david.vrabel@citrix.com>
parent c004a6fe
...@@ -961,7 +961,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req, ...@@ -961,7 +961,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req,
seg[n].nsec = segments[i].last_sect - seg[n].nsec = segments[i].last_sect -
segments[i].first_sect + 1; segments[i].first_sect + 1;
seg[n].offset = (segments[i].first_sect << 9); 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)) { (segments[i].last_sect < segments[i].first_sect)) {
rc = -EINVAL; rc = -EINVAL;
goto unmap; goto unmap;
...@@ -1210,6 +1210,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, ...@@ -1210,6 +1210,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
req_operation = req->operation == BLKIF_OP_INDIRECT ? req_operation = req->operation == BLKIF_OP_INDIRECT ?
req->u.indirect.indirect_op : req->operation; req->u.indirect.indirect_op : req->operation;
if ((req->operation == BLKIF_OP_INDIRECT) && if ((req->operation == BLKIF_OP_INDIRECT) &&
(req_operation != BLKIF_OP_READ) && (req_operation != BLKIF_OP_READ) &&
(req_operation != BLKIF_OP_WRITE)) { (req_operation != BLKIF_OP_WRITE)) {
...@@ -1268,7 +1269,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, ...@@ -1268,7 +1269,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
seg[i].nsec = req->u.rw.seg[i].last_sect - seg[i].nsec = req->u.rw.seg[i].last_sect -
req->u.rw.seg[i].first_sect + 1; req->u.rw.seg[i].first_sect + 1;
seg[i].offset = (req->u.rw.seg[i].first_sect << 9); 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].last_sect <
req->u.rw.seg[i].first_sect)) req->u.rw.seg[i].first_sect))
goto fail_response; goto fail_response;
......
...@@ -39,6 +39,7 @@ ...@@ -39,6 +39,7 @@
#include <asm/pgalloc.h> #include <asm/pgalloc.h>
#include <asm/hypervisor.h> #include <asm/hypervisor.h>
#include <xen/grant_table.h> #include <xen/grant_table.h>
#include <xen/page.h>
#include <xen/xenbus.h> #include <xen/xenbus.h>
#include <xen/interface/io/ring.h> #include <xen/interface/io/ring.h>
#include <xen/interface/io/blkif.h> #include <xen/interface/io/blkif.h>
...@@ -51,12 +52,20 @@ extern unsigned int xen_blkif_max_ring_order; ...@@ -51,12 +52,20 @@ extern unsigned int xen_blkif_max_ring_order;
*/ */
#define MAX_INDIRECT_SEGMENTS 256 #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 \ #define MAX_INDIRECT_PAGES \
((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME) ((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
#define INDIRECT_PAGES(_segs) \ #define INDIRECT_PAGES(_segs) DIV_ROUND_UP(_segs, XEN_PAGES_PER_INDIRECT_FRAME)
((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
/* Not a real protocol. Used to generate ring structs which contain /* Not a real protocol. Used to generate ring structs which contain
* the elements common to all protocols only. This way we get a * the elements common to all protocols only. This way we get a
......
...@@ -176,21 +176,24 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref, ...@@ -176,21 +176,24 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref,
{ {
struct blkif_sring *sring; struct blkif_sring *sring;
sring = (struct blkif_sring *)blkif->blk_ring; 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; break;
} }
case BLKIF_PROTOCOL_X86_32: case BLKIF_PROTOCOL_X86_32:
{ {
struct blkif_x86_32_sring *sring_x86_32; struct blkif_x86_32_sring *sring_x86_32;
sring_x86_32 = (struct blkif_x86_32_sring *)blkif->blk_ring; 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; break;
} }
case BLKIF_PROTOCOL_X86_64: case BLKIF_PROTOCOL_X86_64:
{ {
struct blkif_x86_64_sring *sring_x86_64; struct blkif_x86_64_sring *sring_x86_64;
sring_x86_64 = (struct blkif_x86_64_sring *)blkif->blk_ring; 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; break;
} }
default: default:
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment